Estimating water erosion from the brightness index of orbital images: A framework for the prognosis of degraded pastures

Mapping soil cadmium content using multi-spectral satellite images and multiple-residual-stacking model: Incorporating information from homologous pollution and spectrally active materials

Soil cadmium (Cd) contamination significantly threatens ecosystems and human health. Traditional geochemical investigation, although accurate, is impractical for wide-area and frequent monitoring applications. Multi-spectral satellite images combined with the homologous pollution information (HPI) and the spectral and content information of soil organic matter (SOMSCI) is an unconventional and promising approach for large-scale, dynamic soil heavy metal (SHM) monitoring. Based on a novel Multiple-Residual-Stacked (MRS) machine-learning framework, the study estimated the soil Cd content in Yueyang City, China, during the past decade (2014-2023) using Landsat 8 images. Within it, three feature construction methods and four models were employed. The experimental results indicate that the XGB-MRS model incorporating HPI and SOMSCI significantly improved the estimation performance (RPD exceeded 90 %, R2, RMSE, and MAE exceeded 40 %). Moreover, against 243 ground samples during 2016-2022, the average overall estimation accuracy exceeded 80 %, validating the model's robustness and practicality. Furthermore, the descending order of contribution in the modelling is environmental auxiliary variables (55 %), HPI and SOMSCI (26 %), and spectral information (19 %). The fertilizer usage has direct (up to 2 years) and delayed (3-5 years) effects on soil Cd accumulation. Overall, our study provides a scalable framework for monitoring global SHM pollution using open-source multi-spectral satellite data.

Monitoring of areas in conflict with the Legislation for the Protection of Native Vegetation in Brazil: opportunity for large-scale forest restoration and for the Brazilian global agenda

Forest restoration, combined with the mitigation of climate change, has attracted significant interest from several stakeholders. This can aid in restoring degraded areas and enhancing carbon storage. Brazil's global environmental commitments, particularly in the state of Minas Gerais (MG), require substantial financial investments to meet the goals of the Paris Agreement and the Convention on Biological Diversity. Minas Gerais has extensive areas protected by the Legislation for the Protection of Native Vegetation (LPVN) that are not compliant and must be restored in the next 20 years. Geographic data was collected from the government SICAR database. Land use in MG was analyzed using geoprocessing techniques using data from the MapBiomas platform to estimate the area in conflict with LPVN regulations. Minas Gerais has an environmental liability of 3.7 million hectares (Mha) that need restoration in the next 20 years. The Legal Reserve (RL) (2.2 Mha) and Permanent Preservation Areas of watercourses (1.3 Mha) are the most non-compliant protected areas. The "Triângulo Mineiro" and "Norte de Minas" mesoregions have the largest areas in conflict with the LPVN. The Cerrado faces a more critical situation, with approximately 56% of the conflicting areas located there. This study outlines the extent of restoration needed with native vegetation to comply with LPVN requirements in MG.

Total environment sentinels: Dragonflies as ambivalent/amphibiotic bioindicators of damage to soil and freshwater

Discerning the impact of anthropogenic impacts requires the implementation of bioindicators that quantify the susceptibilities and vulnerabilities of natural terrestrial and aquatic ecosystems to perturbation and transformation. Although legal regulations in Brazil recognize the value of bioindicators in monitoring water quality, the depreciation of soil conditions has yet to receive adequate attention. Thus, our study aimed to evaluate the potential of odonates (dragonflies and damselflies) as amphibiotic bioindicators to reflect the correlation between the degradation of aquatic and terrestrial habitats in pasture-dominated landscapes. We assessed the relationship between the biotic indices of Odonata and the conservation status of preserved riparian landscapes adjacent to anthropogenically altered pastures in 40 streams in the Brazilian savannah. Our results support the hypothesis that Odonata species composition may be a surrogate indicator for soil and water integrity, making them promising sentinels for detecting environmental degradation and guiding conservation strategies in human-altered landscapes. Importantly, while the Zygoptera/Anisoptera species ratio is a useful bioindicator tool in Brazilian forest, it is less effective in the open savannah here, and so an alternative index is required. Importantly, while the Zygoptera/Anisoptera species ratio is a useful bioindicator tool in Brazilian forest, it is less effective in the open savannah here, and so an alternative index is required. On the other hand, our results showed the Dragonfly Biotic Index to be a suitable tool for assessing freshwater habitats in Brazilian savannah. We also identified certain bioindicator species at both ends of the environment intactness spectrum.

Urban Form and Function Optimization for Reducing Carbon Emissions Based on Crowd-Sourced Spatio-Temporal Data

The low-carbon city has become an important global urban development-oriented goal. One important aspect of urban space is low-carbon urban planning, which has a vital role in urban carbon emissions. Which types of urban form and function allocations are conducive to reducing carbon emissions is therefore a key issue. In this study, the Futian and Luohu Districts of Shenzhen, Guangdong Province, China, are taken as an example to investigate this issue. Firstly, a "head/tail" breaks method based on the third fractal theory is adopted to obtain the minimum evaluation parcel of urban space. Then, the Landscape Shape Index (LSI), Fragmentation Index (C), Shannon's Diversity Index (SHDI), and Density of Public Facilities (Den) are used to evaluate the form and function allocation of each parcel. In addition, the CO₂ concentration distribution in this study area is acquired from remote sensing satellite data. Finally, the relationships between urban form, function allocation, and CO₂ concentration are obtained. The results show that the lower the urban form index or the higher the urban function index, the less the CO₂ concentration. To verify this conclusion, three experiments are designed and carried out. In experiment A, the CO₂ concentration of the tested area is reduced by 14.31% by decreasing the LSI and C by 6.1% and 9.4%, respectively. In experiment B, the CO₂ concentration is reduced by 15.15% by increasing the SHDI and Den by 16.3% and 12.1%, respectively. In experiment C, the CO₂ concentration is reduced by 27.72% when the urban form and function are adjusted in the same was as in experiments A and B.

Recognition of the Bare Soil Using Deep Machine Learning Methods to Create Maps of Arable Soil Degradation Based on the Analysis of Multi-Temporal Remote Sensing Data

The detection of degraded soil distribution areas is an urgent task. It is difficult and very time consuming to solve this problem using ground methods. The modeling of degradation processes based on digital elevation models makes it possible to construct maps of potential degradation, which may differ from the actual spatial distribution of degradation. The use of remote sensing data (RSD) for soil degradation detection is very widespread. Most often, vegetation indices (indicative botany) have been used for this purpose. In this paper, we propose a method for constructing soil maps based on a multi-temporal analysis of the bare soil surface (BSS). It is an alternative method to the use of vegetation indices. The detection of the bare soil surface was carried out using the spectral neighborhood of the soil line (SNSL) technology. For the automatic recognition of BSS on each RSD image, computer vision based on deep machine learning (neural networks) was used. A dataset of 244 BSS distribution masks on 244 Landsat 4, 5, 7, and 8 scenes over 37 years was developed. Half of the dataset was used as a training sample (Landsat path/row 173/028). The other half was used as a test sample (Landsat path/row 174/027). Binary masks were sufficient for recognition. For each RSD pixel, value “1” was set when determining the BSS. In the absence of BSS, value “0” was set. The accuracy of the machine prediction of the presence of BSS was 75%. The detection of degradation was based on the average long-term spectral characteristics of the RED and NIR bands. The coefficient Cmean, which is the distance of the point with the average long-term values of RED and NIR from the origin of the spectral plane RED/NIR, was calculated as an integral characteristic of the mean long-term values. Higher long-term average values of spectral brightness served as indicators of the spread of soil degradation. To test the method of constructing soil degradation maps based on deep machine learning, an acceptance sample of 133 Landsat scenes of path/row 173/026 was used. On the territory of the acceptance sample, ground verifications of the maps of the coefficient Cmean were carried out. Ground verification showed that the values of this coefficient make it possible to estimate the content of organic matter in the plow horizon (R2 = 0.841) and the thickness of the humus horizon (R2 = 0.8599). In total, 80 soil pits were analyzed on an area of 649 ha on eight agricultural fields. Type I error (false positive) of degradation detection was 17.5%, and type II error (false negative) was 2.5%. During the determination of the presence of degradation by ground methods, 90% of the ground data coincided with the detection of degradation from RSD. Thus, the quality of machine learning for BSS recognition is sufficient for the construction of soil degradation maps. The SNSL technology allows us to create maps of soil degradation based on the long-term average spectral characteristics of the BSS.