Mapping LUCAS topsoil chemical properties at European scale using Gaussian process regression

Investigation of spatially varying relationships between cadmium accumulation and potential controlling factors in the topsoil of island of Ireland based on spatial machine learning approaches

BACKGROUND

Cadmium (Cd) contamination in soils is a pressing environmental issue due to its toxicity and persistence. Given the diverse geological formations and intensive agricultural activities in Ireland, understanding the distribution and sources of soil Cd is particularly important.

METHODS

This study used multiple GIS-based and spatial machine learning (SML) techniques to investigate the spatial distribution and controlling factors of Cd in 16,783 topsoil samples across the island of Ireland. Three analytical methods were applied: hot spot analysis to detect clusters of high and low Cd concentrations, Geographically Weighted Pearson Correlation Coefficients (GWPCC) to explore how Cd relationships with other soil properties vary across space, and Random Forest (RF) to rank the contributing factors in Cd accumulation.

RESULTS

Hot spot analysis revealed strong spatial overlap between Cd concentrations and key geochemical variables including CIA, Fe, P, pH, SOC, and Zn. GWPCC further highlighted their spatially varying relationships, with significantly strong positive correlations between Cd and pH, Zn, and P in the central midlands. The local correlation coefficients obtained from the GWPCC ranged from negative to the highest values of 0.80, 0.92 and 0.86, respectively, which were significantly higher than the results of traditional Pearson correlation coefficients. These patterns were associated with impure limestones, Zn mineralization, and phosphate fertilizer inputs. Furthermore, the RF model ranked Zn (39.4 %) and P (17.6 %) as the most influential factors, with their importance increasing in limestone-dominated areas (50.9 % and 27.4 %), which emphasized the external contributions from local Zn mineralization and phosphate fertilizers in addition to natural accumulation.

CONCLUSION

This study demonstrated the effectiveness of integrating SML techniques with geochemical analysis for identifying Cd sources in the topsoil of Ireland, highlighting the roles of lithology and agricultural activities in Cd accumulation. The results provided valuable insights for contamination management and environmental policy development in Ireland and elsewhere.

Prediction of zinc, cadmium, and arsenic in european soils using multi-end machine learning models

Heavy metal contamination in soil is a major environmental and public health concern, especially in regions with substantial industrial and agricultural activities. Conventional predictive models often focus on single contaminants, limiting their utility for comprehensive environmental monitoring. This study addressed these limitations by developing an advanced multi-end ensemble convolutional neural network model capable of simultaneously predicting the concentrations of cadmium, arsenic, and zinc in European soils. A comprehensive dataset with 18 diverse factors was prepared, including soil properties, climatic factors, and anthropogenic activities. Moreover, the model compared four ensemble learning techniques in contamination prediction, including simple averaging, snapshot ensembles, integrated stacking, and separate stacking. Among these, the separate stacking model with random forest regressor meta-model achieved the highest accuracy, with a mean spared error of 0.0378, a mean absolute error of 0.0785, and a coefficient of determination of 0.79 in the testing phases. Sensitivity analysis highlighted farming area, road length, nitrogen content, and mean annual temperature as key factors influencing metal concentrations. To enhance accessibility, a GUI-based web application was developed, allowing users to enter relevant factors and receive real-time predictions of contamination levels. This application empowers stakeholders, such as environmental regulators and policymakers, to make informed, data-driven decisions for targeted remediation. These findings underscore the critical role of integrated machine learning approaches in environmental science, offering a powerful tool for identifying contamination hotspots, supporting soil health management, and promoting sustainable land use.

Integrated analysis of characteristic volatile flavor formation mechanisms in probiotic co-fermented cheese by untargeted metabolomics and sensory predictive modeling

The aroma components and sensory characteristics of fresh cheese fermented with three novel probiotics (Lacticaseibacillus rhamnosus B6, Limosilactobacillus fermentum B44, and Lacticaseibacillus rhamnosus KF7) were investigated using an omics approach based on HS-SPME-GC-TOFMS. Multi-dimensional and single-dimensional predictive mathematical models were developed to analyze the relationship between sensory scores and characteristic compounds. The results demonstrated that the three probiotics significantly influenced the volatile metabolite composition and sensory properties of fresh cheese. Totally 16 key aroma compounds (OAV ≥ 1) were identified. Based on OAV and (O) PLS-DA, 4, 7, and 4 significantly upregulated key aroma compounds were detected in the B6, B44, and KF7 groups, respectively. The metabolic pathways of these key compounds were reconstructed, revealing their association with fatty acid β-oxidation, aromatic amino acid metabolism, glycolysis, and esterification. L. fermentum B44, L. rhamnosus KF7, and L. rhamnosus B6 promoted the production of favorable key volatiles, altering flavor profiles. The samples of B6, B44, and KF7 groups exhibited distinct flavor characteristics described as "milk odor", "cheese odor", and "lactic odor", respectively, with the B44 sample achieving the highest overall acceptance. A natural logarithm-based partial least squares regression model was optimized, and the suitability of a nonparametric Bayesian Gaussian regression model for fitting sensory scores was confirmed. Among the identified compounds, 1-pentanol emerged as the most likely sensory score marker. This study elucidated the mechanisms underlying the formation of characteristic flavors and metabolites in probiotic fresh cheese and provided a reliable correlation model to support flavor regulation and quality control.

Multiple independent MGR5 alleles contribute to a clinal pattern in leaf magnesium across the distribution of Arabidopsis thaliana

Magnesium (Mg) is a crucial element in plants, particularly for photosynthesis. Mg homeostasis is influenced by environmental and genetic factors, and our understanding of its variation in natural populations remains incomplete. We examine the variation in leaf Mg accumulation across the distribution of Arabidopsis thaliana, and we investigate the environmental and genetic factors associated with Mg levels. Using genome-wide association studies in both the widespread Eurasian population and a local-scale population in Cape Verde, we identify genetic factors associated with variation in leaf Mg. We validate our main results, including effect size estimates, using Clustered Regularly Interspaced Short Palindromic Repeats (CRISPR) mutagenesis. Our findings reveal a significant association between leaf Mg and latitude of origin. In Eurasia, we find a signal at the nutrient-response regulator, RAPTOR1A, and across the species range, we find that multiple alleles of the Mg transporter, MAGNESIUM RELEASE 5 (MGR5), underlie variation in leaf Mg and contribute to the observed latitudinal cline. Overall, our results indicate that the spatial distribution of leaf Mg in A. thaliana is affected by climatic and genetic factors, resulting in a latitudinal cline. Further, they show an example of allelic heterogeneity, in which multiple alleles at a single locus contribute to a trait and the formation of a phenotypic cline.

A partitioned conditioned Latin hypercube sampling method considering spatial heterogeneity in digital soil mapping

The design of sampling methods is crucial in digital soil mapping for soil organic carbon (SOC), as it directly affects prediction precision and reliability. While sampling methods based on environmental variables are widely used, the spatial heterogeneity of soil properties poses challenges by introducing variability in influential driving factors across subregions, potentially reducing prediction accuracy. To address this, a partitioned conditioned Latin hypercube sampling (PcLHS) method explicitly considering spatial heterogeneity is proposed. PcLHS first employs the regionalization with dynamically constrained agglomerative clustering and partitioning (REDCAP) method to partition the study area into relatively homogeneous subregions. Key environmental variables are then identified using the Boruta and the Variance Inflation Factor method, followed by conditioned Latin hypercube sampling (cLHS) to select training points within each subregion. Finally, the selected training points are combined to form the complete training dataset. A case study on SOC sampling in northeastern France demonstrated that PcLHS consistently outperformed traditional sampling methods, achieving lower root mean square error (RMSE, 0.40-0.43), higher coefficient of determination (R2, 0.36-0.44), and improved concordance correlation coefficient (CCC, 0.58-0.63). Compared to other methods, PcLHS reduced RMSE by 4-11%, increased R2 by 18-46%, and improved CCC by 14-29%. These results highlight the necessity of considering spatial heterogeneity in soil sampling design and establish PcLHS as an effective method for SOC prediction in heterogeneous landscapes.

Global and regional patterns of soil metal(loid) mobility and associated risks

Soil contamination by metals and metalloids (metal[loid]s) is a global issue with significant risks to human health, ecosystems, and food security. Accurate risk assessment depends on understanding metal(loid) mobility, which dictates bioavailability and environmental impact. Here we show a theory-guided machine learning model that predicts soil metal(loid) fractionation across the globe. Our model identifies total metal(loid) content and soil organic carbon as primary drivers of metal(loid) mobility. We find that 37% of the world's land is at medium-to-high mobilization risk, with hotspots in Russia, Chile, Canada, and Namibia. Our analysis indicates that global efforts to enhance soil carbon sequestration may inadvertently increase metal(loid) mobility. Furthermore, in Europe, the divergence between spatial distributions of total and mobile metal(loid)s is uncovered. These findings offer crucial insights into global distributions and drivers of soil metal(loid) mobility, providing a robust tool for prioritizing metal(loid) mobility testing, raising awareness, and informing sustainable soil management practices.

Revisiting the soil carbon saturation concept to inform a risk index in European agricultural soils

The form in which soil organic carbon (SOC) is stored determines its capacity and stability, commonly described by separating bulk SOC into its particulate- (POC) and mineral-associated (MAOC) constituents. MAOC is more persistent, but the association with mineral surfaces imposes a maximum MAOC capacity for a given fine fraction content. Here, we leverage SOC fraction data and spectroscopy to investigate POC/MAOC distribution, together with SOC changes data over 2009-2018 period, across pedo-climatic zones in the European Union and the UK. We find that rather than a universal mineralogy- dependent maximum MAOC capacity, an emergent effective MAOC capacity can be identified across pedo-climatic zones. These findings led us to propose the SOC risk index, combining SOC changes and effective MAOC capacity. We find that between 43 and 83 Mha of agricultural soils are classified as high risk, mostly constrained to cool and humid regions. The index provides a synthetic information to decision makers for preserving and accruing POC and MAOC.

Soil phosphorus stocks could prolong global reserves and improve water quality

Combining existing databases, we estimated global phosphorus stocks in croplands and grasslands that are not readily available to plants as 32-41% of the 2020 estimated geologic phosphorus reserves, representing 146-186 years of the 2020 mass of phosphorus fertilizer applied annually. Especially if accessed by more efficient crops, this stock could reduce the need for additional fertilizer, improve water quality and contribute to all-round phosphorus sustainability.

Mapping the exposure to outdoor radon in the German population

INTRODUCTION

Data on outdoor radon are generally scarce compared to indoor radon. However, knowledge of the spatial distribution of outdoor radon is necessary to estimate the overall exposure of the population to radon, it supports the prediction of indoor radon and characterizes the natural radon background. Germany has a comprehensive dataset on long-term outdoor radon concentration and the equilibrium factor at national level, which allowed to produce what is probably the only spatially continuous outdoor radon map at national level so far.

DATA

In this study, outdoor radon concentration measurement data (n = 172) and equilibrium factors (n = 25) from a national survey from 2003 to 2006 were reanalyzed using state-of-the-art machine learning routines. Spatially comprehensive maps of distance to the sea, radon concentration in soil, sand content in topsoil and a terrain-based wind exposure index are used as predictors.

METHODS

Quantile regression forest was used to map the conditional distribution of outdoor radon concentration at 500 m grid resolution. The equilibrium factor was mapped using a linear regression model. Both maps were combined to derive the equivalent outdoor radon equilibrium concentration. Population weighting of the results was achieved by explicitly accounting for the population distribution using a probabilistic sampling procedure from the estimated conditional distributions.

RESULTS

The arithmetic mean and the interquartile range (25th to 75th percentile) for the population-weighted outdoor radon concentration for Germany are 9.3 Bq/m³ and 5.8 Bq/m³ to 11.2 Bq/m³, respectively. The mean equilibrium factor is 0.49. The arithmetic mean and the interquartile range (25th to 75th percentile) for the population-weighted outdoor radon equilibrium equivalent concentration are 4.7 Bq/m³ and 2.7 Bq/m³ to 5.9 Bq/m³ respectively. The estimated inhalation dose due to outdoor exposure to radon is 0.056 mSv/a (arithmetic mean), with less than 10 % of the population exceeding a value of 0.1 mSv/a. The unavoidable inhalation dose due to radon exposure (outdoors plus indoors) in Germany is estimated at an arithmetic mean of 0.37 mSv/a. The spatial distribution of radon outdoors is mainly determined by the distance to the sea. The predictors radon concentration in soil, sand in topsoil and wind exposure still have a significant influence, especially at local to regional level.

CONCLUSION

Knowledge about the spatial distribution of outdoor radon and its local variability for Germany was improved using a modern regression technique and relevant predictive information. The results confirm a low outdoor radon concentration with a small contribution to the effective dose received by the population from outdoor radon exposure.

Is soil contamination a missing driver of soil heterotrophic respiration in land surface models? A study case with copper

Land Surface Models (LSMs) are crucial elements of Earth System Models used to estimate the effects of anthropogenic greenhouse gas (GHG) emissions on Earth's climate. Nevertheless, as well as land use change and direct GHG emissions, anthropogenic activities are also associated with contaminant emissions and depositions. Although contamination has a recognized impact on soil processes such as GHG emissions, soil contamination is currently not considered as an important process to consider into LSMs. In this study we hypothesized that soil contamination has significant impact on soil CO2 emissions such as heterotrophic respiration (Rh). To this end, we analyzed how soil contamination may account for residuals of modeled Rh from 11 LSMs as compared to Rh products derived from observations over Europe. We used generalized least squared mixed models to evaluate the primary factors driving of the model residuals. Among contaminants, we focused on copper (Cu), which is widely used in industry or agriculture, causing significant diffuse contamination. Additionally, research demonstrated a strong correlation between soil Rh and Cu availability to soil fauna and various soil pedological and climatic parameters. Hence, we completed our analysis by including pedo-environmental parameters and by analyzing Rh against a proxy of bioavailable Cu. Our findings indicate that Cu is a non-negligible variable in explaining the Rh models inaccuracy considering either total or free Cu forms. Therefore, it can be concluded that Cu should not be disregarded as a key factor in predicting Rh.

Quantifying the impact of an abrupt reduction in mineral nitrogen fertilization on crop yield in the European Union

Contemporary crop production in Europe relies on nitrogen (N) fertilization. Fertilizer prices soared in 2021-2022, and remained at historical high levels in 2023. These high prices invoked an immediate concern on the possible consequences for Europe's food production. In this study, we use a biogeochemical model framework to estimate the impact of reducing mineral N fertilization on crop yields in the European Union (EU). First, crop yields simulated with the biogeochemical DayCent model are evaluated against subnational yield data averaged for 2015-2018 reported by Eurostat and National Statistical Institutes in the EU for soft wheat, barley, grain maize and rapeseed. Then, we simulate three different scenarios where mineral N fertilization across the EU is abruptly reduced by respectively 5, 15 and 25 %, and compare yields to the projected baseline for contemporary conditions (2019-2022). The model evaluation gives r2 values ranging from 0.28 (rapeseed) to 0.61 (soft wheat) and root mean square errors (RMSE) ranging from 0.6 (rapeseed) to 1.95 t ha-1 (maize). The model shows a reduction in yield per crop at the EU level up to 2.1, 6.4 and 11.2 % with the 5, 15 and 25 % reduction scenario, respectively. Different crops show different percentage reduction in yield following a reduction in mineral N fertilization, showing a legacy effect over the years and depending on the availability of organic fertilizer. The strongest relative yield reduction occurs for soft wheat for all three scenarios. Even with 25 % drop in mineral N fertilization, maize yield in the Netherlands, Belgium and Denmark is not significantly reduced, because of the high N surplus and large share of organic fertilization in these countries. This process-based modelling study provides spatially explicit, high resolution information on the response of crop yields to N fertilizer input reductions, helping policy-makers in decision-making on food security and environmentally-friendly food systems.

Future land use maps for the Netherlands based on the Dutch One Health Shared Socio-economic Pathways

To enable detailed study of a wide variety of future health challenges, we have created future land use maps for the Netherlands for 2050, based on the Dutch One Health Shared Socio-economic Pathways (SSPs). This was done using the DynaCLUE modelling framework. Future land use is based on altitude, soil properties, groundwater, salinity, flood risk, agricultural land price, distance to transport hubs and climate. We also account for anticipated demand for different land use types, historic land use changes and potential spatial restrictions. These land use maps can be used to model many different health risks to people, animals and the environment, such as disease, water quality and pollution. In addition, the Netherlands can serve as an example for other rapidly urbanising deltas where many of the health risks will be similar.

Pilot scale on-site demonstration and seasonality assessment of nitrogen recovery and water reclamation from pig's slurry liquid fraction

Livestock slurry has gathered significant interest as a secondary raw material for fertilisers industry due to its content on macronutrients -nitrogen, phosphorous, and potassium- and organic carbon. In this study, the performance of an on-site pilot plant composed by microfiltration, membrane-assisted stripping, and reverse osmosis for selective recovery of nitrogen as fertiliser and water reclamation was demonstrated for 2 years in a pig farm, referenced to 8 batches for seasonal assessment. Microfiltration mitigated the seasonal variation in the composition of pig slurry leading to stable process efficiency in the following steps. Membrane-assisted stripping resulted in the recovery of up to 56% of nitrogen as high-purity ammonium sulphate, and up to 42% of reclaimed water as reverse osmosis permeate. The proposed train of technologies reported proper performance and robustness during the whole demonstration period as it resulted in the production of reclaimed water and ammonium sulphate with no significant quality variations. The energy cost for both products obtained in this study was found in the average of the previous works reviewed with 12.49 kWh kg-1 NH3 produced, and 0.37 kWh m-3 of reclaimed water. The environmental assessment showed that nitrogen losses could be reduced by up to 90 kg N ha-1 d-1 by replacing manure spreading with precise fertilisation techniques, enabled by the selective recovery of nitrogen from SLF. Finally, the financial study showed that the scaling up of the proposed train of technologies would result in benefits for farms with more than 1600 pig heads.

Identifying the spatial pattern and driving factors of nitrate in groundwater using a novel framework of interpretable stacking ensemble learning

Groundwater nitrate contamination poses a potential threat to human health and environmental safety globally. This study proposes an interpretable stacking ensemble learning (SEL) framework for enhancing and interpreting groundwater nitrate spatial predictions by integrating the two-level heterogeneous SEL model and SHapley Additive exPlanations (SHAP). In the SEL model, five commonly used machine learning models were utilized as base models (gradient boosting decision tree, extreme gradient boosting, random forest, extremely randomized trees, and k-nearest neighbor), whose outputs were taken as input data for the meta-model. When applied to the agricultural intensive area, the Eden Valley in the UK, the SEL model outperformed the individual models in predictive performance and generalization ability. It reveals a mean groundwater nitrate level of 2.22 mg/L-N, with 2.46% of sandstone aquifers exceeding the drinking standard of 11.3 mg/L-N. Alarmingly, 8.74% of areas with high groundwater nitrate remain outside the designated nitrate vulnerable zones. Moreover, SHAP identified that transmissivity, baseflow index, hydraulic conductivity, the percentage of arable land, and the C:N ratio in the soil were the top five key driving factors of groundwater nitrate. With nitrate threatening groundwater globally, this study presents a high-accuracy, interpretable, and flexible modeling framework that enhances our understanding of the mechanisms behind groundwater nitrate contamination. It implies that the interpretable SEL framework has great promise for providing valuable evidence for environmental management, water resource protection, and sustainable development, particularly in the data-scarce area.

Soil health is associated with higher primary productivity across Europe

Soil health is expected to be of key importance for plant growth and ecosystem functioning. However, whether soil health is linked to primary productivity across environmental gradients and land-use types remains poorly understood. To address this gap, we conducted a pan-European field study including 588 sites from 27 countries to investigate the link between soil health and primary productivity across three major land-use types: woodlands, grasslands and croplands. We found that mean soil health (a composite index based on soil properties, biodiversity and plant disease control) in woodlands was 31.4% higher than in grasslands and 76.1% higher than in croplands. Soil health was positively linked to cropland and grassland productivity at the continental scale, whereas climate best explained woodland productivity. Among microbial diversity indicators, we observed a positive association between the richness of Acidobacteria, Firmicutes and Proteobacteria and primary productivity. Among microbial functional groups, we found that primary productivity in croplands and grasslands was positively related to nitrogen-fixing bacteria and mycorrhizal fungi and negatively related to plant pathogens. Together, our results point to the importance of soil biodiversity and soil health for maintaining primary productivity across contrasting land-use types.

Stage dependence of Elton's biotic resistance hypothesis of biological invasions

Elton's biotic resistance hypothesis posits that species-rich communities are more resistant to invasion. However, it remains unknown how species, phylogenetic and functional richness, along with environmental and human-impact factors, collectively affect plant invasion as alien species progress along the introduction-naturalization-invasion continuum. Using data from 12,056 local plant communities of the Czech Republic, this study reveals varying effects of these factors on the presence and richness of alien species at different invasion stages, highlighting the complexity of the invasion process. Specifically, we demonstrate that although species richness and functional richness of resident communities had mostly negative effects on alien species presence and richness, the strength and sometimes also direction of these effects varied along the continuum. Our study not only underscores that evidence for or against Elton's biotic resistance hypothesis may be stage-dependent but also suggests that other invasion hypotheses should be carefully revisited given their potential stage-dependent nature.

Development of a High-Resolution Indoor Radon Map Using a New Machine Learning-Based Probabilistic Model and German Radon Survey Data

BACKGROUND

Radon is a carcinogenic, radioactive gas that can accumulate indoors and is undetected by human senses. Therefore, accurate knowledge of indoor radon concentration is crucial for assessing radon-related health effects or identifying radon-prone areas.

OBJECTIVES

Indoor radon concentration at the national scale is usually estimated on the basis of extensive measurement campaigns. However, characteristics of the sampled households often differ from the characteristics of the target population owing to the large number of relevant factors that control the indoor radon concentration, such as the availability of geogenic radon or floor level. Furthermore, the sample size usually does not allow estimation with high spatial resolution. We propose a model-based approach that allows a more realistic estimation of indoor radon distribution with a higher spatial resolution than a purely data-based approach.

METHODS

A multistage modeling approach was used by applying a quantile regression forest that uses environmental and building data as predictors to estimate the probability distribution function of indoor radon for each floor level of each residential building in Germany. Based on the estimated probability distribution function, a probabilistic Monte Carlo sampling technique was applied, enabling the combination and population weighting of floor-level predictions. In this way, the uncertainty of the individual predictions is effectively propagated into the estimate of variability at the aggregated level.

RESULTS

The results show an approximate lognormal distribution of indoor radon in dwellings in Germany with an arithmetic mean of 63  Bq / m 3 , a geometric mean of 41  Bq / m 3 , and a 95th percentile of 180  Bq / m 3 . The exceedance probabilities for 100 and 300  Bq / m 3 are 12.5% (10.5 million people affected) and 2.2% (1.9 million people affected), respectively. In large cities, individual indoor radon concentration is generally estimated to be lower than in rural areas, which is due to the different distribution of the population on floor levels.

DISCUSSION

The advantages of our approach are that is yields a) an accurate estimation of indoor radon concentration even if the survey is not fully representative with respect to floor level and radon concentration in soil, and b) an estimate of the indoor radon distribution with a much higher spatial resolution than basic descriptive statistics. https://doi.org/10.1289/EHP14171.

Potential migration pathways of broadleaved trees across the receding boreal biome under future climate change

Climate change has triggered poleward expansions in the distributions of various taxonomic groups, including tree species. Given the ecological significance of trees as keystone species in forests and their socio-economic importance, projecting the potential future distributions of tree species is crucial for devising effective adaptation strategies for both biomass production and biodiversity conservation in future forest ecosystems. Here, we fitted physiographically informed habitat suitability models (HSMs) at 50-m resolution across Sweden (55-68° N) to estimate the potential northward expansion of seven broadleaved tree species within their leading-edge distributions in Europe under different future climate change scenarios and for different time periods. Overall, we observed that minimum temperature was the most crucial variable for comprehending the spatial distribution of broadleaved tree species at their cold limits. Our HSMs projected a complex range expansion pattern for 2100, with individualistic differences among species. However, a frequent and rather surprising pattern was a northward expansion along the east coast followed by narrow migration pathways along larger valleys towards edaphically suitable areas in the north-west, where most of the studied species were predicted to expand. The high-resolution maps generated in this study offer valuable insights for our understanding of range shift dynamics at the leading edge of southern tree species as they expand into the receding boreal biome. These maps suggest areas where broadleaved tree species could already be translocated to anticipate forest and biodiversity conservation adaptation efforts in the face of future climate change.

A critical systematic review on spectral-based soil nutrient prediction using machine learning

The United Nations (UN) emphasizes the pivotal role of sustainable agriculture in addressing persistent starvation and working towards zero hunger by 2030 through global development. Intensive agricultural practices have adversely impacted soil quality, necessitating soil nutrient analysis for enhancing farm productivity and environmental sustainability. Researchers increasingly turn to Artificial Intelligence (AI) techniques to improve crop yield estimation and optimize soil nutrition management. This study reviews 155 papers published from 2014 to 2024, assessing the use of machine learning (ML) and deep learning (DL) in predicting soil nutrients. It highlights the potential of hyperspectral and multispectral sensors, which enable precise nutrient identification through spectral analysis across multiple bands. The study underscores the importance of feature selection techniques to improve model performance by eliminating redundant spectral bands with weak correlations to targeted nutrients. Additionally, the use of spectral indices, derived from mathematical ratios of spectral bands based on absorption spectra, is examined for its effectiveness in accurately predicting soil nutrient levels. By evaluating various performance measures and datasets related to soil nutrient prediction, this paper offers comprehensive insights into the applicability of AI techniques in optimizing soil nutrition management. The insights gained from this review can inform future research and policy decisions to achieve global development goals and promote environmental sustainability.

Evaluation of the prediction effectiveness for geochemical mapping using machine learning methods: A case study from northern Guangdong Province in China

This study compares seven machine learning models to investigate whether they improve the accuracy of geochemical mapping compared to ordinary kriging (OK). Arsenic is widely present in soil due to human activities and soil parent material, posing significant toxicity. Predicting the spatial distribution of elements in soil has become a current research hotspot. Lianzhou City in northern Guangdong Province, China, was chosen as the study area, collecting a total of 2908 surface soil samples from 0 to 20 cm depth. Seven machine learning models were chosen: Random Forest (RF), Support Vector Machine (SVM), Ridge Regression (Ridge), Gradient Boosting Decision Tree (GBDT), Artificial Neural Network (ANN), K-Nearest Neighbors (KNN), and Gaussian Process Regression (GPR). Exploring the advantages and disadvantages of machine learning and traditional geological statistical models in predicting the spatial distribution of heavy metal elements, this study also analyzes factors affecting the accuracy of element prediction. The two best-performing models in the original model, RF (R2 = 0.445) and GBDT (R2 = 0.414), did not outperform OK (R2 = 0.459) in terms of prediction accuracy. Ridge and GPR, the worst-performing methods, have R2 values of only 0.201 and 0.248, respectively. To improve the models' prediction accuracy, a spatial regionalized (SR) covariate index was added. Improvements varied among different methods, with RF and GBDT increasing their R2 values from 0.4 to 0.78 after enhancement. In contrast, the GPR model showed the least significant improvement, with its R2 value only reaching 0.25 in the improved method. This study concluded that choosing the right machine learning model and considering factors that influence prediction accuracy, such as regional variations, the number of sampling points, and their distribution, are crucial for ensuring the accuracy of predictions. This provides valuable insights for future research in this area.

Acidification of European croplands by nitrogen fertilization: Consequences for carbonate losses, and soil health

Soil acidification is an ongoing problem in intensively cultivated croplands due to inefficient and excessive nitrogen (N) fertilization. We collected high-resolution data comprising 19,969 topsoil (0-20 cm) samples from the Land Use and Coverage Area frame Survey (LUCAS) of the European commission in 2009 to assess the impact of N fertilization on buffering substances such as carbonates and base cations. We have only considered the impacts of mineral fertilizers from the total added N, and a N use efficiency of 60 %. Nitrogen fertilization adds annually 6.1 × 107 kmol H+ to European croplands, leading to annual loss of 6.1 × 109 kg CaCO3. Assuming similar acidification during the next 50 years, soil carbonates will be completely removed from 3.4 × 106 ha of European croplands. In carbonate-free soils, annual loss of 2.1 × 107 kmol of basic cations will lead to strong acidification of at least 2.6 million ha of European croplands within the next 50 years. Inorganic carbon and basic cation losses at such rapid scale tremendously drop the nutrient status and production potential of croplands. Soil liming to ameliorate acidity increases pH only temporarily and with additional financial and environmental costs. Only the direct loss of soil carbonate stocks and compensation of carbonate-related CO2 correspond to about 1.5 % of the proposed budget of the European commission for 2023. Thus, controlling and decreasing soil acidification is crucial to avoid degradation of agricultural soils, which can be done by adopting best management practices and increasing nutrient use efficiency. Regular screening or monitoring of carbonate and base cations contents, especially for soils, where the carbonate stocks are at critical levels, are urgently necessary.

A unifying modelling of multiple land degradation pathways in Europe

Land degradation is a complex socio-environmental threat, which generally occurs as multiple concurrent pathways that remain largely unexplored in Europe. Here we present an unprecedented analysis of land multi-degradation in 40 continental countries, using twelve dataset-based processes that were modelled as land degradation convergence and combination pathways in Europe's agricultural (and arable) environments. Using a Land Multi-degradation Index, we find that up to 27%, 35% and 22% of continental agricultural (~2 million km2) and arable (~1.1 million km2) lands are currently threatened by one, two, and three drivers of degradation, while 10-11% of pan-European agricultural/arable landscapes are cumulatively affected by four and at least five concurrent processes. We also explore the complex pattern of spatially interacting processes, emphasizing the major combinations of land degradation pathways across continental and national boundaries. Our results will enable policymakers to develop knowledge-based strategies for land degradation mitigation and other critical European sustainable development goals.

Effects of climate on the distribution and conservation of commonly observed European earthworms

Belowground biodiversity distribution does not necessarily reflect aboveground biodiversity patterns, but maps of soil biodiversity remain scarce because of limited data availability. Earthworms belong to the most thoroughly studied soil organisms and-in their role as ecosystem engineers-have a significant impact on ecosystem functioning. We used species distribution modeling (SDMs) and available data sets to map the spatial distribution of commonly observed (i.e., frequently recorded) earthworm species (Annelida, Oligochaeta) across Europe under current and future climate conditions. First, we predicted potential species distributions with commonly used models (i.e., MaxEnt and Biomod) and estimated total species richness (i.e., number of species in a 5 × 5 km grid cell). Second, we determined how much the different types of protected areas covered predicted earthworm richness and species ranges (i.e., distributions) by estimating the respective proportion of the range area. Earthworm species richness was high in central western Europe and low in northeastern Europe. This pattern was mainly associated with annual mean temperature and precipitation seasonality, but the importance of predictor variables to species occurrences varied among species. The geographical ranges of the majority of the earthworm species were predicted to shift to eastern Europe and partly decrease under future climate scenarios. Predicted current and future ranges were only poorly covered by protected areas, such as national parks. More than 80% of future earthworm ranges were on average not protected at all (mean [SD] = 82.6% [0.04]). Overall, our results emphasize the urgency of considering especially vulnerable earthworm species, as well as other soil organisms, in the design of nature conservation measures.

Phosphorus applications adjusted to optimal crop yields can help sustain global phosphorus reserves

With the longevity of phosphorus reserves uncertain, distributing phosphorus to meet food production needs is a global challenge. Here we match plant-available soil Olsen phosphorus concentrations to thresholds for optimal productivity of improved grassland and 28 of the world's most widely grown and valuable crops. We find more land (73%) below optimal production thresholds than above. We calculate that an initial capital application of 56,954 kt could boost soil Olsen phosphorus to their threshold concentrations and that 28,067 kt yr-1 (17,500 kt yr-1 to cropland) could maintain these thresholds. Without additional reserves becoming available, it would take 454 years at the current rate of application (20,500 kt yr-1) to exhaust estimated reserves (2020 value), compared with 531 years at our estimated maintenance rate and 469 years if phosphorus deficits were alleviated. More judicious use of phosphorus fertilizers to account for soil Olsen phosphorus can help achieve optimal production without accelerating the depletion of phosphorus reserves.

Fecal calcium levels of bird nestlings as a potential indicator of species-specific metal sensitivity

Sensitivity of bird species to environmental metal pollution varies but there is currently no general framework to predict species-specific sensitivity. Such information would be valuable from a conservation point-of-view. Calcium (Ca) has antagonistic effects on metal toxicity and studies with some common model species show that low dietary and circulating calcium (Ca) levels indicate higher sensitivity to harmful effects of toxic metals. Here we measured fecal Ca and five other macroelement (potassium K, magnesium Mg, sodium Na, phosphorus P, sulphur S) concentrations as proxies for dietary levels in 66 bird species to better understand their interspecific variation and potential use as an indicator of metal sensitivity in a wider range of species (the main analyses include 39 species). We found marked interspecific differences in fecal Ca concentration, which correlated positively with Mg and negatively with Na, P and S levels. Lowest Ca concentrations were found in insectivorous species and especially aerial foragers, such as swifts (Apodidae) and swallows (Hirundinidae). Instead, ground foraging species like starlings (Sturnidae), sparrows (Passeridae), cranes (Gruidae) and larks (Alaudidae) showed relatively high fecal Ca levels. Independent of phylogeny, insectivorous diet and aerial foraging seem to indicate low Ca levels and potential sensitivity to toxic metals. Our results, together with information published on fecal Ca levels and toxic metal impacts, suggest that fecal Ca levels are a promising new tool to evaluate potential metal-sensitivity of birds, and we encourage gathering such information in other bird species. Information on the effects of metals on breeding parameters in a wider range of bird species would also help in ranking species by their sensitivity to metal pollution.

Modeling arsenic in European topsoils with a coupled semiparametric (GAMLSS-RF) model for censored data

Arsenic (As) is a versatile heavy metalloid trace element extensively used in industrial applications. As is carcinogen, poses health risks through both inhalation and ingestion, and is associated with an increased risk of liver, kidney, lung, and bladder tumors. In the agricultural context, the repeated application of arsenical products leads to elevated soil concentrations, which are also affected by environmental and management variables. Since exposure to As poses risks, effective assessment tools to support environmental and health policies are needed. However, the most comprehensive soil As data available, the Land Use/Cover Area frame statistical Survey (LUCAS) database, contains severe limitations due to high detection limits. Although within International Organization for Standardization standards, the detection limits preclude the adoption of standard methodologies for data analysis. The present work focused on developing a new method to model As contamination in European soils using LUCAS soil samples. We introduce the GAMLSS-RF model, a novel approach that couples Random Forests with Generalized Additive Models for Location, Scale, and Shape. The semiparametric model can capture non-linear interactions among input variables while accommodating censored and non-censored observations and can be calibrated to include information from other campaign databases. After fitting and validating a spatial model, we produced European-scale As concentration maps at a 250 m spatial resolution and evaluated the patterns against reference values (i.e., two action levels and a background concentration). We found a significant variability of As concentration across the continent, with lower concentrations in Northern countries and higher concentrations in Portugal, Spain, Austria, France and Belgium. By overcoming limitations in existing databases and methodologies, the present approach provides an alternative way to handle highly censored data. The model also consists of a valuable probabilistic tool for assessing As contamination risks in soils, contributing to informed policy-making for environmental and health protection.

Cadmium in topsoils of the European Union - An analysis based on LUCAS topsoil database

Cadmium (Cd) is a naturally occurring element that can accumulate in the soil through the application of fertilisers containing cadmium and as a waste of industrial processes. Cadmium inputs in the soil have increased significantly (+50 %) during the 20th century as a result of the application of fertilisers and sewage sludge, and also due to local contamination (e.g. waste dumping, mining) and industrial emissions (e.g. zinc smelters). Using the 21,682 soil samples from the LUCAS soil survey, we aim to estimate the spatial distribution of the concentration of Cd in the European Union (EU) and UK topsoil. Out of the total, 72.6 % of the samples have Cd values <0.07 mg kg-1, 21.6 % in the range 0.07-1 mg kg-1 and the remaining 5.5 % higher than the threshold of 1 mg kg-1, which is generally considered the limit for risk assessment. The mean Cd value in the EU topsoils is 0.20 mg kg-1, slightly higher in grasslands (0.24 mg kg-1) compared to croplands (0.17 mg kg-1). Applying an ensemble of machine learning models supported by a variety of environmental descriptors, we created maps of Cd distribution at a resolution of 100 m. The ensemble approach included five models and increased the prediction accuracy to R2 of 0.45 (an increase of 0.1 compared to best single model performance). The approach used resulted in a high predictive power for the general Cd distribution, while also identifying hotspots of Cd contamination. Natural factors influencing Cd levels include soil properties (pH, clay), topography, soil erosion, and leaching. As anthropogenic factors, we identified phosphorus inputs to agricultural lands as the most important for Cd levels. The application of the EU Fertiliser Directive should further limit Cd inputs and potentially the Cd content in soils.

Ecological and Syntaxonomic Analysis of the Communities of Glebionis coronaria and G. discolor (Malvion neglectae) in the European Mediterranean Area

Nitrophilous communities dominated by Glebionis coronaria and Glebionis discolor in the European Mediterranean area were studied. The nomenclature was corrected according to the current taxonomy, following the International Code of Phytosociological Nomenclature (ICPN). The statistical analysis revealed six new associations and one subassociation, with four in Spain, one in Greece, and one in Italy. Additionally, a subassociation of high relevance due to its endemic character was identified. These grasslands exhibit requirements for organic matter and other edaphic nutrients that are closer to those of Malva neglecta communities than to those of Hordeum murinum subsp. leporinum. We confirmed the published syntaxon with the rank of Resedo albae-Glebionenion coronariae suballiance and its subordination to the Malvion neglectae alliance, and we established the type association for this suballiance. Sisimbrietalia officinalis J. Tüxen in Lohmeyer et al. 1962 em. Rivas-Martínez, Báscones, T. E. Díaz, Fernández-González & Loidi 1991. Stellarietea mediae Tüxen, Lohmeyer & Preising ex von Rochow 1951.

Quantitative analysis of the compliance of EU Sewage Sludge Directive by using the heavy metal concentrations from LUCAS topsoil database

In the European Union (EU), a common understanding of the potential harmful effect of sewage sludge (SS) on the environment is regulated by the Sewage Sludge Directive 86/278/EEC (SSD). Limit values (LVs) for concentrations of heavy metals in soil are listed in Impact Assessment of this directive, and they were transposed by EU member states using different criteria. Member states adopted either single limit values or based on soil factors such as pH and texture to define the maximum limit values for concentrations of heavy metals in soils. Our work presents the first quantitative analysis of the SSD at the European level by using the Land Use and Coverage Area Frame Survey (LUCAS) 2009 topsoil database. The reference values at the European level were arranged taking into account the upper value (EU_UL) and the lower value (EU_LL) for each heavy metal (arsenic, cadmium, copper, chromium, mercury, nickel, lead, and zinc) as well as taking into account the pH of the soil (cadmium, copper, mercury, nickel, lead, and zinc) as introduced in the SSD Annex IA. Single and integrated contamination rate indices were developed to identify those agricultural soils that exceeded the reference values for each heavy metal. In total, 10%, 36%, and 19% of the LUCAS 2009 topsoil samples exceeded the limit values. Additionally, 12% and 16% of agricultural soils exceeded the concentration of at least one single heavy metal when European LVs were fixed following the soil pH in Strategy II compared to those national ones in Strategy I. Generally, all member states apply similar or stricter limit values than those laid down in the SSD. Our work indicates that choosing LVs quantitatively affects further actions such as monitoring and remediation of contaminated soils. The actual soil parameters, such as heavy metal concentrations and soil pH values from the LUCAS 2009 topsoil database, could be used by SSD-involved policy stakeholders not only to lay down the LVs for concentrations of heavy metal in soils but also for monitoring the SSD compliance grade by using the LUCAS surveys over time (past and upcoming LUCAS datasets).

Assessing the phosphorus cycle in European agricultural soils: Looking beyond current national phosphorus budgets

Phosphorus (P) is an essential nutrient for all crops, yet its excess negatively affects public health, the environment, and the economy. At the same time, rock P is a critical raw material due to its importance for food production, the finite geological deposits, and its unequal regional distribution. As a consequence, nutrient management is addressed by numerous environmental policies. Process-based biogeochemical models are valuable instruments to monitor the P cycle and predict the effect of agricultural management policies. In this study, we upscale the calibrated DayCent model at European level using data-derived soil properties, advanced input data sets, and representative management practices. Our results depicted a P budget with an average P surplus (0.11 kg P ha-1 year-1), a total soil P (2240.0 kg P ha-1), and available P content (77.4 kg P ha-1) consistent with literature and national statistics. Through agricultural management scenarios, we revealed a range of potential changes in the P budget by 2030 and 2050, influenced by the interlink of P with biogeochemical carbon and nitrogen cycles. Thus, we developed a powerful assessment tool capable of i) identifying areas with P surplus or deficit at high spatial resolution of 1 km2, (ii) pinpointing areas where a change in agricultural management would be most urgent to reach policy goals in terms of environmental pollution, food security and resource efficiency of a critical raw material, and iii) assessing the response of the P cycle to modifications in agricultural management.

Development of a robust daily soil temperature estimation in semi-arid continental climate using meteorological predictors based on computational intelligent paradigms

Changes in soil temperature (ST) play an important role in the main mechanisms within the soil, including biological and chemical activities. For instance, they affect the microbial community composition, the speed at which soil organic matter breaks down and becomes minerals. Moreover, the growth and physiological activity of plants are directly influenced by the ST. Additionally, ST indirectly affects plant growth by influencing the accessibility of nutrients in the soil. Therefore, designing an efficient tool for ST estimating at different depths is useful for soil studies by considering meteorological parameters as input parameters, maximal air temperature, minimal air temperature, maximal air relative humidity, minimal air relative humidity, precipitation, and wind speed. This investigation employed various statistical metrics to evaluate the efficacy of the implemented models. These metrics encompassed the correlation coefficient (r), root mean square error (RMSE), Nash-Sutcliffe (NS) efficiency, and mean absolute error (MAE). Hence, this study presented several artificial intelligence-based models, MLPANN, SVR, RFR, and GPR for building robust predictive tools for daily scale ST estimation at 05, 10, 20, 30, 50, and 100cm soil depths. The suggested models are evaluated at two meteorological stations (i.e., Sulaimani and Dukan) located in Kurdistan region, Iraq. Based on assessment of outcomes of this study, the suggested models exhibited exceptional predictive capabilities and comparison of the results showed that among the proposed frameworks, GPR yielded the best results for 05, 10, 20, and 100cm soil depths, with RMSE values of 1.814°C, 1.652°C, 1.773°C, and 2.891°C, respectively. Also, for 50cm soil depth, MLPANN performed the best with an RMSE of 2.289°C at Sulaimani station using the RMSE during the validation phase. Furthermore, GPR produced the most superior outcomes for 10cm, 30cm, and 50cm soil depths, with RMSE values of 1.753°C, 2.270°C, and 2.631°C, respectively. In addition, for 05cm soil depth, SVR achieved the highest level of performance with an RMSE of 1.950°C at Dukan station. The results obtained in this research confirmed that the suggested models have the potential to be effectively used as daily predictive tools at different stations and various depths.

Application of nitrogen-rich sunflower husks biochar promotes methane oxidation and increases abundance of Methylobacter in nitrogen-poor soil

The area of sunflower crops is steadily increasing. A beneficial way of managing sunflower waste biomass could be its use as a feedstock for biochar production. Biochar is currently being considered as an additive for improving soil parameters, including the ability to oxidise methane (CH4) - one of the key greenhouse gases (GHG). Despite the high production of sunflower husk, there is still insufficient information on the impact of sunflower husk biochar on the soil environment, especially on the methanotrophy process. To fill this knowledge gap, an experiment was designed to evaluate the effects of addition of sunflower husk biochar (produced at 450-550 °C) at a wide range of doses (1-100 Mg ha-1) to Haplic Luvisol. In the presented study, the CH4 oxidation potential of soil with and without sunflower husk biochar was investigated at 60 and 100% water holding capacity (WHC), and with the addition of 1% CH4 (v/v). The comprehensive study included GHG exchange (CH4 and CO2), physicochemical properties of soil (pH, soil organic carbon (SOC), dissolved organic carbon (DOC), nitrate nitrogen (NO3--N), WHC), and the structure of soil microbial communities. That study showed that even low biochar doses (5 and 10 Mg ha-1) were sufficient to enhance pH, SOC, DOC and NO3--N content. Importantly, sunflower husk biochar was significant source of NO3--N, which soil concentration increased from 9.40 ± 0.09 mg NO3--N kg-1 for the control to even 19.40 ± 0.26 mg NO3--N kg-1 (for 100 Mg ha-1). Significant improvement of WHC (by 11.0-12.4%) was observed after biochar addition at doses of 60 Mg ha-1 and higher. At 60% WHC, application of biochar at a dose of 40 Mg ha-1 brought significant improvements in CH4 oxidation rate, which was 4.89 ± 0.37 mg CH4-C kg-1 d-1. Higher biochar doses were correlated with further improvement of CH4 oxidation rates, which at 100 Mg ha-1 was seventeen-fold higher (8.36 ± 0.84 mg CH4-C kg-1 d-1) than in the biochar-free control (0.48 ± 0.28 mg CH4-C kg-1 d-1). CO2 emissions were not proportional to biochar doses and only grew circa (ca.) twofold from 3.16 to 6.90 mg CO2-C kg-1 d-1 at 100 Mg ha-1. Above 60 Mg ha-1, the diversity of methanotrophic communities increased, with Methylobacter becoming the most abundant genus, which was as high as 7.45%. This is the first, such advanced and multifaceted study of the wide range of sunflower husk biochar doses on Haplic Luvisol. The positive correlation between soil conditions, methanotroph abundance and CH4 oxidation confirmed the multifaceted, positive effect of sunflower husk biochar on Haplic Luvisol. Sunflower husk biochar can be successfully used for Haplic Luvisol supplementation. This additive facilitates soil protection against degradation and has the potential to mitigate GHG emissions.

Use of random forest algorithm for predictive modelling of transfer factor soil-plant for radiocaesium: A feasibility study

A German dataset with soil-plant transfer factors for radiocaesium including many co-variables was analysed and prepared for the application of the Random Forest (RF) algorithm using the R libraries 'party', and 'caret'. A RF predictive model for soil-plant transfer factor was created based on 10 co-variables. These are, for example, taxonomic plant family, plant part, soil type and the exchangeable potassium concentration in the soil. The RF model results were compared with the results of two (semi-)mechanistic models. Of the more than 3000 entries in the original dataset, only about 1200 could be used, as this was the largest complete dataset with the largest number of co-variables available. The obtained RF predictive model can reproduce the experimental observations better than the two (semi)-mechanistic models, which are based on many assumptions and fixed parameter values. Model performance was quantified using the metrics of Root Mean Square Error (rmse) and Mean Absolute Error (mae). The RF model was able to reproduce the variability of the data by up to 6 orders of magnitude. The categorical co-predictors, especially taxonomic plant family and plant part, have a greater influence than the numerical co-predictors, such as pH and exchangeable soil potassium concentration. This feasibility study shows that RF is a promising tool to obtain predictive models for transfer factors. However, to build a widely applicable predictive model, a dataset is needed that contains at least thousands of entries for transfer factors and for the most important co-variables and considers a large parameter space.

Spatial modelling of topsoil properties in Romania using geostatistical methods and machine learning

Various research topics from the field of soil science or agriculture require digital maps of soil properties as input data. Such maps can be achieved by digital soil mapping (DSM) techniques which have developed consistently during the last decades. Our research focuses on the application of geostatistical methods (including ordinary kriging, regression-kriging and geographically weighted regression) and machine learning algorithms to produce high resolution digital maps of topsoil properties in Romania. Six continuous predictors were considered in our study (digital elevation model, topographic wetness index, normalized difference vegetation index, slope, latitude and longitude). A tolerance test was performed to ensure that all predictors can be used for the purpose of digital soil mapping. The input soil data was extracted from the LUCAS database and includes 7 chemical properties (pH, electrical conductivity, calcium carbonate, organic carbon, N, P, K) and the particle-size fractions (sand, silt, clay). The spatial autocorrelation is higher for pH, organic carbon and calcium carbonate, as indicated by the partial sill / nugget ratio of semivariograms, meaning that these properties are more predictable than the others by kriging interpolation. The optimal DSM method was selected by independent sample validation, using resampled statistics from 100 samples randomly extracted from the validation dataset. Also, an additional independent sample of soil profiles, comprising legacy soil data, and the 200k Romania soil map were used for a supplementary validation. The results show that machine learning and regression-kriging are the optimal methods in most cases. Among the machine learning tested algorithms, the best performance is associated with Support Vector Machines and Random Forests methods. The geographically weighted regression is also among the optimum methods for pH and calcium carbonates spatial prediction. Good predictions were achieved for pH (R2 of 0.417-0.469, depending on the method), organic carbon (R2 of 0.302-0.443), calcium carbonates (R2 of 0.300-0.330) and moderate predictions for electric conductivity, total nitrogen, silt and sand (R2 of 0.155-0.331), while the lowest prediction characterizes the phosphorous content (R2 of 0.015-0.044). LUCAS proved to be a reliable and useful soil database and the achieved spatial distributions of soil properties can be further used for national and regional soil studies.

Effects of optical and radar satellite observations within Google Earth Engine on soil organic carbon prediction models in Spain

The modeling and mapping of soil organic carbon (SOC) has advanced through the rapid growth of Earth observation data (e.g., Sentinel) collection and the advent of appropriate tools such as the Google Earth Engine (GEE). However, the effects of differing optical and radar sensors on SOC prediction models remain uncertain. This research aims to investigate the effects of different optical and radar sensors (Sentinel-1/2/3 and ALOS-2) on SOC prediction models based on long-term satellite observations on the GEE platform. We also evaluate the relative impact of four synthetic aperture radar (SAR) acquisition configurations (polarization mode, band frequency, orbital direction and time window) on SOC mapping with multiband SAR data from Spain. Twelve experiments involving different satellite data configurations, combined with 4027 soil samples, were used for building SOC random forest regression models. The results show that the synthesis mode and choice of satellite images, as well as the SAR acquisition configurations, influenced the model accuracy to varying degrees. Models based on SAR data involving cross-polarization, multiple time periods and "ASCENDING" orbits outperformed those involving copolarization, a single time period and "DESCENDING" orbits. Moreover, combining information from different orbital directions and polarization modes improved the soil prediction models. Among the SOC models based on long-term satellite observations, the Sentinel-3-based models (R² = 0.40) performed the best, while the ALOS-2-based model performed the worst. In addition, the predictive performance of MSI/Sentinel-2 (R² = 0.35) was comparable with that of SAR/Sentinel-1 (R² = 0.35); however, the combination (R² = 0.39) of the two improved the model performance. All the predicted maps involving Sentinel satellites had similar spatial patterns that were higher in northwest Spain and lower in the south. Overall, this study provides insights into the effects of different optical and radar sensors and radar system parameters on soil prediction models and improves our understanding of the potential of Sentinels in developing soil carbon mapping.

A Global Database of Soil Plant Available Phosphorus

Soil phosphorus drives food production that is needed to feed a growing global population. However, knowledge of plant available phosphorus stocks at a global scale is poor but needed to better match phosphorus fertiliser supply to crop demand. We collated, checked, converted, and filtered a database of c. 575,000 soil samples to c. 33,000 soil samples of soil Olsen phosphorus concentrations. These data represent the most up-to-date repository of freely available data for plant available phosphorus at a global scale. We used these data to derive a model (R2 = 0.54) of topsoil Olsen phosphorus concentrations that when combined with data on bulk density predicted the distribution and global stock of soil Olsen phosphorus. We expect that these data can be used to not only show where plant available P should be boosted, but also where it can be drawn down to make more efficient use of fertiliser phosphorus and to minimise likely phosphorus loss and degradation of water quality.

Effects of microplastics on the water characteristic curve of soils with different textures

Microplastic (MP) pollution in the soil severely damages the soil structure and affects the soil water-holding property, thereby affecting the soil water characteristic curve (SWCC). After polyethylene MP (PE-MP) addition at three concentrations (0.5%, 1%, and 2%) under three particle sizes (150 μm, 550 μm, and 950 μm) and two soil textures (sandy soil and loamy soil), SWCCs were measured and fitted with the van Genuchten model. The soil pore structure characteristics were obtained based on CT scanning combined with soil pore three-dimensional reconstruction to quantitatively analyze the relationships between MP properties and soil structure and the SWCC. Low concentrations (0.5%) of PE-MPs did not significantly affect the soil water content, while the accumulation of PE-MPs at a high concentration (2%) strongly affected the soil water-holding property, with small PE-MPs (150 μm) exerting significantly positive effects on the water-holding capacity of loamy soil and 950-μm MPs reducing the soil water content more strongly in sandy soil. The contributions of MP properties and soil textures to the SWCCs differed, and the impact of soil texture on the SWCCs was significantly higher than those of MP concentrations and particle sizes. Differences in MP occurrence characteristics and soil textures also led to variations in the fitted hydraulic parameters of the SWCCs. The addition of 2% 150-μm PE-MPs to loamy soil increased the soil porosity and surface area, while the addition of a higher concentration of large PE-MPs (2%, 950 μm) to sandy soil reduced soil porosity and circularity. This is related to the addition of a large number of small MPs, which may adsorb and bind many smaller soil particles to form larger, water-stable agglomerated structures, while the addition of high concentrations of large MPs in sandy soils may be related to the destruction of the original capillary pore structure of sandy soils and the weakening of soil capillarity. This study provides a theoretical basis for agroecological risk assessments.

Mapping risks associated with soil copper contamination using availability and bio-availability proxies at the European scale

Soil contamination by trace elements like copper (Cu) can affect soil functioning. Environmental policies with guidelines and soil survey measurements still refer to the total content of Cu in soils. However, Cu content in soil solution or free Cu content have been shown to be better proxies of risks of Cu mobility or (bio-)availability for soil organisms. Several empirical equations have been defined at the local scale to predict the amount of Cu in soil solution based on both total soil Cu content and main soil parameters involved in the soil/solution partitioning. Nevertheless, despite the relevance for risk assessment, these equations are not applied at a large spatial scale due to difficulties to perform changes from local to regional. To progress in this challenge, we collected several empirical equations from literature and selected those allowing estimation of the amount of Cu in solution, used as a proxy of available Cu, from the knowledge of both total soil Cu content and soil parameters. We did the same for the estimation of free Cu in solution, used as a proxy of bio-available Cu. These equations were used to provide European maps of (bio-)available Cu based on the one of total soil Cu over Europe. Results allowed comparing the maps of available and bio-available Cu at the European scale. This was done with respective median values of each form of Cu to identify specific areas of risks linked to these two proxies. Higher discrepancies were highlighted between the map of bio-available Cu and the map of soil total Cu compared to the Cu available map. Such results can be used to assess environmental-related issues for land use planning.

IoT-Based Systems for Soil Nutrients Assessment in Horticulture

Soil nutrients assessment has great importance in horticulture. Implementation of an information system for horticulture faces many challenges: (i) great spatial variability within farms (e.g., hilly topography); (ii) different soil properties (e.g., different water holding capacity, different content in sand, sit, clay, and soil organic matter, different pH, and different permeability) for different cultivated plants; (iii) different soil nutrient uptake by different cultivated plants; (iv) small size of monoculture; and (v) great variety of farm components, agroecological zone, and socio-economic factors. Advances in information and communication technologies enable creation of low cost, efficient information systems that would improve resources management and increase productivity and sustainability of horticultural farms. We present an information system based on different sensing capability, Internet of Things, and mobile application for horticultural farms. An overview on different techniques and technologies for soil fertility evaluation is also presented. The results obtained in a botanical garden that simulates the diversity of environment and plant diversity of a horticultural farm are discussed considering the challenges identified in the literature and field research. The study provides a theoretical basis and technical support for the development of technologies that enable horticultural farmers to improve resources management.

Improving the phosphorus budget of European agricultural soils

Despite phosphorus (P) being crucial for plant nutrition and thus food security, excessive P fertilization harms soil and aquatic ecosystems. Accordingly, the European Green Deal and derived strategies aim to reduce P losses and fertilizer consumption in agricultural soils. The objective of this study is to calculate a soil P budget, allowing the quantification of the P surpluses/deficits in the European Union (EU) and the UK, considering the major inputs (inorganic fertilizers, manure, atmospheric deposition, and chemical weathering) and outputs (crop production, plant residues removal, losses by erosion) for the period 2011-2019. The Land Use/Cover Area frame Survey (LUCAS) topsoil data include measured values for almost 22,000 samples for both available and total P. With advanced machine learning models, we developed maps for both attributes at 500 m resolution. We estimated the available P for crops at a mean value of 83 kg ha^-1 with a clear distinction between North and South. The ratio of available P to the total P is about 1:17. The inorganic fertilizers and manure contribute almost equally as P inputs (mean 16 ± 2 kg P ha^-1 yr^-1 at 90 % confidence level) to agricultural soils, with high regional variations depending on farming practices, livestock density, and cropping systems. The P outputs came mainly from the exportation by the harvest of crop products and residues (97.5 %) and, secondly, by erosion. Using a sediment distribution model, we quantified the P fluxes to river basins and sea outlets. In the EU and UK, we estimated an average surplus of 0.8 kg P ha^-1 yr^-1 with high variability between countries with some regional variations. The P annual budget at regional scale showed ample possibility to improve P management by both reducing inputs in regions with high surplus (and P soil available) and rebalancing fertilization in those at risk of soil fertility depletion.

Can we abandon phosphorus starter fertilizer in maize? Results from a diverse panel of elite and doubled haploid landrace lines of maize (Zea mays L.)

The importance of phosphorus (P) in agriculture contrasts with the negative environmental impact and the limited resources worldwide. Reducing P fertilizer application by utilizing more efficient genotypes is a promising way to address these issues. To approach this, a large panel of maize (Zea mays L.) comprising each 100 Flint and Dent elite lines and 199 doubled haploid lines from six landraces was assessed in multi-environment field trials with and without the application of P starter fertilizer. The treatment comparison showed that omitting the starter fertilizer can significantly affect traits in early plant development but had no effect on grain yield. Young maize plants provided with additional P showed an increased biomass, faster growth and superior vigor, which, however, was only the case under environmental conditions considered stressful for maize cultivation. Importantly, though the genotype-by-treatment interaction variance was comparably small, there is genotypic variation for this response that can be utilized in breeding. The comparison of elite and doubled haploid landrace lines revealed a superior agronomic performance of elite material but also potentially valuable variation for early traits in the landrace doubled haploid lines. In conclusion, our results illustrate that breeding for P efficient maize cultivars is possible towards a reduction of P fertilizer in a more sustainable agriculture.

Sources of copper into the European aquatic environment

Chemical contamination from point source discharges in developed (resource-rich) countries has been widely regulated and studied for decades; however, diffuse sources are largely unregulated and widespread. In the European Union (EU), large dischargers report releases of some chemicals, yet little is known of total emissions (point and diffuse) and their relative significance. We estimated copper loadings from all significant sources including industry, sewage treatment plants, surface runoff (from traffic, architecture, and atmospheric deposition), septic tanks, agriculture, mariculture, marine transport (antifoulant leaching), and natural processes. A combination of European datasets, literature, and industry data were used to generate export coefficients. These were then multiplied by activity rates to derive loads. A total of approximately 8 kt of copper per annum (ktpa) is estimated to enter freshwaters in the EU, and another 3.5 ktpa enters transitional and coastal waters. The main inputs to freshwater are natural processes (3.7 ktpa), agriculture (1.8 ktpa), and runoff (1.8 ktpa). Agricultural emissions are dominated by copper-based plant protection products and farmyard manure. Urban runoff is influenced by copper use in architecture and by vehicle brake linings. Antifoulant leaching from boats (3.2 ktpa) dominates saline water loads of copper. It is noteworthy that most of the emissions originate in a limited number of copper uses where environmental exposure and pathways exist, compared with the bulk of copper use within electrical and electronic equipment and infrastructure that has no environmental pathway during its use. A sensitivity analysis indicated significant uncertainty in data from abandoned mines and urban runoff load estimates. This study provided for the first time a methodology and comprehensive metal load apportionment to European aquatic systems, identifying data gaps and uncertainties, which may be refined over time. Source apportionments using this methodology can inform more cost-effective environmental risk assessment and management. Integr Environ Assess Manag 2022;00:1-17. © 2022 The Authors. Integrated Environmental Assessment and Management published by Wiley Periodicals LLC on behalf of Society of Environmental Toxicology & Chemistry (SETAC).

Holistic evaluation of long-term earthworm field studies with a fungicide

Plant protection products to be placed on the market in the European Union need to meet rigorous safety criteria including the testing of lumbricid earthworms, the functionally most important soil organism group in Central European agricultural ecosystems. To address uncertainties and investigate the potential long-term in-crop effects of the fungicide Cantus^® containing 50% boscalid as an active substance, a series of standardized earthworm field studies with an overall duration of 5 years per study program was carried out in four German agricultural fields under realistic crop rotation conditions. A two-step approach was chosen to analyze the potential overall long-term effects on earthworms in agricultural fields: (i) an assessment of the earthworm abundance development in the course of the four study programs in relation to the determined actual content of boscalid in soil and (ii) an effect size meta-analysis of earthworm abundance 1 year after treatment for each consecutive year and study program. Measured boscalid concentrations in the soil after multiple applications were well above the maximum boscalid residues observed in agricultural soils across Central Europe. There were isolated statistically significant reductions of earthworm abundance for some species and groups at some time points during the studies, but no consistent relationship to the Cantus^® treatments was observed. These results were supported by the meta-analysis, indicating no adverse effects on earthworm populations. Therefore, fluctuations of abundance reflect the natural variation of the populations rather than a concentration-related response. Based on this comprehensive analysis, we conclude that there is no application rate-related effect of the 5-year use of Cantus^® on the development of the earthworm communities. The four study programs, paired with a comprehensive evaluation, directly address the concerns about the potential long-term effects of boscalid on earthworms in the field and suggest that multiyear applications do not adversely affect earthworm populations. Integr Environ Assess Manag 2022;18:1399-1413. © 2021 ECT Oekotoxikologie GmbH and BASF SE. Integrated Environmental Assessment and Management published by Wiley Periodicals LLC on behalf of Society of Environmental Toxicology & Chemistry (SETAC).

Plot size matters: Toward comparable species richness estimates across plot-based inventories

To understand the state and trends in biodiversity beyond the scope of monitoring programs, biodiversity indicators must be comparable across inventories. Species richness (SR) is one of the most widely used biodiversity indicators. However, as SR increases with the size of the area sampled, inventories using different plot sizes are hardly comparable. This study aims at producing a methodological framework that enables SR comparisons across plot-based inventories with differing plot sizes. We used National Forest Inventory (NFI) data from Norway, Slovakia, Spain, and Switzerland to build sample-based rarefaction curves by randomly incrementally aggregating plots, representing the relationship between SR and sampled area. As aggregated plots can be far apart and subject to different environmental conditions, we estimated the amount of environmental heterogeneity (EH) introduced in the aggregation process. By correcting for this EH, we produced adjusted rarefaction curves mimicking the sampling of environmentally homogeneous forest stands, thus reducing the effect of plot size and enabling reliable SR comparisons between inventories. Models were built using the Conway-Maxell-Poisson distribution to account for the underdispersed SR data. Our method successfully corrected for the EH introduced during the aggregation process in all countries, with better performances in Norway and Switzerland. We further found that SR comparisons across countries based on the country-specific NFI plot sizes are misleading, and that our approach offers an opportunity to harmonize pan-European SR monitoring. Our method provides reliable and comparable SR estimates for inventories that use different plot sizes. Our approach can be applied to any plot-based inventory and count data other than SR, thus allowing a more comprehensive assessment of biodiversity across various scales and ecosystems.

Comparison of Bayesian, k-Nearest Neighbor and Gaussian process regression methods for quantifying uncertainty of suspended sediment concentration prediction

Suspended sediment transport in river system is a complex process influenced by many factors that their interactions lead to nonlinear and high scatter of concentration-discharge relationships. This makes the model prediction subject to high uncertainty and providing one value as the model prediction is somehow useless and cannot provide adequate information about the model accuracy and associated uncertainty. Current study compares the efficiency of Bayesian (i.e. Bayesian segmented linear regression (BSLR) and Bayesian linear model (BLR)), Gaussian Process Regression (GPR) and k-Nearest Neighbor (k-NN) in quantifying uncertainty of the suspended sediment concentration prediction in three watersheds namely Arazkoseh, Oghan and Jajrood located in Iran. Three input combinations including, contemporary discharge, slow and quick flow components and contemporary, one and two antecedent days discharge, were used. The BSLR model was able to identify threshold value, furthermore, pre-threshold and post-threshold slopes of BSLR model indicated that for Arazkoseh watershed channel and for Oghan and Jajrood watersheds, upland area are dominate sediment sources. In all three studied cases, given prediction interval width and the percent of enclosed observed data by prediction interval, k-NN model provided more reliable prediction interval. Moreover, separation stream flow into slow and quick flow components lead to improved performance of GPR and k-NN models in the studied watersheds, and the best results for Arazkoseh and Oghan watersheds were obtained when slow and quick flow components were used as the model input.

Range Size and Niche Breadth as Predictors of Climate-Induced Habitat Change in Epipactis (Orchidaceae)

While there is mounting evidence that ongoing changes in the climate system are shifting species ranges poleward and to higher altitudes, responses to climate change vary considerably between species. In general, it can be expected that species responses to climate change largely depend on how broad their ecological niches are, but evidence is still scant. In this study, we investigated the effects of predicted future climate change on the availability of suitable habitat for 14 Epipactis (Orchidaceae) species, and tested whether habitat specialists would experience greater changes in the extent of their habitats than habitat generalists. We used Maxent to model the ecological niche of each species in terms of climate, soil, elevation and land-use and projected it onto climate scenarios predicted for 2061–2080. To test the hypothesis that temperate terrestrial orchid species with small ranges or small niche breadths may be at greater risk under climate change than species with wide ranges or large niche breadths, we related niche breadth in both geographic and environmental space to changes in size and location of suitable habitat. The habitat distributions of half of the species shifted northwards in future projections. The area of suitable habitat increased for eight species but decreased for the remaining six species. If expansion at the leading edge of the distribution was not possible, the area of suitable habitat decreased for 12 species. Species with wide niche breadth in geographic space experienced greater northwards expansions and higher habitat suitability scores than species with small niche breadth. Niche breadth in environmental space was not significantly related to change in habitat distribution. Overall, these results indicate that terrestrial orchid species with a wide distribution will be more capable of shifting their distributions under climate change than species with a limited distribution, but only if they are fully able to expand into habitats at the leading edge of their distributions.

Phosphorus plant removal from European agricultural land

Phosphorus (P) is an important nutrient for all plant growth and it has become a critical and often imbalanced element in modern agriculture. A proper crop fertilization is crucial for production, farmer profits, and also for ensuring sustainable agriculture. The European Commission has published the Farm to Fork (F2F) Strategy in May 2020, in which the reduction of the use of fertilizers by at least 20% is among one of the main objectives. Therefore, it is important to look for the optimal use of P in order to reduce its pollution effects but also ensure future agricultural production and food security. It is essential to estimate the P budget with the best available data at the highest possible spatial resolution. In this study, we focused on estimating the P removal from soils by crop harvest and removal of crop residues. Specifically, we attempted to estimate the P removal by taking into account the production area and productivity rates of 37 crops for 220 regions in the European Union (EU) and the UK. To estimate the P removal by crops, we included the P concentrations in plant tissues (%), the crop humidity rates, the crop residues production, and the removal rates of the crop residues. The total P removal was about 2.55 million tonnes (Mt) (± 0.23 Mt), with crop harvesting having the larger contribution (ca. 94%) compared to the crop residues removal. A Monte-Carlo analysis estimated a ± 9% uncertainty. In addition, we performed a projection of P removal from agricultural fields in 2030. By providing this picture, we aim to improve the current P balances in the EU and explore the feasibility of F2F objectives.

Semantic Conceptual Framework for Environmental Monitoring and Surveillance—A Case Study on Forest Fire Video Monitoring and Surveillance

This paper presents a semantic conceptual framework and definition of environmental monitoring and surveillance and demonstrates an ontology implementation of the framework. This framework is defined in a mathematical formulation and is built upon and focused on the notation of observation systems. This formulation is utilized in the analysis of the observation system. Three taxonomies are presented, namely, the taxonomy of (1) the sampling method, (2) the value format and (3) the functionality. The definition of concepts and their relationships in the conceptual framework clarifies the task of querying for information related to the state of the environment or conditions related to specific events. This framework aims to make the observation system more queryable and therefore more interactive for users or other systems. Using the proposed semantic conceptual framework, we derive definitions of the distinguished tasks of monitoring and surveillance. Monitoring is focused on the continuous assessment of an environment state and surveillance is focused on the collection of all data relevant for specific events. The proposed mathematical formulation is implemented in the format of the computer readable ontology. The presented ontology provides a general framework for the semantic retrieval of relevant environmental information. For the implementation of the proposed framework, we present a description of the Intelligent Forest Fire Video Monitoring and Surveillance system in Croatia. We present the implementation of the tasks of monitoring and surveillance in the application domain of forest fire management.

Use of ammonium sulphate as a sulphur fertilizer: Implications for ammonia volatilization

Ammonium sulphate is widely used as a sulphur (S) fertilizer, constituting about 50% of global S use. Within nitrogen (N) management, it is well known that ammonium-based fertilizers are subject to ammonia (NH₃) volatilization in soils with pH > 7, but this has been overlooked in decision making on S fertilization. We reviewed 41 publications reporting measurements of NH₃ loss from ammonium sulphate in 16 countries covering a wide range of soil types and climates. In field experiments, loss was mostly <5% of applied N in soils with pH (in water) <7.0. In soils with pH > 7.0, there was a wide range of losses (0%-66%), with many in the 20%-40% range and some indication of increased loss (ca. 5%-15%) in soils with pH 6.5-7.0. We estimate that replacing ammonium sulphate with a different form of S for arable crops could decrease NH₃ emissions from this source by 90%, even taking account of likely emissions from alternative fertilizers to replace the N, but chosen for low NH₃ emission. For every kt of ammonium sulphate replaced on soils of pH > 7.0 in temperate regions, NH₃ emission would decrease from 35.7 to 3.6 t NH₃. Other readily available sources of S include single superphosphate, potassium sulphate, magnesium sulphate, calcium sulphate dihydrate (gypsum), and polyhalite (Polysulphate). In view of the large areas of high pH soils globally, this change of S fertilizer selection would make a significant contribution to decreasing NH₃ emissions worldwide, contributing to necessary cuts to meet agreed ceilings under the Gothenburg Convention.