Mapping Soil Organic Carbon Research Articles

A Comprehensive Evaluation of Machine Learning Algorithms for Digital Soil Organic Carbon Mapping on a National Scale

The aim of this study was to narrow the research gap of ambiguity in which machine learning algorithms should be selected for evaluation in digital soil organic carbon (SOC) mapping. This was performed by providing a comprehensive assessment of prediction accuracy for 15 frequently used machine learning algorithms in digital SOC mapping based on studies indexed in the Web of Science Core Collection (WoSCC), providing a basis for algorithm selection in future studies. Two study areas, including mainland France and the Czech Republic, were used in the study based on 2514 and 400 soil samples from the LUCAS 2018 dataset. Random Forest was first ranked for France (mainland) and then ranked for the Czech Republic regarding prediction accuracy; the coefficients of determination were 0.411 and 0.249, respectively, which was in accordance with its dominant appearance in previous studies indexed in the WoSCC. Additionally, the K-Nearest Neighbors and Gradient Boosting Machine regression algorithms indicated, relative to their frequency in studies indexed in the WoSCC, that they are underrated and should be more frequently considered in future digital SOC studies. Future studies should consider study areas not strictly related to human-made administrative borders, as well as more interpretable machine learning and ensemble machine learning approaches.

Including soil spatial neighbor information for digital soil mapping

Digital soil mapping (DSM) is transforming how we understand and manage soil resources, offering high-resolution spatial–temporal soil information essential for addressing environmental challenges. The integration of environmental covariates has advanced soil mapping accuracy, while the potential of neighboring soil sample data has been largely overlooked. This study introduces soil spatial neighbor information (SSNI) as a novel approach to enhance the predictive power of spatial models. Utilizing two open-access datasets from LUCAS Soil and Meuse, our findings showed that incorporating SSNI improved the accuracy of random forest models in mapping soil organic carbon density (reduced %RMSE of 3.1%), cadmium (reduced %RMSE of 3.6%), copper (reduced %RMSE of 5.9%), lead (reduced %RMSE of 11.5%), and zinc (reduced %RMSE of 7.4%). Compared to the inclusion of buffer distance or oblique geographic coordinates for modelling, SSNI also performed better for both LUCAS Soil and Meuse datasets. This study underscores the value of SSNI in improving digital soil maps by capturing the neighboring information. Embracing SSNI could lead to more informed decision-making in soil management and its potential applicability across other disciplines also remains open for exploration in future research endeavors.

Visible, near-infrared, and shortwave-infrared spectra as an input variable for digital mapping of soil organic carbon

This study proposes a novel methodology to employ discrete point spectra as input variable for digital mapping of soil organic carbon (SOC). Accordingly, two SOC modeling approaches were used in three agricultural sites in Czech Republic: i) machine learning (ML) including partial least square regression (PLSR), cubist, random forest (RF), and support vector regression (SVR), and ii) regression kriging (RK) by the combination of ordinary kriging (OK) and PLSR (PLSR-K), cubist (cubist-K), RF (RF-K), and SVR (SVR-K). Models were developed on environmental predictor covariates (EPCs) and thirty genetic algorithms (GA)-selected visible, near-infrared, and shortwave-infrared (VNIR–SWIR) wavelengths spectra, individually and combined. Thirty rasters were then created using interpolation of the selected spectra and served as the input variables – with and without EPCs – to test and compare the developed models and SOC predictive maps with each other and with those retrieved from the third approach: iii) kriging using OK of the measured and ML-predicted SOC. The impact of employing selected wavelengths’ spectra and EPCs on models' performance was investigated using independent test samples and the uncertainty associated with the produced maps. Using interpolated spectra as the only input variable yielded a relatively acceptable accuracy (Nová Ves: RMSE = 0.19%, Údrnice: RMSE = 0.12%, Klučov: RMSE = 0.13%). In comparison, the interpolated spectra coupled with EPCs enhanced the results. Regarding the uncertainty, however, the ML-based SOC maps were more reliable, than RK-based ones. Furthermore, maps produced using both spectra and EPCs showed less uncertainty than those constructed on the individual datasets.

Developing a digital mapping of soil organic carbon on a national scale using Sentinel-2 and hybrid models at varying spatial resolutions

Mapping the spatial distribution of soil organic carbon (SOC) is crucial for monitoring soil health, understanding ecosystem functions, and contributing to global carbon cycling. However, few studies have directly compared the influence of hybrid models and individual models with varying spatial resolutions on SOC prediction at a national scale. In this study, by combining remote sensing data, we utilized the LUCAS 2018 soil dataset to evaluate the potential capacities of hybrid models for predicting SOC content at different spatial resolutions in Germany. The hybrid models PLSRK and RFK consisted of partial least square regression (PLSR) with residual original kriging (OK) models, and random forest (RF) models with residual OK models, respectively. Individual PLSR and RF models were used as reference models. All these models were applied to estimate SOC content at 10 m, 50 m, 100 m, and 200 m spatial resolutions. Sentinel-2 bands, band indices, and topography variables were as predictors. The results revealed that hybrid models had a more accurate prediction of SOC content with higher explanations and lower prediction errors compared with individual models. The RFK model at the spatial resolution of 100 m was the fittest model with R2 = 0.416, RMSE = 0.545, and RPIQ = 1.647, which enhanced 3.74% of explanation compared with the performance of RF model. The results also showed that hybrid models at a relatively coarse resolution (100 m) had better accuracy instead of those at high spatial resolution (10 m, 50 m). Sentinel-2 remote sensing data showed significant predictive capabilities for estimating SOC content. The predicted spatial distribution of SOC content revealed that the high SOC concentrated in the northwest grassland, central and southwestern mountains, and the Alps in Germany. Our study provided a benchmark SOC map in Germany for monitoring the changes resulting from land use and climate impacts, and we illustrated the accuracy of hybrid models and the effects of spatial resolutions on SOC predictions at a national scale.

Application of Ordinary Kriging in Mapping Soil Organic Carbon in Chad using SoilGrids data

Application of Ordinary Kriging in Mapping Soil Organic Carbon in Chad using SoilGrids data

On the effectiveness of multi-scale landscape metrics in soil organic carbon mapping

Soil organic carbon (SOC) mapping delivers invaluable information to the global carbon budget and climate change mitigation endeavour. Environmental variables at sample locations are frequently used as explanatory variables for simulating the spatial distribution of soil properties. However, these may not fully capture the spatial information generated by soil-forming processes. We applied multi-scale landscape metrics that can comprehensively characterize the surrounding landscape information of sample points. The metrics were extracted at two levels (landscape level and class level) and include the diversity, shape and area, fragmentation and connectivity with a buffer distance from 500 m to 5,000 m. We then investigated its effectiveness as environmental variables via recursive feature elimination, random forests, and quantile regression forests. The Jianghan Plain, China, was selected as the study area, where over 19,000 topsoil samples were collected. Results indicated that multi-scale landscape metrics enhanced the predictability of SOC mapping, with R2 increased by 43 %. Specifically, Shannon’s diversity index, the percentage of landscape index, interspersion and juxtaposition index, and patch cohesion index outperformed environmental variables that were extracted at the sample location. In addition, the relationships between SOC and landscape metrics were found to be scale-dependent. Landscape metrics demonstrated significant explanatory capacity for SOC across various spatial scales. Notably, as the scale surpassed 3,000 m, there was a discernible improvement in the explanatory effectiveness of the landscape metrics for SOC. Our findings highlight that landscape metrics are effective in characterising the soil-landscape relationship that is generated by multi-scale natural and anthropogenic soil-forming processes. Meanwhile, knowledge of the intricate relationship between landscape characteristics and SOC is crucial for informing land management decisions aimed at enhancing carbon sequestration, mitigating climate change, and maintaining soil fertility.

Geospatial mapping of soil organic carbon in Sirsi Forst division using remote sensing techniques

Geospatial mapping of soil organic carbon in Sirsi Forst division using remote sensing techniques

Mapping soil organic carbon density via geographically weighted regression with smooth terms: A case study in Shanxi Province

Soil, as the largest organic carbon reservoir in terrestrial ecosystems, plays a crucial role in the global carbon cycle. Accurately predicting the spatial distribution of soil organic carbon density (SOCD) is highly important for estimating organic carbon stocks and guiding agricultural production. Due to the complex relationship between the spatial distribution of SOCD and environmental factors, its relationship with a specific region is not exclusively linear or nonlinear; both types of relationships may coexist simultaneously. In this study, a new model, geographically weighted regression with smooth terms (SGWR), was proposed. This model can simultaneously consider both global spatial nonlinear relationships and local spatial nonstationary relationships. It was utilized to predict SOCD in Shanxi Province and was compared to multiple linear regression (MLR), generalized additive models (GAM) and geographically weighted regression (GWR) in terms of spatial prediction performance. The results showed that SGWR was highly competitive in predicting the spatial distribution of SOCD in Shanxi Province. Of factors influencing SOCD in Shanxi Province, elevation and slope were considered local linear variables, while the normalized difference vegetation index (NDVI), gross primary productivity (GPP), annual precipitation (AP), and soil moisture (SM) were considered global nonlinear variables. Among these factors, the NDVI and GPP had the most significant impacts on the distribution of SOCD, while elevation and SM had the least significant impacts on it. The results imply that integrating global linear, local linear, and global nonlinear relationships concurrently, as implemented in SGWR, improves predictive accuracy compared to approaches that solely address either local or global linear relationships based on environmental variable changes in SGWR. The results of this study indicate that the SGWR model is potentially a competitive method for digital soil mapping.

Assessing and mapping of soil organic carbon at multiple depths in the semi-arid Trans-Ural steppe zone

The quantification of soil organic carbon (SOC) and its vertical distribution is crucial for understanding carbon dynamics in terrestrial ecosystems. This study aimed to 2.5D digital mapping of SOC content in the Trans-Ural steppe zone (Russia) using a quantile regression forest (QRF) approach. The study utilized a dataset comprising 2495 SOC measurements collected from 1316 locations across three soil depths: 0–20 cm, 20–40 cm, and 40–60 cm. Environmental covariates were incorporated into the SOC modeling process, capturing major soil formation factors, and the uncertainty of the generated maps was estimated. The results revealed that SOC content ranged from 0.59 to 9.05 % in the topsoil, from 0.5 to 6.61 % in the subsurface layer and from 0.06 to 4.64 % in the subsoil. Based on the error metrics, including root mean square error (RMSE), coefficient of determination (R2), and Nash-Sutcliffe efficiency coefficient (NSE), we found a decrease in prediction accuracy with increasing soil depth. Furthermore, climate and vegetation variables, as well as elevation, emerged as key factors influencing the prediction of SOC concentrations at all depths. We also made an attempt to assess the future change of SOC under the influence of climate and anthropogenic impact. We anticipate that climate aridization and plowing will lead to a decline in SOC content in the Trans-Ural steppe region. Our findings contribute to the existing knowledge of SOC dynamics in steppe ecosystems at several depths, supporting informed decision-making for sustainable land use and climate change mitigation strategies.

Unveiling the explanatory power of environmental variables in soil organic carbon mapping: A global–local analysis framework

Soil organic carbon (SOC) is a critical component that affects soil quality and global carbon cycling. Current SOC mapping approaches are based on the spatial stationarity relationship of SOC and soil formation processes. Nevertheless, the spatial pattern of SOC is the consequence of different soil-forming factors and processes that operate at different scales. In this work, we hypothesized that the covariation of environmental variables and SOC might differ spatially, and proposed a global (whole area) and local analysis framework that aimed to enhance our comprehension of the explanatory scale of environmental variables on SOC variation. This framework primarily incorporates Geographically Weighted correlation and the Multi-scale Geographically Weighted Regression (MGWR) model. With 216 farmland topsoil samples collected from the Qilu Lake watershed in Yunnan Province, China (area of 354 km2), we explored both global and local relationships between environmental variables and SOC to verify the feasibility of this framework. Results showed that the explanatory power of environmental variables on SOC variation is scale-dependent. Our analysis revealed that certain variables, which may explain local variations of SOC, are often overlooked due to their insignificant global correlation with SOC (p > 0.05). For example, in this case study, soil porosity and two landscape metrics that characterize the anthropogenic processes of land use patterns can effectively explain the local spatial variation of SOC. They improved the model performance of MGWR, but their global correlation with SOC is not significant. The proposed framework highlights the necessity of investigating the explanatory power of environmental variables on a global and local scale.

Remote Sensing and Sustainable Management of Soil Organic Carbon in the Sahelian Area, Senegal, West Africa

The mapping of soil organic carbon (SOC) variability was carried out in a Sahelian region of Senegal by testing the effectiveness to include the Sentinel 2 remote sensed data in the characterization of the soil properties. Ordinary kriging (OK) applied under ArcGIS is compared with multiple linear regression (MLR) calibrated under R software. The results showed a slight decrease of the root mean square error ranging from 0.18 with kriging to 0.16 for multiple linear regression. Carbon variability was also detailed at a finer scale with multiple linear regression at the pixel scale from 10 to 20 m. Spectral bands situated in the visible wavelength, NDWI and NDVI were the most discriminating explanatory variables in the spatial modeling of organic carbon by multiple linear regression. Specific locations that require inputs of manure or compost were also geo-localized with multiple linear regression in order to ensure sustainable management of soil organic carbon. The use of remote sensed data also puts into perspective the possibility of spatializing the physical and chemical properties of the soil on larger areas and correcting the lack of information on soil mapping in the Sahelian regions of Africa.

Remote Sensing and Sustainable Management of Soil Organic Carbon in the Sahelian Area, Senegal, West Africa

The mapping of soil organic carbon (SOC) variability was carried out in a Sahelian region of Senegal by testing the effectiveness to include the Sentinel 2 remote sensed data in the characterization of the soil properties. Ordinary kriging (OK) applied under ArcGIS is compared with multiple linear regression (MLR) calibrated under R software. The results showed a slight decrease of the root mean square error ranging from 0.18 with kriging to 0.16 for multiple linear regression. Carbon variability was also detailed at a finer scale with multiple linear regression at the pixel scale from 10 to 20 m. Spectral bands situated in the visible wavelength, NDWI and NDVI were the most discriminating explanatory variables in the spatial modeling of organic carbon by multiple linear regression. Specific locations that require inputs of manure or compost were also geo-localized with multiple linear regression in order to ensure sustainable management of soil organic carbon. The use of remote sensed data also puts into perspective the possibility of spatializing the physical and chemical properties of the soil on larger areas and correcting the lack of information on soil mapping in the Sahelian regions of Africa.

Analyze QRF model for soil organic carbon map building with digital soil mapping (case study: Sumatra island and Java island)

Abstract In the current era of global warming, soil organic content is one of the most important soil properties. The goal of the entire globe is for carbon neutrality to be achieved and regularly assessed. It is hoped that a dynamic, quick and effective soil organic carbon mapping method will be able to distribute the presence of soil organic carbon to support calculations for changes in carbon stocks and carbon sequestration so that carbon neutrality can be achieved. Digital Soil Mapping (DSM) recently has become the ultimate framework for accurately representing spatial distribution based on its quantitative result and uncertainty analysis. These advantages allow DSM to be replicated uniquely in each mapped area. Digital soil mapping requires input in the form of laboratory and field observation results that are spatially modeled using machine learning techniques. Field observations and laboratory data for Sumatra and Java Island from the Indonesian Center for Agricultural Land Resources Standard Testing (1970-2022) were used in this study, and the results were modeled using Quantile Regression Forests (QRF) in the R Software. Evaluation results from this model with 5738 observation points covering a 47.3 million-hectare-sized island of Sumatra and 3398 observation points covering a 12.8 million-hectare-sized island of Java show an RMSE value of 0.78 with a coefficient of determination (R2) of 0.31 for Sumatra Island and RMSE value of 0.68 with a coefficient of determination (R2) of 0.71 for Java Island. These findings indicate that the neighborhoods for the organic carbon content on the islands of Sumatra and Java differ quite noticeably. This may be due to the relatively wide range in some soils in the Sumatra region, which are peat soils with relatively high carbon content values compared to regions in Java where mineral soils predominate. In conclusion, the evaluation results for digital mapping with the QRF model for soil organic carbon content in Indonesia referring to these 2 large islands show good results with sufficient coefficients of determination in mineral soil areas and there is a need a different modeling approach in areas where peat soil predominates.

Open Remote Sensing Data in Digital Soil Organic Carbon Mapping: A Review

This review focuses on digital soil organic carbon (SOC) mapping at regional or national scales in spatial resolutions up to 1 km using open data remote sensing sources, emphasizing its importance in achieving United Nations’ Sustainable Development Goals (SDGs) related to hunger, climate action, and land conservation. The literature review was performed according to scientific studies indexed in the Web of Science Core Collection database since 2000. The analysis reveals a steady rise in total digital soil mapping studies since 2000, with digital SOC mapping studies accounting for over 20% of these studies in 2023, among which SDGs 2 (Zero Hunger) and 13 (Climate Action) were the most represented. Notably, countries like the United States, China, Germany, and Iran lead in digital SOC mapping research. The shift towards machine and deep learning methods in digital SOC mapping has surged post-2010, necessitating environmental covariates like topography, climate, and spectral data, which are cornerstones of machine and deep learning prediction methods. It was noted that the available climate data primarily restrict the spatial resolution of digital SOC mapping to 1 km, which typically requires downscaling to harmonize with topography (up to 30 m) and multispectral data (up to 10–30 m). Future directions include the integration of diverse remote sensing data sources, the development of advanced algorithms leveraging machine learning, and the utilization of high-resolution remote sensing for more precise SOC mapping.

Importance of Terrain and Climate for Predicting Soil Organic Carbon Is Highly Variable across Local to Continental Scales.

Soil organic carbon (SOC) plays a vital role in global carbon cycling and sequestration, underpinning the need for a comprehensive understanding of its distribution and controls. This study explores the importance of various covariates on SOC spatial distribution at both local (up to 1.25 km) and continental (USA) scales using a deep learning approach. Our findings highlight the significant role of terrain attributes in predicting SOC concentration distribution with terrain, contributing approximately one-third of the overall prediction at the local scale. At the continental scale, climate is only 1.2 times more important than terrain in predicting SOC distribution, whereas at the local scale, the structural pattern of terrain is 14 and 2 times more important than climate and vegetation, respectively. We underscore that terrain attributes, while being integral to the SOC distribution at all scales, are stronger predictors at the local scale with explicit spatial arrangement information. While this observational study does not assess causal mechanisms, our analysis nonetheless presents a nuanced perspective about SOC spatial distribution, which suggests disparate predictors of SOC at local and continental scales. The insights gained from this study have implications for improved SOC mapping, decision support tools, and land management strategies, aiding in the development of effective carbon sequestration initiatives and enhancing climate mitigation efforts.

Advancements in Soil Organic Carbon Mapping and Interpolation Techniques: A Case Study from Lithuania’s Moraine Plains

Monitoring soil organic carbon (SOC) is essential for assessing the sustainability of soil usage. This study explores the spatial variability and mapping of SOC in Lithuania’s Nevėžis Plain using various interpolation methods, with an emphasis on understanding the impacts of soil typological units, moisture regimes, and erosion on SOC distribution. A total of 275 soil samples were collected from agricultural croplands at depths of 0–10 cm, supplemented by 38 samples from previous studies. The SOC map was created based on the contours of the Lithuanian soil geodatabase. Statistical analysis revealed that the distribution of SOC in the studied area was significantly influenced by soil moisture and the degree of erosion. Based on these findings, SOC mapping was conducted according to the contours of Lithuanian soils. Comparing the interpolation methods that were analyzed, it was found that the kriging, RBF, and EBK methods fail to adequately capture the minimum and maximum values of SOC, while the IDW fails to adequately capture only the minimum values. In summary, the integrated geographical approach is complex but applicable to SOC mapping. This method facilitates the creation of adaptable SOC maps that are both geographically and pedologically informed. Key principles to apply this approach for future research and practical application should include establishing a statistically reliable data foundation, categorizing samples based on contrasting soil moisture regime, degrees of erosion, and land use patterns, and developing contouring principles along with a criteria algorithm that enables accurate spatial interpolation of average SOC values.

Exploring the Potential of PRISMA Satellite Hyperspectral Image for Estimating Soil Organic Carbon in Marvdasht Region, Southern Iran

Soil organic carbon (SOC) is a crucial factor for soil fertility, directly impacting agricultural yields and ensuring food security. In recent years, remote sensing (RS) technology has been highly recommended as an efficient tool for producing SOC maps. The PRISMA hyperspectral satellite was used in this research to predict the SOC map in Fars province, located in southern Iran. The main purpose of this research is to investigate the capabilities of the PRISMA satellite in estimating SOC and examine hyperspectral processing techniques for improving SOC estimation accuracy. To this end, denoising methods and a feature generation strategy have been used. For denoising, three distinct algorithms were employed over the PRISMA image, including Savitzky–Golay + first-order derivative (SG + FOD), VisuShrink, and total variation (TV), and their impact on SOC estimation was compared in four different methods: Method One (reflectance bands without denoising, shown as M#1), Method Two (denoised with SG + FOD, shown as M#2), Method Three (denoised with VisuShrink, shown as M#3), and Method Four (denoised with TV, shown as M#4). Based on the results, the best denoising algorithm was TV (Method Four or M#4), which increased the estimation accuracy by about 27% (from 40% to 67%). After TV, the VisuShrink and SG + FOD algorithms improved the accuracy by about 23% and 18%, respectively. In addition to denoising, a new feature generation strategy was proposed to enhance accuracy further. This strategy comprised two main steps: first, estimating the number of endmembers using the Harsanyi–Farrand–Chang (HFC) algorithm, and second, employing Principal Component Analysis (PCA) and Independent Component Analysis (ICA) transformations to generate high-level features based on the estimated number of endmembers from the HFC algorithm. The feature generation strategy was unfolded in three scenarios to compare the ability of PCA and ICA transformation features: Scenario One (without adding any extra features, shown as S#1), Scenario Two (incorporating PCA features, shown as S#2), and Scenario Three (incorporating ICA features, shown as S#3). Each of these three scenarios was repeated for each denoising method (M#1–4). After feature generation, high-level features were added to the outputs of Methods One, Three, and Four. Subsequently, three machine learning algorithms (LightGBM, GBRT, RF) were employed for SOC modeling. The results showcased the highest accuracy when features obtained from PCA transformation were added to the results from the TV algorithm (Method Four—Scenario Two or M#4–S#2), yielding an R2 of 81.74%. Overall, denoising and feature generation methods significantly enhanced SOC estimation accuracy, escalating it from approximately 40% (M#1–S#1) to 82% (M#4–S#2). This underscores the remarkable potential of hyperspectral sensors in SOC studies.

Assessing the 3D distribution of soil organic carbon by integrating predictions of water and tillage erosion into a digital soil mapping-approach: a case study for silt loam cropland (Belgium)

Although agricultural intensification has generally increased crop yields, it also resulted in a range of environmental issues. These include increased erosion rates and declined soil organic carbon (SOC) stocks. In order to improve our understanding on how erosion impacts the overall SOC storage capacity of croplands, this study analyses the 3D distribution of SOC as a function of water and tillage erosion in a conventionally ploughed field in the Belgian silt loam region. We present a novel methodological framework to integrate the output of an advanced erosion model as a co-variate within a Digital Soil Mapping (DSM) approach with the objective to create detailed SOC maps. More precisely, we combined (i) the Water and Tillage Erosion Model and Sediment Delivery Model (WaTEM/SEDEM), simulating spatial patterns of soil erosion and sediment deposition due to water and tillage erosions, with (ii) a SOC sampling campaign, resulting in a SOC spatial distribution model that considers both types of erosion. The results show that, as compared to plateaus, SOC stocks are nearly half as large along eroding slopes (i.e. convex slope positions affected by tillage erosion and steep slopes affected by water erosion). Yet, they are up to twice as large in areas characterized by sediment deposition (i.e. concave positions due to tillage erosion and foot slope positions due to water erosion). Our results further show that tillage erosion has a significant influence on the SOC stocks in the top 0.7 m and in particular on the top 0.4 m. The influence of water erosion is less strong but mostly significant along the entire depth profile. Overall, this work demonstrates the relevance of considering different erosion processes when aiming to predict spatial patterns of SOC. Considering the top 1 m and a WaTEM/SEDEM application at a resolution of 10 m our 3D SOC modelling approach obtained a coefficient of determination (R2) of 0.62, a relative root mean square error (RRMSE) of 30.5 % and a relative mean absolute error (RMAE) of 26.0 %. While future work may likely lead to further improvements e.g. a more detailed SOC sampling network along the foot slopes and thalwegs in order to obtain a more spatially detailed prediction of the area characterized by depositions due to water erosion, we demonstrate the great potential of existing erosion and deposition models in doing so.

Synergistic Use of Multi-Temporal Radar and Optical Remote Sensing for Soil Organic Carbon Prediction

Exploring soil organic carbon (SOC) mapping is crucial for addressing critical challenges in environmental sustainability and food security. This study evaluates the suitability of the synergistic use of multi-temporal and high-resolution radar and optical remote sensing data for SOC prediction in the Kaffrine region of Senegal, covering over 1.1 million hectares. For this purpose, various scenarios were developed: Scenario 1 (Sentinel-1 data), Scenario 2 (Sentinel-2 data), Scenario 3 (Sentinel-1 and Sentinel-2 combination), Scenario 4 (topographic features), and Scenario 5 (Sentinel-1 and -2 with topographic features). The findings from comparing three different algorithms (Random Forest (RF), XGBoost, and Support Vector Regression (SVR)) with 671 soil samples for training and 281 samples for model evaluation highlight that RF outperformed the other models across different scenarios. Moreover, using Sentinel-2 data alone yielded better results than using only Sentinel-1 data. However, combining Sentinel-1 and Sentinel-2 data (Scenario 3) further improved the performance by 6% to 11%. Including topographic features (Scenario 5) achieved the highest accuracy, reaching an R2 of 0.7, an RMSE of 0.012%, and an RPIQ of 5.754 for the RF model. Applying the RF and XGBoost models under Scenario 5 for SOC mapping showed that both models tended to predict low SOC values across the study area, which is consistent with the predominantly low SOC content observed in most of the training data. This limitation constrains the ability of ML models to capture the full range of SOC variability, particularly for less frequent, slightly higher SOC values.

Three-dimensional spatiotemporal variation of soil organic carbon and its influencing factors at the basin scale

The variability of soil organic carbon (SOC) extends across three dimensions. However, quantitative analyses of the factors influencing spatiotemporal variations of SOC in various soil depth is scarce. This study leverages legacy data from two soil surveys conducted in the Dongting Lake Basin during the 1980s and the 2010s, employing Random Forest models to generate three-dimensional SOC maps. Through correlation analysis and permutation importance, we identified the primary factors driving temporal and spatial changes of SOC. The results showed that in the 2010s, SOC storage up to a depth of 1 m in the Dongting Lake Basin was approximately 2.95 Pg, increasing at an average rate of 0.0047 Pg C per year since the 1980s. Regions with higher average SOC contents were predominantly found in the western, southern, and eastern parts of the basin, despite significant losses over the 30-year period. In contrast, the central and northern areas, which initially had lower SOC contents in the 1980s, exhibited increases by the 2010s. Soil depth was the most influential predictor of SOC patterns in both the 1980s and 2010s. Meanwhile, relief and organism factors were primarily responsible for spatial variations in SOC, with the influence of organism factors diminishing by the 2010s. The temporal variations of SOC were chiefly attributed to changes in soil conservation practices, extreme precipitation events, and grain production. Consequently, it is imperative to prioritize ecological restoration and conservation tillage practices to mitigate the impacts of extreme weather conditions and safeguard food security.