Digital soil mapping using remote sensing indices, terrain attributes, and vegetation features in the rangelands of northeastern Iran

Machine learning-based digital mapping of soil organic carbon and texture in the mid-Himalayan terrain

Mountain soils have received significant attention due to their profound influence on ecological processes and environmental factors. However, mapping these soils in digital soil mapping technique encounters several challenges, including high local variability, non-linear relationships between environmental covariates and soil properties, limited accessibility in complex topographical settings, and the absence of universally applicable covariates for soil formation. To address these issues, this study integrates soil-forming factors of the scorpan model to map soil organic carbon (SOC) and soil texture in the mid-Himalayas. By considering over 100 environmental covariates, with a focus on terrain parameters relevant to mountainous environments, the study aims to enhance the accuracy of ML regression models through augmentation techniques that overcome data insufficiency. Using augmented soil observations and covariates, a non-parametric random forest regression model is trained and applied to predict soil variables across the study area, generating a continuous fine-resolution map. The model's performance, evaluated against an unknown dataset, was significant with an R-square of 0.80, 0.79, 0.72, and 0.84 for clay, sand, silt, and SOC, respectively. Furthermore, a sensitivity analysis of the environmental covariates and their impact on the model revealed that all the soil-forming factors make a significant contribution to the model's effectiveness. The insights gained from this research contribute to a better understanding of mountain soils and facilitate the development of effective conservation and sustainable management strategies for mountainous regions.

Synergetic use of DEM derivatives, Sentinel-1 and Sentinel-2 data for mapping soil properties of a sloped cropland based on a two-step ensemble learning method

Understanding the spatial variability of soil organic matter (SOM), soil total nitrogen (STN), soil total phosphorus (STP), and soil total potassium (STK) is important to support site-specific agronomic management, food production, and climate change adaptation. High-resolution remote sensing imageries have emerged as an innovative solution to investigate the spatial variation in agricultural soils with machine learning (ML) algorithms. However, the predictive power of the individual and combined effects of Sentinel-1 (S1) synthetic aperture radar (SAR) and Sentinel-2 (S2) multispectral images for mapping soil properties, especially STN, STP, and STK, have rarely been investigated. Moreover, single ML model may achieve unstable performance for predicting multiple soil properties due to strong spatial heterogeneity. This study explored the combine use of S1, S2, and DEM derivatives to map SOM, STN, STP, and STK content of a sloped cropland of northeastern China. A two-step method with a weighted sum of four ML models was proposed to improve the accuracy and robustness in predicting multiple soil properties. Our results showed that single ML model has various performance in predicting the four soil properties. The optimal ML models could explain approximately 56 %, 53 %, 56 % and 37 % of the variability of SOM, STN, STP, and STK, respectively. Using the weights estimated through a 10-fold cross-validation procedure, the two-step ensemble learning model was retrained and showed more robust performance than the four ML models, in which the prediction accuracy was improved by 2.38 %, 1.40 %, 3.52 %, and 3.29 % for SOM, STN, STP, and STK, respectively. Our results also showed that the optical S2 derived features, especially the two S2 short-wave infrared bands, enhanced vegetation index, and soil adjusted vegetation index, were more important for soil property prediction than S1 data and DEM derivatives. Compared with individual sensor, a combination of S1 and S2 data yielded more accurate predictions of STN and STP but not for SOM and STK. The results of this study highlight the potential of high-resolution S1 and S2 data and the two-step method for soil property prediction at farmland scale.

Digital mapping of soil pH and carbonates at the European scale using environmental variables and machine learning

Soil pH and carbonates (CaCO₃) are important indicators of soil chemistry and fertility, and the prediction of their spatial distribution is critical for the agronomic and environmental management. Digital soil mapping (DSM) techniques are widely accepted for the geospatial analysis of the soil properties. They are rapid and cost-efficient approaches that can provide quantitative prediction. However, the digital mapping of soil pH and CaCO₃ are not well studied, especially at a continental scale. In this research, we mapped the soil pH and CaCO₃ at the European scale using multisource environmental variables and machine learning approaches. Moderate Resolution Imaging Spectroradiometer (MODIS) products, terrain attributes, and climatic variables were considered. Meanwhile, nine machine learning algorithms, namely, three linear and six nonlinear models, were used for the spatial prediction of soil pH and CaCO₃. The land use and cover area frame statistical survey (LUCAS) 2015 topsoil dataset provided by the European Soil Data Centre was utilised. The performances of different models were compared and analysed in terms of coefficient of determination (R²), root mean square error (RMSE), and ratio of performance to deviation (RPD). Specifically, nonlinear machine learning models outperformed the linear ones, and extremely randomized trees (ERT) gave the most satisfactory result for soil pH (R² = 0.70, RMSE = 0.75, and RPD = 1.84) and CaCO₃ (R² = 0.53, RMSE = 93.49 g/kg, and RPD = 1.46). The results revealed that MODIS products and climatic variables were important in predicting soil pH and CaCO₃. Moreover, spatial distribution of soil pH and CaCO₃ in Europe were mapped at 250 m resolution, and the areas with high CaCO₃ content always showed high soil pH value.

Improving the Prediction of Soil Organic Matter in Arable Land Using Human Activity Factors

Detailed spatial distribution of soil organic matter (SOM) in arable land is essential for agricultural management and decision making. Based on digital soil mapping (DSM) theory, much attention has been focused on the selection of environmental covariates. However, the importance of human activity factors in SOM prediction has not received enough attention, especially in arable soil. Moreover, due to the insufficient amount of soil sampling data used to train and validate the DSM model, the prediction results may be questionable, and some even contradictory. This paper explores the effectiveness of the human footprint, amount of fertilizer application, agronomic management level, crop planting type, and irrigation guarantee degree in SOM mapping of arable land in Heilongjiang Province. The results show that the model only including environmental covariates accounts for 41% of the variation in SOM distribution. The model combining the five human activity factors increases the SOM spatial prediction by 39% in terms of R2 (coefficient of determination), 12% in terms of RMSE (root mean square error), 15% in terms of MAE (mean absolute error), and 11% in terms of LCCC (Lin’s concordance correlation coefficient), showing better prediction accuracy and performance. This indicates that human activity factors play a crucial role in determining SOM distribution in arable land. In the SOM prediction, soil moisture is the most important environmental covariate, and the amount of fertilizer application with a relative importance of 11.36% (ranking 3rd) is the most important human activity factor, higher than the annual average precipitation and elevation. From a spatial point of view, the Sanjiang Plain is a difficult area for prediction.

A Comparison of Model Averaging Techniques to Predict the Spatial Distribution of Soil Properties

This study tested and evaluated a suite of nine individual base learners and seven model averaging techniques for predicting the spatial distribution of soil properties in central Iran. Based on the nested-cross validation approach, the results showed that the artificial neural network and Random Forest base learners were the most effective in predicting soil organic matter and electrical conductivity, respectively. However, all seven model averaging techniques performed better than the base learners. For example, the Granger–Ramanathan averaging approach resulted in the highest prediction accuracy for soil organic matter, while the Bayesian model averaging approach was most effective in predicting sand content. These results indicate that the model averaging approaches could improve the predictive accuracy for soil properties. The resulting maps, produced at a 30 m spatial resolution, can be used as valuable baseline information for managing environmental resources more effectively.

Predicting Bioaccumulation of Potentially Toxic Element in Soil–Rice Systems Using Multi-Source Data and Machine Learning Methods: A Case Study of an Industrial City in Southeast China

Potentially toxic element (PTE) pollution in farmland soils and crops is a serious cause of concern in China. To analyze the bioaccumulation characteristics of chromium (Cr), zinc (Zn), copper (Cu), and nickel (Ni) in soil-rice systems, 911 pairs of top soil (0–0.2 m) and rice samples were collected from an industrial city in Southeast China. Multiple linear regression (MLR), support vector machines (SVM), random forest (RF), and Cubist were employed to construct models to predict the bioaccumulation coefficient (BAC) of PTEs in soil–rice systems and determine the potential dominators for PTE transfer from soil to rice grains. Cr, Cu, Zn, and Ni contents in soil of the survey region were higher than corresponding background contents in China. The mean Ni content of rice grains exceeded the national permissible limit, whereas the concentrations of Cr, Cu, and Zn were lower than their thresholds. The BAC of PTEs kept the sequence of Zn (0.219) > Cu (0.093) > Ni (0.032) > Cr (0.018). Of the four algorithms employed to estimate the bioaccumulation of Cr, Cu, Zn, and Ni in soil–rice systems, RF exhibited the best performance, with coefficient of determination (R2) ranging from 0.58 to 0.79 and root mean square error (RMSE) ranging from 0.03 to 0.04 mg kg−1. Total PTE concentration in soil, cation exchange capacity (CEC), and annual average precipitation were identified as top 3 dominators influencing PTE transfer from soil to rice grains. This study confirmed the feasibility and advantages of machine learning methods especially RF for estimating PTE accumulation in soil–rice systems, when compared with traditional statistical methods, such as MLR. Our study provides new tools for analyzing the transfer of PTEs from soil to rice, and can help decision-makers in developing more efficient policies for regulating PTE pollution in soil and crops, and reducing the corresponding health risks.

Prediction of Soil Organic Carbon under Different Land Use Types Using Sentinel-1/-2 Data in a Small Watershed

Soil organic carbon (SOC) is a key property for evaluating soil quality. SOC is thus an important parameter of agricultural soils and needs to be regularly monitored. The aim of this study is to explore the potential of synthetic aperture radar (SAR) satellite imagery (Sentinel-1), optical satellite imagery (Sentinel-2), and digital elevation model (DEM) data to estimate the SOC content under different land use types. The extreme gradient boosting (XGboost) algorithm was used to predict the SOC content and evaluate the importance of feature variables under different land use types. For this purpose, 290 topsoil samples were collected and 49 features were derived from remote sensing images and DEM. Feature selection was carried out to prevent data redundancy. Coefficient of determination (R2), mean absolute error (MAE), mean squared error (MSE), percent root mean squared error (%RMSE), ratio of performance to interquartile range (RPIQ), and corrected akaike information criterion (AICc) were employed for evaluating model performance. The results showed that Sentinel-1 and Sentinel-2 data were both important for the prediction of SOC and the prediction accuracy of the model differed with land use types. Among them, the prediction accuracy of this model is the best for orchard (R2 = 0.86 and MSE = 0.004%), good for dry land (R2 = 0.74 and MSE = 0.008%) and paddy field (R2 = 0.66 and MSE = 0.009%). The prediction model of SOC content is effective and can provide support for the application of remote sensing data to soil property monitoring.

Multiscaling NDVI Series Analysis of Rainfed Cereal in Central Spain

Vegetation indices time series analysis is increasingly improved for characterizing agricultural land processes. However, this is challenging because of the multeity of factors affecting vegetation growth. In semiarid regions the rainfall, the soil properties and climate are strongly correlated with crop growth. These relationships are commonly analyzed using the normalized difference vegetation index (NDVI). NDVI series from two sites, belonging to different agroclimatic zones, were examined, decomposing them into the overall average pattern, residuals, and anomalies series. All of them were studied by applying the concept of the generalized Hurst exponent. This is derived from the generalized structure function, which characterizes the series’ scaling properties. The cycle pattern of NDVI series from both zones presented differences that could be explained by the differences in the climatic precipitation pattern and soil characteristics. The significant differences found in the soil reflectance bands confirm the differences in both sites. The scaling properties of NDVI original series were confirmed with Hurst exponents higher than 0.5 showing a persistent structure. The opposite was found when analyzing the residual and the anomaly series with a stronger anti-persistent character. These findings reveal the influences of soil–climate interactions in the dynamic of NDVI series of rainfed cereals in the semiarid.

High-resolution digital mapping of soil organic carbon and soil total nitrogen using DEM derivatives, Sentinel-1 and Sentinel-2 data based on machine learning algorithms

Soil organic carbon (SOC) and soil total nitrogen (STN) are important indicators of soil health and play a key role in the global carbon and nitrogen cycles. High-resolution radar Sentinel-1 and multispectral Sentinel-2 images have the potential to investigate soil spatial distribution information over a large area, although Sentinel-1 and Sentinel-2 data have rarely been combined to map either SOC or STN content. In this study, we applied machine learning techniques to map both SOC and STN content in the southern part of Central Europe using digital elevation model (DEM) derivatives, multi-temporal Sentinel-1 and Sentinel-2 data, and evaluated the potential of different remote sensing sensors (Sentinel-1 and Sentinel-2) to predict SOC and STN content. Four machine-learners including random forest (RF), boosted regression trees (BRT), support vector machine (SVM) and Bagged CART were used to construct predictive models of SOC and STN contents based on 179 soil samples and different combinations of environmental covariates. The performance of these models was evaluated based on a 10-fold cross-validation method by three statistical indicators. Overall, the BRT model performed better than RF, SVM and Bagged CART, and these models yielded similar spatial distribution patterns of SOC and STN. Our results showed that multi-source sensor methods provided more accurate predictions of SOC and STN contents than individual sensors. The application of radar Sentinel-1 and multispectral Sentinel-2 images proved useful for predicting SOC and STN. A combination of Sentinel-1/2-derived predictors and DEM derivatives yielded the highest prediction accuracy. The prediction accuracy changed with and without the Sentinel-1/2-derived predictors, with the R² for estimating both SOC and STN content using the BRT model increasing by 12.8% and 18.8%, respectively. Topographic variables were the main explanatory variables for SOC and STN predictions, where elevation was assigned as the variable with the most importance by the models. The results of this study illustrate the potential of free high-resolution radar Sentinel-1 and multispectral Sentinel-2 data as input when developing SOC and STN prediction models.

Improved digital soil mapping with multitemporal remotely sensed satellite data fusion: A case study in Iran

Modeling and mapping of soil properties are critical in many environmental, climatic, ecological and hydrological applications. Digital soil mapping (DSM) techniques are now commonly applied to predict soil properties with limited data by developing predictive relationships with environmental covariates. Most studies derive covariates from a digital elevation model (named static covariates). Many works also include single-day remotely sensed satellite imagery. However, multitemporal satellite images can capture information about soil properties over time and bring additional information in predicting soil properties in DSM. We refer to covariates derived from multitemporal satellite images as dynamic covariates. The objective of this study was to assess the performance of DSM when using terrain derivatives (static covariates), single-date remotely sensed satellite indices (limited dynamic covariates), multitemporal satellite indices (dynamic covariates), and combinations of terrain derivatives and satellite indices (covariate fusion) as covariates in predicting soil properties and estimating uncertainty. Three soil properties are considered in this study: organic carbon (OC), sand content, and calcium carbonate equivalent (CCE). Inclusion of single and/or multitemporal remotely sensed satellite indices improved the prediction of soil properties over traditionally used terrain indices. Significant improvements were observed in the prediction of soil properties using two models, Cubist and random forest (RF). The increase in the R² values for Cubist and RF were 126% and 78% for OC, 110% and 54% for sand, and 87% and 32% for CCE. The RMSE decreased by 34% and 27% for OC, 25% and 12% for sand, and 39% and 19% for CCE, when compared to the terrain indices only model. This also reduced the uncertainty of estimation and mapping. These clearly showed the advantage of using multitemporal satellite data fusion rather than simply using static terrain indices for DSM of soil properties to deliver a great potential in improving soil modeling and mapping for many applications.

Combining Object-Based Image Analysis with Topographic Data for Landform Mapping: A Case Study in the Semi-Arid Chaco Ecosystem, Argentina

This paper presents an object-based approach to mapping a set of landforms located in the fluvio-eolian plain of Rio Dulce and alluvial plain of Rio Salado (Dry Chaco, Argentina), with two Landsat 8 images collected in summer and winter combined with topographic data. The research was conducted in two stages. The first stage focused on basic-spectral landform classifications where both pixel- and object-based image analyses were tested with five classification algorithms: Mahalanobis Distance (MD), Spectral Angle Mapper (SAM), Maximum Likelihood (ML), Support Vector Machine (SVM) and Decision Tree (DT). The results obtained indicate that object-based analyses clearly outperform pixel-based classifications, with an increase in accuracy of up to 35%. The second stage focused on advanced object-based derived variables with topographic ancillary data classifications. The combinations of variables were tested in order to obtain the most accurate map of landforms based on the most successful classifiers identified in the previous stage (ML, SVM and DT). The results indicate that DT is the most accurate classifier, exhibiting the highest overall accuracies with values greater than 72% in both the winter and summer images. Future work could combine both, the most appropriate methodologies and combinations of variables obtained in this study, with physico-chemical variables sampled to improve the classification of landforms and even of types of soil.