Mapping soil organic carbon stocks and trends with satellite-driven high resolution maps over South Africa

Spatial predictive modeling of soil organic carbon stocks in Norwegian forests

Boreal forest soils are a critical terrestrial carbon (C) reservoir, with soil organic carbon (SOC) stocks playing a key role in global C cycling. In this study, we generated high-resolution (16 m) spatial predictions of SOC stocks in Norwegian forests for three depth intervals: (1) soil surface down to 100 cm depth, (2) forest floor (LFH layer), and (3) 0-30 cm into the mineral soil. Our predictions were based on legacy soil data collected between 1988 and 1992 from a subset (n = 1014) of National Forest Inventory plots. We used boosted regression tree models to generate SOC estimates, incorporating environmental predictors such as land cover, site moisture, climate, and remote sensing data. Based on the resulting maps, we estimate total SOC stocks of 1.57-1.87 Pg C down to 100 cm, with 0.55-0.66 Pg C stored in the LFH layer and 0.68-0.80 Pg C in the upper mineral soil. These correspond to average SOC densities of 15.3, 5.4, and 6.6 kg C m-2, respectively. We compared the predictive performance of these models with another set, supplemented by soil chemistry variables. These models showed higher predictive performance (R2 = 0.65-0.71) than those used for mapping (R2 = 0.44-0.58), suggesting that the mapping models did not fully capture environmental variability influencing SOC stock distributions. Within the spatial predictive models, Sentinel-2 Normalized Difference Vegetation Index, depth to water table, and slope contributed strongly, while soil nitrogen and manganese concentrations had major roles in models incorporating soil chemistry. Prediction uncertainties were related to soil depth, soil types, and geographical regions, and we compared the spatial prediction against external SOC data. The generated maps of this offer a valuable starting point for identifying forest areas in Norway where SOC may be vulnerable to climate warming and management-related disturbances, with implications for soil CO2 emissions.

Modelling soil organic carbon at multiple depths in woody encroached grasslands using integrated remotely sensed data

Woody plants encroachment into grasslands has considerable hydrological and biogeochemical consequences to grassland soils that include altering the Soil Organic Carbon (SOC) pool. Consequently, continuous SOC stock assessment and evaluation at deeper soil depths of woody encroached grasslands is essential for informed management and monitoring of the phenomenon. Due to high litter biomass and deep root structures, woody encroached landscapes have been suggested to alter the accumulation of SOC at deeper soil layers; however, the extent at which woody plants sequester SOC within localized protected grasslands is still poorly understood. Remote sensing methods and techniques have recently been popular in SOC analysis due to better spatial and spectral data properties as well as the availability of affordable and eco-friendly data. In this regard, this study sought to quantify the accumulation of SOC at various depths (30 cm, 60 cm, and 100 cm) in a woody-encroached grassland by integrating Sentinel-1 (S1), Sentinel-2 (S2), PlanetScope (PS) satellite imagery, and topographic variables. SOC was quantified from 360 field-collected soil samples using the loss-On-Ignition (LOI) method and spatial distribution of SOC across the Bisley Nature Reserve modelled by employing the Random Forest (RF) algorithm. The study's results demonstrate that the integration of topographic variables, Synthetic Aperture Radar (SAR), and PlanetScope data effectively modelled SOC stocks at all investigated soil depths, with high R2 values of 0.79 and RMSE of 0.254 t/ha. Interestingly, SOC stocks were higher at 30 cm compared to 60 cm and 100 cm depths. The horizontal reception (VH), Slope, Topographic Weightiness Index (TWI), Band 11 and vertical reception (VV) were optimal predictors of SOC in woody encroached landscapes. These results highlight the significance of integrating RF model with spectral data and topographic variables for accurate SOC modelling in woody encroached ecosystems. The findings of this study are pivotal for developing a cost-effective and labour-efficient assessment and monitoring system for the appropriate management of SOC in woody encroached habitats.

Spatiotemporal Monitoring of Cropland Soil Organic Carbon Changes From Space

Soil monitoring requires accurate and spatially explicit information on soil organic carbon (SOC) trends and changes over time. Spatiotemporal SOC models based on Earth Observation (EO) satellite data can support large-scale SOC monitoring but often lack sufficient temporal validation based on long-term soil data. In this study, we used repeated SOC samples from 1986 to 2022 and a time series of multispectral bare soil observations (Landsat and Sentinel-2) to model high-resolution cropland SOC trends for almost four decades. An in-depth validation of the temporal model uncertainty and accuracy of the derived SOC trends was conducted based on a network of 100 long-term monitoring sites that were continuously resampled every 5 years. While the general SOC prediction accuracy was high (R2 = 0.61; RMSE = 5.6 g kg-1), the direct validation of the derived SOC trends revealed a significantly greater uncertainty (R2 = 0.16; p < 0.0001), even though predicted and measured values showed similar distributions. Classifying the results into declining and increasing SOC trends, we found that 95% of all sites were either correctly identified or predicted as stable (p < 0.001), highlighting the potential of our findings. Increased accuracies for SOC trends were found in soils with higher SOC contents (R2 = 0.4) and sites with reduced tillage (R2 = 0.26). Based on the signal-to-noise ratio and temporal model uncertainty, we were able to show that the necessary time frame to detect SOC trends strongly depends on the absolute SOC changes present in the soils. Our findings highlight the potential to generate significant cropland SOC trend maps based on EO data and underline the necessity for direct validation with repeated soil samples and long-term SOC measurements. This study marks an important step toward the usability and integration of EO-based SOC maps for large-scale soil carbon monitoring.

Environmental variables improve the accuracy of remote sensing estimation of soil organic carbon content

Accurately and quickly estimating the soil organic carbon (SOC) content is crucial in the monitoring of global carbon. Environmental variables play a significant role in improving the accuracy of the SOC content estimation model. This study focuses on modeling methodologies and environmental variables, which significantly influence the SOC content estimation model. The modeling methods used in this research comprise multiple linear regression (MLR), partial least squares regression (PLSR), random forest, and support vector machines (SVM). The analyzed environmental variables include terrain, climate, soil, and vegetation cover factors. The original spectral reflectance (OSR) of Landsat 5 TM images and the spectral reflectivity after the derivative processing were combined with the above environmental variables to estimate SOC content. The results showed that: (1) The SOC content can be efficiently estimated using the OSR of Landsat 5 TM, however, the derived processing method cannot significantly improve the estimation accuracy. (2) Environmental variables can effectively improve the accuracy of SOC content estimation, with climate and soil factors producing the most significant improvements. (3) Machine learning modeling methods provide better estimation accuracy than MLR and PLSR, especially the SVM model which has the highest accuracy. According to our observations, the best estimation model in the study area was the "OSR + SVM" model (R2 = 0.9590, RMSE = 13.9887, MAE = 10.8075), which considered four environmental factors. This study highlights the significance of environmental variables in monitoring SOC content, offering insights for more precise future SOC assessments. It also provides crucial data support for soil health monitoring and sustainable agricultural development in the study area.

Remote Sensing of Depth-Induced Variations in Soil Organic Carbon Stocks Distribution Within Different Vegetated Landscapes

The preservation and augmentation of soil organic carbon (SOC) stocks is critical to designing climate change mitigation strategies and alleviating global warming. However, due to the susceptibility of SOC stocks to environmental and topo-climatic variability and changes, it is essential to obtain a comprehensive understanding of the state of current SOC stocks both spatially and vertically. Consequently, to effectively assess SOC storage and sequestration capacity, precise evaluations at multiple soil depths are required. Hence, this study implemented an advanced Deep Neural Network (DNN) model incorporating Sentinel-1 Synthetic Aperture Radar (SAR) data, topo-climatic features, and soil physical properties to predict SOC stocks at multiple depths (0-30cm, 30-60cm, 60-100cm, and 100-200cm) across diverse land-use categories in the KwaZulu-Natal province, South Africa. There was a general decline in the accuracy of the DNN model's prediction with increasing soil depth, with the root mean square error (RMSE) ranging from 8.34 t/h to 11.97 t/h for the four depths. These findings imply that the link between environmental covariates and SOC stocks weakens with soil depth. Additionally, distinct factors driving SOC stocks were discovered in both topsoil and deep-soil, with vegetation having the strongest effect in topsoil, and topo-climate factors and soil physical properties becoming more important as depth increases. This underscores the importance of incorporating depth-related soil properties in SOC modelling. Grasslands had the largest SOC stocks, while commercial forests have the highest SOC sequestration rates per unit area. This study offers valuable insights to policymakers and provides a basis for devising regional management strategies that can be used to effectively mitigate climate change.

Mapping Sub-surface Distribution of Soil Organic Carbon Stocks in South Africa's Arid and Semi-Arid Landscapes: Implications for Land Management and Climate Change Mitigation

Soil organic carbon (SOC) stocks are critical for land management strategies and climate change mitigation. However, understanding SOC distribution in South Africa's arid and semi-arid regions remains a challenge due to data limitations, and the complex spatial and sub-surface variability in SOC stocks driven by desertification and land degradation. Thus, to support soil and land-use management practices as well as advance climate change mitigation efforts, there is an urgent need to provide more precise SOC stock estimates within South Africa's arid and semi-arid regions. Hence, this study adopted remote-sensing approaches to determine the spatial sub-surface distribution of SOC stocks and the influence of environmental co-variates at four soil depths (i.e., 0-30 cm, 30-60 cm, 60-100 cm, and 100-200 cm). Using two regression-based algorithms, i.e., Extreme Gradient Boosting (XGBoost) and Random Forest (RF), the study found the former (RMSE values ranging from 7.12 t/ha to 29.55 t/ha) to be a superior predictor of SOC in comparison to the latter (RMSE values ranging from 7.36 t/ha to 31.10 t/ha). Nonetheless, both models achieved satisfactory accuracy (R2 ≥ 0.52) for regional-scale SOC predictions at the studied soil depths. Thereafter, using a variable importance analysis, the study demonstrated the influence of climatic variables like rainfall and temperature on SOC stocks at different depths. Furthermore, the study revealed significant spatial variability in SOC stocks, and an increase in SOC stocks with soil depth. Overall, these findings enhance the understanding of SOC dynamics in South Africa's arid and semi-arid landscapes and emphasizes the importance of considering site specific topo-climatic characteristics for sustainable land management and climate change mitigation. Furthermore, the study offers valuable insights into sub-surface SOC distribution, crucial for informing carbon sequestration strategies, guiding land management practices, and informing environmental policies within arid and semi-arid environments.

The possibility of spatial mapping of SOC content in olive groves under integrated production using easy-to-obtain ancillary data in a Mediterranean area

Background

Unlike most of Europe, Andalucía in southern Spain as a Mediterranean area still lacks digital maps of SOC content provided by machine learning algorithms. The wide diversity of climate, geology, hydrology, landscape, topography, vegetation, and micro-relief data as easy-to-obtain covariates facilitated the development of digital soil mapping (DSM). The purpose of this research is to model and map the spatial distribution of SOC at three depths, in an area of approximately 10000 km 2 located in Seville and Cordoba Provinces, and to use R programming to compare two machine learning techniques (cubist and random forest) for developing SOC maps at multiple depths.

Methods

Environmental covariates used in this research include nine derivatives from digital elevation models (DEM), three climatic variables and finally eighteen remotely-sensed spectral data (band ratios calculated by the acquired Landsat-8 OLI and Sentinel-2A MSI in July 2019). In total, 300 soil samples from 100 points were taken (0-25 cm). The purpose of this research is to model and map the spatial distribution of SOC, in an area with approximately 10000 km2 located in Seville and Cordoba Provinces, and to compare two machine learning techniques (cubist and random forest) by R programming.

Results

The findings showed that the novel approach for integrating the indices using Landsat-8 OLI and Sentinel-2A MSI satellite data had a better result.

Conclusions

Finally, we obtained evidence that the resolution of satellite images is more important in modelling and digital mapping.

Drivers of field-saturated soil hydraulic conductivity: Implications for restoring degraded tropical landscapes

Water security represents a major challenge in East Africa, affecting the livelihoods of millions of people and hindering sustainable development. Predicted increases in rainfall intensity and variability are expected to exacerbate water insecurity and land degradation. Improving soil infiltrability is an effective strategy for addressing water insecurity and land degradation. Research on soil infiltrability is often highly localized; therefore, scientific understanding of the drivers of infiltrability on larger spatial scales is limited. The aim of this study was to understand the main drivers of infiltrability across five contrasting landscapes in Kenya. We measured field-saturated hydraulic conductivity (Kfs) in 257 plots and collected data for variables representing soil properties (sand content, soil organic carbon (SOC) and pH), land degradation (grazing pressure and presence of erosion), vegetation quantity (woody aboveground biomass), and vegetation quality (functional properties and diversity). We used generalized mixed-effects models to test for the effects of these variables on Kfs. Median Kfs for the five sites ranged between 23.8 and 101.8 mm h-1. We found that Kfs was positively associated with sand content (standardized effect 0.39), SOC content (0.15), and functional diversity of woody vegetation (0.09), while it had a negative relationship with the presence of erosion (-0.24) and grazing pressure (-0.09). Subsequently, we conclude that infiltrability can be enhanced through using land restoration strategies which specifically target parameters that affect Kfs. The results further support that Kfs is not solely dictated by inherent soil properties, and that management interventions which boost SOC, reduce erosion, and minimize unsustainable grazing can help address water scarcity by restoring soil hydrological function.

Soil organic carbon stock retrieval from Sentinel-2A using a hybrid approach

Digital soil maps find application in numerous fields, making their accuracy a crucial factor. Mapping soil properties in homogeneous landscapes where the soil surface is concealed, as in forests, presents a complex challenge. In this study, we evaluated the spatial distribution of soil organic carbon stocks (SOCstock) under forest vegetation using three methods: regression kriging (RK), random forest (RF), and RF combined with ordinary kriging of residuals (RFOK) in combination with Sentinel-2A satellite data. We also compared their accuracies and identified key influencing factors. We determined that SOCstock ranged from 0.6 to 10.9 kg/m2 with an average value of 4.9 kg/m2. Among the modelling approaches, we found that the RFOK exhibited the highest accuracy (RMSE = 1.58 kg/m2, NSE = 0.33), while the RK demonstrated a lack of spatial correlation of residuals, rendering this method inapplicable. An analysis of variable importance revealed that the SWIR B12 band of the Sentinel-2A satellite contributed the most to RFOK predictions. We concluded that the RFOK hybrid approach outperformed the others, potentially serving as a foundation for digital soil mapping under similar environmental conditions. Therefore, it is essential to consider spatial correlations when mapping soil properties in ecosystems that are inaccessible for capturing the spectral response of the soil surface.

Integrated LiDAR-supported valuation of biomass and litter in forest ecosystems. A showcase in Spain

Belowground components (biomass and soils) can stock as much carbon as the aboveground component of forest ecosystems. In this study, we present a fully-integrated assessment of the biomass budget and the three pools evaluated: aboveground (AGBD) and belowground biomass in root systems (BGBD) and litter (LD). We turned National Forest Inventory data, airborne Light Detection and Ranging (LiDAR) data actionable to map three biomass compartments at 25-m resolution over more than 2.7 million ha of Mediterranean forests in the South-West of Spain. We assessed distributions and balanced among the three modelled components for the entire region of Extremadura and specifically for five representative forest types. Our results showed belowground biomass and litter represent an important 61 % of the AGBD stock. Among forest types, AGBD stocks were the dominant pool in pine-dominated areas while its lowers contribution was found over sparse oak forests. The three biomass pools estimated at the same resolution were used to produce ratio-based indicators to highlight areas where the contribution of belowground biomass and litter can exceed AGBD and where carbon-sequestration and conservation practices should acknowledge belowground-oriented carbon management. The recognition and valuation of biomass and carbon stocks beyond the AGBD is a must step forward that the scientific community must support in order to properly assess living components of the ecosystem such as root systems sustaining AGBD stocks and to value carbon-oriented ecosystem services related to soil-water dynamics and soil biodiversity. This study aims at enforcing a change of paradigm in forest carbon accounting, advocating for a better recognition and broader integration of living biomass in land carbon mapping.

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.

Mapping soil organic carbon distribution across South Africa's major biomes using remote sensing-topo-climatic covariates and Concrete Autoencoder-Deep neural networks

The management of soil organic carbon (SOC) stocks remains at the forefront of greenhouse gas mitigation. However, unprecedented anthropogenic disturbances emanating from continued land-use change have significantly altered SOC distribution across global biomes leading to considerable carbon losses. Consequently, understanding the spatial distribution of SOC across different biomes, particularly at larger scales, is critical for climate change policy formulation and planning. Advancements in remote sensing, availability of big data, and deep learning architecture offer great potential in large-scale SOC mapping. In this regard, this study mapped SOC distribution across South Africa's major biomes using remotely sensed-topo-climatic data and Concrete Autoencoder-Deep neural networks (CAE-DNN). From the different deep neural frameworks tested, the CAE-DNN model (developed from 26 selected covariates) achieved the best accuracy with an RMSE value of 7.91 t/ha (about 20 % of the mean). Results further showed that SOC stock correlated with general biome coverage, as the Grassland and Savanna biomes contributed the most (32.38 % and 31.28 %) to the overall SOC pool in South Africa. However, despite their smaller footprint, Forests (44.12 t/h) and the Indian Ocean Coastal Belt (43.05 t/h) biomes demonstrated the highest SOC sequestration capacity. The restoration of degraded biomes is advocated for, in order to boost SOC storage; but a balance between carbon sequestration capacity, biodiversity health, and the adequate provision of ecosystem services must be maintained. To this end, these findings provide a guideline to facilitate sustainable SOC stock management within South Africa's major biomes and indeed other regions of the world.

Evaluation of the Carbon Sink Capacity of the Proposed Kunlun Mountain National Park

National parks, as an important type of nature protected areas, are the cornerstone that can effectively maintain biodiversity and mitigate global climate change. At present, China is making every effort to build a nature-protection system, with national parks as the main body, and this approach considers China's urgent goals of obtaining carbon neutrality and mitigating climate change. It is of great significance to the national carbon-neutralization strategy to accurately predict the carbon sink capacity of national park ecosystems under the background of global change. To evaluate and predict the dynamics of the carbon sink capacity of national parks under climate change and different management measures, we combined remote-sensing observations, model simulations and scenario analyses to simulate the change in the carbon sink capacity of the proposed Kunlun Mountain National Park ecosystem over the past two decades (2000-2020) and the change in the carbon sink capacity under different zoning controls and various climate change scenarios from 2020 to 2060. Our results show that the carbon sink capacity of the proposed Kunlun Mountain National Park area is increasing. Simultaneously, the carbon sink capacity will be improved with the implementation of park management and control measures; which will be increased by 2.04% to 2.13% by 2060 in the research area under multiple climate change scenarios. The research results provide a scientific basis for the establishment and final boundary determination of the proposed Kunlun Mountain National Park.

Storage, patterns, and environmental controls of soil organic carbon stocks in the permafrost regions of the Northern Hemisphere

Large stocks of soil organic carbon (SOC) accumulated in the Northern Hemisphere permafrost regions may be vulnerable to climatic warming, but global estimates of SOC distribution and magnitude in permafrost regions still have large uncertainties. Based on multiple high-resolution environmental variables and a compiled soil sample dataset (>3000 soil profiles), we used machine-learning methods to estimate the size and spatial distribution of SOC for the top 3 m soils in the Northern Hemisphere permafrost regions. We also identified key environmental predictors of SOC. The results showed that the SOC storage for the top 3 m soil was 1079 ± 174 Pg C across the Northern Hemisphere permafrost regions (20.8 × 10⁶ km²), including 1057 ± 167 Pg C in the northern permafrost regions and 22 ± 7 Pg C in the Third Pole permafrost regions. The mean annual air temperature and NDVI are the main controlling factors for the spatial distribution of SOC stocks in the northern and the Third Pole permafrost regions. Our estimations were more accurate than the existing global SOC stock maps. The results improve our understanding of the regional and global permafrost carbon cycle and their feedback to the climate system.

Review of Remote Sensing Applications in Grassland Monitoring

The application of remote sensing technology in grassland monitoring and management has been ongoing for decades. Compared with traditional ground measurements, remote sensing technology has the overall advantage of convenience, efficiency, and cost effectiveness, especially over large areas. This paper provides a comprehensive review of the latest remote sensing estimation methods for some critical grassland parameters, including above-ground biomass, primary productivity, fractional vegetation cover, and leaf area index. Then, the applications of remote sensing monitoring are also reviewed from the perspective of their use of these parameters and other remote sensing data. In detail, grassland degradation and grassland use monitoring are evaluated. In addition, disaster monitoring and carbon cycle monitoring are also included. Overall, most studies have used empirical models and statistical regression models, while the number of machine learning approaches has an increasing trend. In addition, some specialized methods, such as the light use efficiency approaches for primary productivity and the mixed pixel decomposition methods for vegetation coverage, have been widely used and improved. However, all the above methods have certain limitations. For future work, it is recommended that most applications should adopt the advanced estimation methods rather than simple statistical regression models. In particular, the potential of deep learning in processing high-dimensional data and fitting non-linear relationships should be further explored. Meanwhile, it is also important to explore the potential of some new vegetation indices based on the spectral characteristics of the specific grassland under study. Finally, the fusion of multi-source images should also be considered to address the deficiencies in information and resolution of remote sensing images acquired by a single sensor or satellite.

Diachronic Mapping of Soil Organic Matter in Eastern Croatia Croplands

The spatiotemporal analysis and mapping of soil organic matter (SOM) play a pivotal role for evaluating soil health and for implementing preservation and restoration actions. In this context, the first aim of the study is to furnish a high-resolution mapping of current SOM content in eastern Croatia. The second aim is to perform a diachronic analysis of SOM content, comparing two datasets characterized by an extreme data imbalance. The more recent dataset (SOM2010), representative of 2010s, comprises 19,386 samples and the older dataset (SOM1970), representative of the 1970s, comprises 152 samples. The marked data imbalance and the different modalities in soil sampling and laboratory analysis of the two datasets are taken into consideration in performing the comparison. The study reveals a general depletion trend of SOM from the 1970s to the 2010s, more evident in with regard to Fluvisols and Gleysols. At a regional scale, the SOM2010 is characterized by lower variability compared to SOM1970, indicating a process of homogenization of SOM spatial distribution in recent years. Considering the local scale, there is limited information for the 1970s; for the 2010s the SOM spatial distribution is characterized by a high short-range spatial variability, with a characteristic spotty appearance, likely related to agricultural practices.

Spectral Index for Mapping Topsoil Organic Matter Content Based on ZY1-02D Satellite Hyperspectral Data in Jiangsu Province, China

Estimation of soil organic matter content (SOMC) is essential for soil quality evaluation. Compared with traditional multispectral remote sensing for SOMC mapping, the distribution of SOMC in a certain area can be obtained quickly by using hyperspectral remote sensing data. The Advanced Hyper-Spectral Imager (AHSI) onboard the ZY1-02D satellite can simultaneously obtain spectral information in 166 bands from visible (400 nm) to shortwave infrared (2500 nm), providing an important data source for SOMC mapping. In this study, SOMC-related spectral indices (SIs) suitable for this satellite were analyzed and evaluated in Shuyang County, Jiangsu Province. A series of SIs were constructed for the bare soil and vegetation-covered (mainly rice crops and tree seedlings) areas by combining spectral transformations (such as reciprocal and square root) and dual-band index formulas (such as ratio and difference), respectively. The optimal SIs were determined based on Pearson’s correlation coefficient (ρ) and satellite data quality, and applied to SOMC level mapping and estimation. The results show that: (1) The SI with the highest ρ in the bare soil area is the ratio index of original reflectance at 654 and 679 nm (OR-RI(654, 679)), whereas the SI in the vegetation area is the square root of the difference between the reciprocal reflectance at 551 and 1998 nm (V-RR-DSI(551, 1998)); (2) the spatial distribution trend of regional SOMC results obtained by linear regression models of OR-RI(654, 679) and V-RR-DSI(551, 1998) is consistent with the samples; (3) based on the optimal SIs, support vector machine and tree ensembles were used to predict the SOMC of bare soil and vegetation-covered areas of Shuyang County, respectively. The determination coefficient of the soil–vegetation combined prediction results is 0.775, the root mean square error is 3.72 g/kg, and the residual prediction deviation is 2.12. The results show that the proposed SIs for ZY1-02D satellite hyperspectral data are of great potential for SOMC mapping.

A novel intelligence approach based active and ensemble learning for agricultural soil organic carbon prediction using multispectral and SAR data fusion

Monitoring agricultural soil organic carbon (SOC) has played an essential role in sustainable agricultural management. Precise and robust prediction of SOC greatly contributes to carbon neutrality in the agricultural industry. To create more knowledge regarding the ability of remote sensing to monitor carbon soil, this research devises a state-of-the-art low cost machine learning model for quantifying agricultural soil carbon using active and ensemble-based decision tree learning combined with multi-sensor data fusion at a national and world scale. This work explores the use of Sentinel-1 (S1) C-band dual polarimetric synthetic aperture radar (SAR), Sentinel-2 (S2) multispectral data, and an innovative machine learning (ML) approach using an integration of active learning for land-use mapping and advanced Extreme Gradient Boosting (XGBoost) for robustness of the SOC estimates. The collected soil samples from a field survey in Western Australia were used for the model validation. The indicators including the coefficient of determination (R²) and root - mean - square - error (RMSE) were applied to evaluate the model's performance. A numerous features computed from optical and SAR data fusion were employed to build and test the proposed model performance. The effectiveness of the proposed machine learning model was assessed by comparing with the two well-known algorithms such as Random Forests (RF) and Support Vector Machine (SVM) to predict agricultural SOC. Results suggest that a combination of S1 and S2 sensors could effectively estimate SOC in farming areas by using ML techniques. Satisfactory accuracy of the proposed XGBoost with optimal features was achieved the highest performance (R² = 0.870; RMSE = 1.818 tonC/ha) which outperformed RF and SVM. Thus, multi-sensor data fusion combined with the XGBoost lead to the best prediction results for agricultural SOC at 10 m spatial resolution. In short, this new approach could significantly contribute to various agricultural SOC retrieval studies globally.

Exploring the likely relationship between soil carbon change and environmental controls using nonrevisited temporal data sets: Mapping soil carbon dynamics across China

The prediction of soil organic carbon (SOC) changes in response to environmental change is often limited by a scarcity of revisited temporal data, which constrains scientific understanding and realistic predictions of soil carbon change. The present study improved the potential of nonrevisited temporal data in the prediction of SOC stocks (SOCS) variations. We proposed a method to develop predictions of SOCS change using two independent temporal data sets (pertaining to the 1980s and 2010s) in China based on the digital soil mapping technique. Changes in SOCS over time at the site level were analyzed via the interpolation of missing SOCS values in each data set. Quantitative SOCS change predictions were generated by modeling the relationship between SOCS change and variables that represent changes in climate, vegetation indices, and land cover. The scale-dependent response of SOCS change to these environmental dynamics was assessed. On average, a slight increase was observed from 3.70 kg m^-2 in the 1980s to 4.53 kg m^-2 in the 2010s. The proposed approach attained moderate accuracy with an R² value of 0.32 and a root mean squared error (RMSE) of 1.73 kg m^-2. We found that changes in climate factors were dominant controls of SOCS change over time at the country scale. At the regional scale, the controlling factors of SOCS change were distinct and variable. Our case study may be of value in the application of independent temporal data sets to analyze soil carbon change on multiple scales. The method may be used to resolve questions of soil carbon change projections and provide an alternative solution to predict likely changes in soil carbon in response to future environmental change when no temporal data are available.

Selecting environmental factors to predict spatial distribution of soil organic carbon stocks, northwestern Iran

Knowledge of environmental factors controlling soil organic carbon (SOC) stocks can help predict spatial distribution SOC stocks. So, this study was carried out to select the best environmental factors to model and estimate the spatial distribution of SOC stocks in northwestern Iran. Soil sampling was performed at 210 points by multiple conditioned Latin Hypercube method (cLHm) and SOC stocks were measured. Also, environmental factors, including terrain attributes, moisture index, and normalized difference vegetation index (NDVI), were calculated. SOC stocks were modeled using random forest (RF) and partial least squares regression (PLSR) models. Modeling SOC stocks by RF model showed that the efficient factors for estimating the SOC stocks were slope height (slph), terrain surface texture (texture), standardized height (standh), elevation, relative slope position (rsp), and normalized height (normalh). Also, the PLSR model selected standardized height (standh), relative slope position (rsp), slope, and channel network base level (chnl base) to model SOC stocks. In both RF and PLSR methods, the standh and rsp factors were suitable parameters for estimating the SOC stocks. Predicting the spatial distribution of SOC stocks using environmental factors showed that the R² values for RF and PLSR models were 0.81 and 0.40, respectively. The result of this study showed that in areas with complex land features, terrain attributes can be good predictors for estimating SOC stocks. These predictors allow more accurate estimates of SOC stocks and contribute considerably to the effective application of land management strategies in arid and semiarid area.