Search

The scientific field of precision agriculture employs increasingly innovative techniques to optimize inputs, maximize profitability, and reduce environmental impact. However, obtaining a high number of soil samples is challenging in order to make precision agriculture viable. There is a trade-off between the amount of data needed and the time and resources spent to obtain these data compared to the accuracy of the maps produced with more or fewer points. In the present study, the research was based on an exhaustive dataset of apparent electrical conductivity (aEC) containing 3906 points distributed along 26 transects with spacing between each of up to 40 m, measured by the proximal soil sensor EM38-MK2, for a grain-producing area of 72 ha in São Paulo, Brazil. A second sparse dataset was simulated, showing only four transects with a 400 m distance and, in the end, only 162 aEC points. The aEC map via ordinary kriging (OK) from the grid with 26 transects was considered the reference, and two other mapping approaches were used to map aEC via sparse grid: kriging with external drift (KED) and geographically weighted regression (GWR). These last two methods allow the increment of auxiliary variables, such as those obtained by remote sensors that present spatial resolution compatible with the pivot scale, such as data from the Landsat-8, Aster, and Sentinel-2 satellites, as well as ten terrain covariates derived from the Alos Palsar digital elevation model. The KED method, when used with the sparse dataset, showed a relatively good fit to the aEC data (R2 = 0.78), with moderate prediction accuracy (MAE = 1.26, RMSE = 1.62) and reasonable predictability (RPD = 1.76), outperforming the GWR method, which had the weakest performance (R2 = 0.57, MAE = 1.78, RMSE = 2.30, RPD = 0.81). The reference aEC map using the exhaustive dataset and OK showed the highest accuracy with an R2 of 0.97, no systematic bias (ME = 0), and excellent precision (RMSE = 0.56, RPD = 5.86). Management zones (MZs) derived from these maps were validated using soil texture data from clay samples measured at 0–10 cm depth in a grid of 72 points. The KED method demonstrated the highest potential for accurately defining MZs for irrigation, producing a map that closely resembled the reference MZ map, thereby providing reliable guidance for irrigation management.

Soil organic matter (SOM) and the ratio of soil organic carbon to total nitrogen (C/N ratio) are fundamental to the ecosystem services provided by soils. Therefore, understanding the spatial distribution and relationships between the SOM components mineral-associated organic matter (MAOM), particulate organic matter (POM), and C/N ratio is crucial. Three ensemble machine learning models were trained to obtain spatial predictions of the C/N ratio, MAOM, and POM in German agricultural topsoil (0–10 cm). Parameter optimization and model evaluation were performed using nested cross-validation. Additionally, a modification to the regressor chain was applied to capture and interpret the interactions among the C/N ratio, MAOM, and POM. The ensemble models yielded mean absolute percent errors (MAPEs) of 8.2% for the C/N ratio, 14.8% for MAOM, and 28.6% for POM. Soil type, pedo-climatic region, hydrological unit, and soilscapes were found to explain 75% of the variance in MAOM and POM, and 50% in the C/N ratio. The modified regressor chain indicated a nonlinear relationship between the C/N ratio and SOM due to the different decomposition rates of SOM as a result of variety in its nutrient quality. These spatial predictions enhance the understanding of soil properties’ distribution in Germany.

This study assessed the perception and use of digital applications for soil fertility management and conservation strategies among small-scale crop farmers in southwest Nigeria. A total of 376 farmers were randomly selected across the six southwest states. The data collected were analyzed using descriptive statistics. The majority of the farmers relied on perception and other non-scientific approaches such as the appearance of weeds and performance of crops in the previous season to assess soil fertility. Only 1.1% and 0.3% of the farmers assessed soil fertility through soil tests and digital applications, respectively. Most farmers adopted bush fallowing and the use of inorganic fertilizers to improve soil fertility. Although 4.8% of the farmers indicated that they had digital applications on their mobile phones, only 2.9% claimed to have used these. More than half (56.4%) of the farmers stated that a lack of awareness of the existence of digital applications and internet-enabled telephones were the reasons they have not been able to use digital applications. The majority of the farmers (97.3%) indicated their willingness to embrace the use of new farm decision digital applications which could provide more information, especially on soil fertility, if introduced. More extensive services focusing on older, less literate farmers and farmers who hitherto did not belong to any farmers’ association are advocated for in order to encourage the use of digital applications and soil fertility management and conservation practices.

Intensive agricultural practices lead to a deterioration in soil quality, causing a decline in farm productivity and quality, and disturbing the ecosystem balance in command areas. To achieve sustainable production and implement effective soil management strategies, understanding the state and spatial variability of soil quality is essential. The study aims to enhance the understanding of soil quality variability and provide actionable insights for sustainable soil management. In this regard, principal component analysis (PCA) and digital soil mapping were used to assess and map the spatial variability of the soil quality index (SQI) in the Cauvery command area, Mandya district, Karnataka, India. A total of 145 georeferenced soil samples were drawn at 0–15 cm depth and analyzed for physico-chemical properties. PCA was used to reduce the dataset into a minimum dataset as eight important soil indicators and to determine relative weightage factors, which were used for assessing SQI with linear and non-linear scoring methods. For spatial assessment of SQI, the random forest algorithm with environmental covariates was used to map eight soil indicators selected in the minimum dataset. The soil property maps were subjected to linear and non-linear scoring, followed by multiplying with corresponding weightage factors and summation to produce SQI maps. Results reveal that values of SQI calculated using linear scoring, range from 0.10 to 0.64, with a mean of 0.39, while non-linear scoring exhibits a wider range of 0.12 to 0.78 and a mean of 0.48. With a slight higher sensitivity index of 6.5, non-linear scoring proved to be the better scoring method compared to linear scoring. Spatial assessment shows that the R2 and LCC between the calculated and predicted SQI were higher for non-linear scoring (0.66 and 0.66) compared to linear scoring (0.60 and 0.65). The SQI maps reveal high spatial variability with more than 40 percent of soils classified as moderate-to-low index. The soils with low SQI were distributed in eastern parts, whereas western parts exhibited high-to-very-high soil quality. To achieve production goals and improve soil quality in the eastern region, sustainable soil and crop management strategies must be developed, and their effects on soil quality should be assessed.

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.

Recently, numerous spatial prediction methods with diverse characteristics have been developed. Selecting an appropriate spatial prediction method, along with its data preprocessing and parameter settings, presents a challenging task for many users, especially for non-experts. This paper addresses this challenge by exploring the potential of automated machine learning method proposed in artificial intelligent domain to automatically determine the most suitable method among various machine learning methods. As a case study, the automated machine learning method was applied to predict the spatial distribution of soil subgroups in Heshan farm. A total of 110 soil samples and 10 terrain variables were utilized in the designed experiments. To evaluate the performance, the proposed method was compared to each machine learning method with default parameters values or parameters determined by expert knowledge. The results showed that the proposed method typically achieved higher accuracy scores than the two alternative methods. This suggests that automated machine learning performs effectively in scenarios where numerous machine learning methods are available and offers practical utility in reducing the dependence on users’ expertise in spatial prediction. However, a more robust automated framework should be developed to encompass a broader range of spatial prediction methods, such as spatial statistic methods, rather than only focusing on machine learning methods.

A WebGis tool called GoProsit has been developed to support winegrowers in planning a new sustainable vineyard and in the identification of high-quality terroir in Tuscany, Central Italy, by providing various information on soils, climate, hydrological risks, and fertilization. GoProsit, hosted by the web platform GEAPP, is a free, user-friendly, and interactive Geographic Decision Support System (GDSS). Soil data behind the WebGis tool has a 1 ha resolution, achieved by processing the legacy vector-type soil database of the Tuscany Region with the DSMART (Disaggregation and Harmonization of Soil Map Units Through Resampled Classification Trees as supervised classification) algorithm, which disaggregated the map to 297,023 vineyard grid cells. Each grid cell holds climatic and pedologic information, along with physical and chemical features for each horizon of the most probable soil. GoProsit also provides soil maps in image format obtained by georeferencing about 50 historical soil maps (1969–2012). Finally, GoProsit runs and returns the outputs of six models: (a) carbon footprint, (b) potential erosion and maximum vine row length compatible with tolerable erosion, (c) potential water stress, (d) risk of runoff/waterlogging, (e) identification of suitable rootstocks, and (f) nutritional needs before planting. Statistics of the main model results for the investigated area are reported. This promising tool will soon be usable for the whole Italian territory; however, its potential makes it suitable for use in any wine-growing district.

The deployment of remote sensing platforms has facilitated the mapping of soil properties to a great extent. However, the accuracy of these soil property estimates is compromised by the presence of non-soil cover, which introduces interference with the acquired reflectance spectra over pixels. Therefore, current soil property estimation by remote sensing is limited to bare soil pixels, which are identified based on spectral indices of vegetation. Our study proposes a composite mapping approach to extend the soil properties mapping beyond bare soil pixels, associated with an uncertainty map. The proposed approach first classified the pixels based on their bare soil fractional cover by spectral unmixing. Then, a specific regression model was built and applied to each bare soil fractional cover class to estimate clay content. Finally, the clay content maps created for each bare soil fractional cover class were mosaicked to create a composite map of clay content estimations. A bootstrap procedure was used to estimate the standard deviation of clay content predictions per bare soil fractional cover dataset, which represented the uncertainty of estimations. This study used a hyperspectral image acquired by the Airborne Visible/Infrared Imaging Spectrometer-Next Generation (AVIRIS-NG) sensor over cultivated fields in South India. The proposed approach provided modest performances in prediction (Rval2 ranging from 0.53 to 0.63) depending on the bare soil fractional cover class and showed a correct spatial pattern, regardless of the bare soil fraction classes. The model’s performance was observed to increase with the adoption of higher bare soil fractional cover thresholds. The mapped area ranged from 10.4% for pixels with bare soil fractional cover >0.7 to 52.7% for pixels with bare soil fractional cover >0.3. The approach thus extended the mapped surface by 42.4%, while maintaining acceptable prediction performances. Finally, the proposed approach could be adopted to extend the mapping capability of planned and current hyperspectral satellite missions.

Soil particle size fractions (PSFs) are important properties for understanding the physical and chemical processes in soil systems. Knowledge about the distribution of soil PSFs is critical for sustainable soil management. Although log-ratio transformations have been widely applied to soil PSFs prediction, the statistical distribution of original data and the transformed data given by log-ratio transformations is different, resulting in biased estimates of soil PSFs. Therefore, multivariate random forest (MRF) was utilized for the simultaneous prediction of soil PSFs, as it is able to capture dependencies and internal relations among the three components. Specifically, 243 soil samples collected across the Loess Plateau were used. Meanwhile, Landsat data, terrain attributes, and climatic variables were employed as environmental variables for spatial prediction of soil PSFs. The results depicted that MRF gave satisfactory soil PSF prediction performance, where the R2 values were 0.62, 0.53, and 0.73 for sand, silt, and clay, respectively. Among the environmental variables, nighttime land surface temperature (LST_N) presented the highest importance in predicting soil PSFs in the Loess Plateau, China. Maps of soil PSFs and texture were generated at a 30 m resolution, which can be utilized as alternative data for soil erosion management and ecosystem conservation.

Soil organic carbon (SOC) is generally thought to act as a carbon sink; however, in areas with high spatial heterogeneity, using a single model to estimate the SOC of the whole study area will greatly reduce the simulation accuracy. The earth surface unit division is important to consider in building different models. Here, we divided the research area into different habitat patches using partitioning around a medoids clustering (PAM) algorithm; then, we built an SOC simulation model using machine learning algorithms. The results showed that three habitat patches were created. The simulation accuracy for Habitat Patch 1 (R2 = 0.55; RMSE = 2.89) and Habitat Patch 3 (R2 = 0.47; RMSE = 3.94) using the XGBoost model was higher than that for the whole study area (R2 = 0.44; RMSE = 4.35); although the R2 increased by 25% and 6.8%, the RMSE decreased by 33.6% and 9.4%, and the field sample points significantly declined by 70% and 74%. The R2 of Habitat Patch 2 using the RF model increased by 17.1%, and the RMSE also decreased by 10.5%; however, the sample points significantly declined by 58%. Therefore, using different models for corresponding patches will significantly increase the SOC simulation accuracy over using one model for the whole study area. This will provide scientific guidance for SOC or soil property monitoring with low field survey costs and high simulation accuracy.

Acid sulfate soil mapping is the first step to avoid possible environmental damages created by one of the most problematic soils existing in nature. One of the problems in acid-sulfate soil mapping is the lack of soil samples in some regions. This prevents the creation of occurrence maps. For the first recognition of these regions, a possible solution could be the use of soil samples from other areas with similar characteristics. In this study, we analyze if a machine learning method is able to correctly classify the soil samples in an area where it has not been trained. For this, Random Forest and two different regions located in southern Finland with a similar composition of soils are considered.

Soil organic carbon (SOC) contents and stocks provide valuable insights into soil health, nutrient cycling, greenhouse gas emissions, and overall ecosystem productivity. Given this, remote sensing data coupled with advanced machine learning (ML) techniques have eased SOC level estimation while revealing its patterns across different ecosystems. However, despite these advances, the intricacies of training reliable and yet certain SOC models for specific end-users remain a great challenge. To address this, we need robust SOC uncertainty quantification techniques. Here, we introduce a methodology that leverages conformal prediction to address the uncertainty in estimating SOC contents while using remote sensing data. Conformal prediction generates statistically reliable uncertainty intervals for predictions made by ML models. Our analysis, performed on the LUCAS dataset in Europe and incorporating a suite of relevant environmental covariates, underscores the efficacy of integrating conformal prediction with another ML model, specifically random forest. In addition, we conducted a comparative assessment of our results against prevalent uncertainty quantification methods for SOC prediction, employing different evaluation metrics to assess both model uncertainty and accuracy. Our methodology showcases the utility of the generated prediction sets as informative indicators of uncertainty. These sets accurately identify samples that pose prediction challenges, providing valuable insights for end-users seeking reliable predictions in the complexities of SOC estimation.

In digital soil mapping, machine learning models have been widely applied. However, the accuracy of machine learning models can be limited by the use of a single model and a small number of soil samples. This study introduces a novel method, semi-supervised classification combined with stacking learning (SSC-SL), to enhance soil classification mapping in hilly and low-mountain areas of Northern Jurong City, Jiangsu Province, China. This study incorporated Gaofen-2 (GF-2) remote sensing imagery along with its associated remote sensing indices, the ALOS Digital Elevation Model (DEM) and their derived topographic factors, and soil parent material data in its modelling process. We first used three base learners, Ranger, Rpart, and XGBoost, to construct the SL model. In addition, we employed the fuzzy c-means clustering algorithm (FCM) to construct a clustering map. To fully leverage the information from a multitude of environmental variables, understand the distribution of data, and enhance the effectiveness of the classification, we selected unlabelled samples near the boundaries of the patches on the clustering map. The SSC-SL model demonstrated superior stability and performance, with optimal accuracy at a 0.9 confidence level, achieving an overall accuracy of 0.77 and a kappa coefficient of 0.73. These metrics exceeded those of the highest performing base learner (Ranger model) by 10.4% and 12.3%, respectively, and they outperformed the least effective base learner (Rpart model) by 27.3% and 32.9%. It notably improves the spatial distribution accuracy of soil types. Key environmental variables influencing soil type distribution include soil parent material (SPM), land use (LU), the multi-resolution valley bottom flatness index (MRVBF), and Elevation (Ele). In conclusion, the SSC-SL model offers a novel and effective approach for enhancing the predictive accuracy of soil classification mapping.

Mapping soil organic carbon (SOC) accurately is essential for sustainable soil resource management. Hyperspectral data, a vital tool for SOC mapping, is obtained through both laboratory and satellite-based sources. While laboratory data is limited to sample point monitoring, satellite hyperspectral imagery covers entire regions, albeit susceptible to external environmental interference. This study, conducted in the Yuncheng Basin of the Yellow River Basin, compared the predictive accuracy of laboratory hyperspectral data (ASD FieldSpec4) and GF-5 satellite hyperspectral imagery for SOC mapping. Leveraging fractional order derivatives (FODs), various denoising methods, feature band selection, and the Random Forest model, the research revealed that laboratory hyperspectral data outperform satellite data in predicting SOC. FOD processing enhanced spectral information, and discrete wavelet transform (DWT) proved effective for GF-5 satellite imagery denoising. Stability competitive adaptive re-weighted sampling (sCARS) emerged as the optimal feature band selection algorithm. The 0.6FOD-sCARS RF model was identified as the optimal laboratory hyperspectral prediction model for SOC, while the 0.8FOD-DWT-sCARS RF model was deemed optimal for satellite hyperspectral prediction. This research, offering insights into farmland soil quality monitoring and strategies for sustainable soil use, holds significance for enhancing agricultural production efficiency.

The demand for high quality and low-cost spatial distribution information of soil texture classes (STCs) is of great necessity in developing countries. This paper explored digital mapping of topsoil STCs using soil fractions, terrain attributes and artificial neural network (ANN) algorithms. The 4493 soil samples covering 10 out of 12 STCs were collected from the rice fields of the Guilan Province of Northern Iran. Nearly 75% of the dataset was used to train the ANN algorithm and the remaining 25% to apply a repeated 10-fold cross-validation. Spatial prediction of soil texture fractions was carried out via geostatistics and then a pixel-based approach with an ANN algorithm was performed to predict STCs. The ANN presented reasonable accuracy in estimating USDA STCs with a kappa coefficient of 0.38 and pixel classification accuracy percentage of 52%. Hybridizing soil particles with relief covariates yielded better estimates for coarse- and medium-STCs. The results also showed that clay particle and terrain attributes are more important covariates than plant indices in areas under single crop cultivation. However, it is recommended to examine the approach in areas with diverse vegetation cover.

Soil salinization can decrease soil productivity and is a significant factor in causing land degradation. Precision mapping of salinization in agricultural fields would improve farmland management. This study focuses on the cropland in the Manas River Basin, located in the arid region of northwest China. It explores the potential of a soil mapping method, the Soil–Land Inference Model (SoLIM), which only requires a small number of soil samples to infer soil salinization of farmlands in arid areas. The model was utilized to create spatial distribution maps of soil salinity for the years 2009 and 2017, and changes in the distribution were analyzed. The research results indicate: (1) Through the analysis of sample point data, it was observed that soil salinity in the study area tends to accumulate in the surface layer (0–30 cm) in spring and in the subsoil layer (60–90 cm) during the crop growing season, with significant spatial variability. Therefore, it is necessary to conduct detailed salinity mapping. (2) Using field measurements as validation data, the simulation results of the SoLIM were compared with spatial interpolation methods and regression models. The SoLIM showed higher inference accuracy, with R2 values for the simulation results of the three soil layers all exceeding 0.5. (3) The SoLIM spatial inference showed salt accumulation in the northern part and desalination in the southern part. The findings of this study suggest that the SoLIM has the potential to effectively map soil salinization of croplands in arid areas, offering an efficient solution for monitoring soil salinity in arid oasis croplands.

Conventional maps of soil parent material (SPM) types obtained by field survey and manual mapping or predictions from other map data have limited accuracy. Digital soil mapping of SPM types necessitates accurate acquisition of SPM distribution information, which is still a challenge in hilly areas. This study developed a high-accuracy method for SPM identification in hilly areas at the county scale. Based on geographic information system technology, seven feature variables were extracted from the geological map, geomorphic map, digital elevation model, and remote sensing image data of Shanggao County, Jiangxi Province, China. Different feature combination schemes were designed to develop SPM identification models based on random forest (RF), support vector machine (SVM), and maximum likelihood classification (MLC) algorithms. The best SPM identification results were obtained from the RF algorithm using the combination of geological type, geomorphic type, elevation, and slope. Confusion matrices were constructed based on a field survey of 586 validation samples, and the results were evaluated in terms of overall accuracy, precision, recall, F1 score, and Kappa coefficient. The overall accuracy and Kappa coefficient of the results from the optimal RF model were 83.11% and 0.79, respectively, which were 26.11% and 0.31 higher than those of the conventional map, respectively. Its precision and recall for various SPM types were greater than 75%. A comprehensive comparison of the accuracy, uncertainty, and plotting performance of the SPM recognition results reveals that the RF algorithm outperforms the SVM algorithm and the MLC algorithm. Geological type was the largest contributor to SPM identification, followed by geomorphic type, elevation, and slope. The importance of different feature variables varied for distinct SPM types. The accuracy of SPM identification was not improved by selecting more feature variables, such as land use type, normalised difference vegetation index, and topographic wetness index. This study demonstrates the feasibility of high-accuracy county-level SPM mapping in hilly areas based on the RF algorithm using geological type, geomorphic type, elevation, and slope as feature variables. As hilly areas have typical topographic features and SPM types, the proposed method of SPM mapping can be useful for application in other similar areas. There are a few limitations in this study with regard to data quality and resolution, feature variable selection, classification algorithm generalisation, and study area representativeness, which may affect the outcomes and need to be solved.

Despite optical remote sensing (and the spectral vegetation indices) contributions to digital soil-mapping studies of soil organic carbon (SOC), few studies have used active radar remote sensing mission data like that from synthetic aperture radar (SAR) sensors to predict SOC. Bearing in mind the importance of SOC mapping for agricultural, ecological, and climate interests and also the recently developed methods for vegetation monitoring using Sentinel-1 SAR data, in this work, we aimed to take advantage of the high operationality of Sentinel-1 imaging to test the accuracy of SOC prediction at different soil depths using machine learning systems. Using linear, nonlinear, and tree regression-based methods, it was possible to predict the SOC content of soils from western Bahia, Brazil, a region with predominantly sandy soils, using as explanatory variables the SAR vegetation indices. The models fed with SAR sensor polarizations and vegetation indices produced more accurate results for the topsoil layers (0–5 cm and 5–10 cm in depth). In these superficial layers, the models achieved an RMSE in the order of 5.0 g kg−1 and an R2 ranging from 0.16 to 0.24, therefore explaining about 20% of SOC variability using only Sentinel-1 predictors.

There is a growing realization among policymakers that in order to pave the way for the development of evidence-based conservation recommendations for policy, it is essential to improve the capacity for soil-health monitoring by adopting multidimensional and integrated approaches. However, the existing ready-to-use maps are characterized mainly by a coarse spatial resolution (>200 m) and information that is not up to date, making their use insufficient for the EU’s policy requirements, such as the common agricultural policy. This work, by utilizing the Soil Data Cube, which is a self-hosted custom tool, provides yearly estimations of soil thematic maps (e.g., exposed soil, soil organic carbon, clay content) covering all the agricultural area in Lithuania. The pipeline exploits various Earth observation data such as a time series of Sentinel-2 satellite imagery (2018–2022), the LUCAS (Land Use/Cover Area Frame Statistical Survey) topsoil database, the European Integrated Administration and Control System (IACS) and artificial intelligence (AI) architectures to improve the prediction accuracy as well as the spatial resolution (10 m), enabling discrimination at the parcel level. Five different prediction models were tested with the convolutional neural network (CNN) model to achieve the best accuracy for both targeted indicators (SOC and clay) related to the R2 metric (0.51 for SOC and 0.57 for clay). The model predictions supported by the prediction uncertainties based on the PIR formula (average PIR 0.48 for SOC and 0.61 for clay) provide valuable information on the model’s interpretation and stability. The model application and the final predictions of the soil indicators were carried out based on national bare-soil-reflectance composite layers, generated by employing a pixel-based composite approach to the overlaid annual bare-soil maps and by using a combination of a series of vegetation indices such as NDVI, NBR2, and SCL. The findings of this work provide new insights for the generation of soil thematic maps on a large scale, leading to more efficient and sustainable soil management, supporting policymakers and the agri-food private sector.

Soil texture is a key physical property that affects the soil’s ability to retain moisture and nutrients. As a result, it is of extreme importance to conduct remote sensing monitoring of soil texture. Songnen Plain is located in the black soil belt of Northeast China. The development of satellite imagery in remote sensing technology enables the rapid monitoring of large areas. This study aimed to map the surface soil texture of cultivated land in Songnen Plain using Sentinel-2 images and Random Forest (RF) algorithm. We conducted this study by collecting 354 topsoil (0–20 cm) samples in Songnen Plain and evaluating the effectiveness of the bands and spectral indices of Sentinel-2 images and RF algorithm in predicting soil texture (sand, silt, and clay fractions). The results demonstrated that the 16 covariates were moderately and highly correlated with soil texture. And, Band11 of Sentinel-2 images could be used as the corresponding band of soil texture. For sand fraction, the Sentinel-2 images and RF algorithm’s Coefficient of Determination (R2) and Root Mean Square Error (RMSE) were 0.77 and 10.48%, respectively, and for silt fraction, they were 0.75 and 9.38%. Sand fraction decreased from southwest to northeast in Songnen Plain, while silt and clay fractions increased. We found that the Songnen Plain was affected by water erosion and wind erosion, in the northeast and southwest, respectively, providing reference for the implementation of Conservation Tillage policies. The outcome of the study can provide reference for future soil texture mapping with a high resolution.

Accurately mapping the spatial distribution and variation of soil organic matter (SOM) is of great significance for guiding regional soil management. However, the applicability and prediction performance of machine learning techniques in dryland agroecosystems still needs to be further studied. In this study, we collected a total of 733 topsoil samples from the farmland in Xiao County, Anhui Province, which is a typical dryland agroecosystem in the Huang-Huai-Hai Plain. Then, the environmental covariates were selected, and the ordinary kriging (OK), multiple linear stepwise regression (MLR), regression kriging (RK), radial basis function neural network (RBFNN), and random forest (RF) models were conducted to map the SOM content, and the optimal model was ascertained. The results demonstrated that the alkali-hydrolyzable nitrogen (26.11%), available potassium (17.73%), mean annual precipitation (13.26%), and pH (11.80%) were the main controlling factors affecting the spatial distribution of SOM in the study area. Meanwhile, the introduction of environmental covariates can effectively improve the SOM prediction accuracy, and the RF model (R2 = 0.48, MAE = 2.38 g kg−1, MRE = 12.99%, RMSE = 3.14 g kg−1) has a better performance than the RFBNN, MLR, RK, and OK methods. Although there are local differences in the spatial distribution of SOM predicted by the five methods, the overall spatial distribution of SOM was characterized by the low concentration area (13.44–20.00 g kg−1) distributed in the central and northwest of study area, and the high concentration area (24.00–28.95 g kg−1) distributed in the southeast. Overall, our study demonstrated that machine learning-based models could accurately predict the SOM content in dryland agroecosystem, and the produced maps function as baseline maps for sustainable agricultural management.

Unsustainable human management has negative effects on cropland soil organic carbon (SOC), causing a decrease in soil health and the emission of greenhouse gas. Due to contiguous fields, large-scale mechanized operations are widely used in the Northeast China Plain, which greatly improves production efficiency while decreasing the soil quality, especially for SOC. Therefore, an up-to-date SOC map is needed to estimate soil health after long-term cultivation to inform better land management. Using Quantile Regression Forest, a total of 396 soil samples from 132 sampling sites at three soil depth intervals and 40 environmental covariates (e.g., Landsat 8 spectral indices, and WorldClim 2 and MODIS products) selected by the Boruta feature selection algorithm were used to map the spatial distribution of SOC in the cropland of the Northeast Plain at a 90 m spatial resolution. The results showed that SOC increased overall from the southern area to the northern area, with an average of 17.34 g kg−1 in the plough layer (PL) and 13.92 g kg−1 in the compacted layer (CL). At the vertical scale, SOC decreased, with depths getting deeper. The average decrease in SOC from PL to CL was 3.41 g kg−1. Climate (i.e., average temperature, daytime and nighttime land surface temperature, and mean temperature of driest quarter) was the dominant controlling factor, followed by position (i.e., oblique geographic coordinate at 105°), and organism (i.e., the average and variance of net primary productivity in the non-crop period). The average uncertainty was 1.04 in the PL and 1.07 in the CL. The high uncertainty appeared in the area with relatively scattered fields, high altitudes, and complex landforms. This study updated the 90 m resolution cropland SOC maps at spatial and vertical scales, which clarifies the influence of mechanized operations and provides a reference for soil conservation policy-making.

Mapping soil fertility attributes at fine spatial resolution is crucial for site-specific management in precision agriculture. This paper evaluated the performance of mobile measurements using visible and near-infrared spectroscopy (vis–NIR) to predict and map key fertility attributes in tropical soils through local data modeling with partial least squares regression (PLS) and artificial neural network (ANN). Models were calibrated and tested in a calibration area (18-ha) with high spatial variability of soil attributes and then extrapolated in the entire field (138-ha). The models calibrated with ANN obtained superior performance for all attributes. Although ANN models obtained satisfactory predictions in the calibration area (ratio of performance to interquartile range (RPIQ) ≥ 1.7) for clay, organic matter (OM), cation exchange capacity (CEC), base saturation (V), and exchangeable (ex-) Ca, it was not repeated for some of them when extrapolated into the entire field. In conclusion, robust mappings (RPIQ = 2.49) were obtained for clay and OM, indicating that these attributes can be successfully mapped on tropical soils using mobile vis–NIR spectroscopy and local calibrations using ANN. This study highlights the need to implement an independent test to assess reliability and extrapolability of previously calibrated models, even when extrapolating the models to neighboring areas.

For most of the arable land in Russia (132–137 million ha), the dominant and accurate soil information is stored in the form of map archives on paper without coordinate reference. The last traditional soil map(s) (TSM, TSMs) were created over 30 years ago. Traditional and/or archival soil map(s) (ASM, ASMs) are outdated in terms of storage formats, dates, and methods of production. The technology of constructing a multitemporal soil line (MSL) makes it possible to update ASMs and TSMs based on the processing of big remote-sensing data (RSD). To construct an MSL, the spectral characteristics of the bare soil surface (BSS) are used. The BSS on RSD is distinguished within the framework of the conceptual apparatus of the spectral neighborhood of the soil line. The filtering of big RSD is based on deep machine learning. In the course of the work, a vector georeferenced version of the ASM and an updated soil map were created based on the coefficient “C” of the MSL. The maps were verified based on field surveys (76 soil pits). The updated map is called the map of soil interpretation of the coefficient “C” (SIC “C”). The SIC “C” map has a more detailed legend compared to the ASM (7 sections/chapters instead of 5), greater accuracy (smaller errors of the first and second kind), and potential suitability for calculating soil organic matter/carbon (SOM/SOC) reserves (soil types/areals in the SIC “C” map are statistically significant are divided according to the thickness of the organomineral horizon and the content of SOM in the plowed layer). When updating, a systematic underestimation of the numbers of contours and areas of soils with manifestations of negative/degradation soil processes (slitization and erosion) on the TSM was established. In the process of updating, all three shortcomings of the ASMs/TSMs (archaic storage, dates, and methods of creation) were eliminated. The SIC “C” map is digital (thematic raster), modern, and created based on big data processing methods. For the first time, the actualization of the soil map was carried out based on the MSL characteristics (coefficient “C”).

In this paper, different machine learning methodologies have been evaluated for the estimation of the multiple soil characteristics of a continental-wide area corresponding to the European region, using multispectral Sentinel-3 satellite imagery and digital elevation model (DEM) derivatives. The results confirm the importance of multispectral imagery in the estimation of soil properties and specifically show that the use of DEM derivatives improves the quality of the estimates, in terms of R2, by about 19% on average. In particular, the estimation of soil texture increases by about 43%, and that of cation exchange capacity (CEC) by about 65%. The importance of each input source (multispectral and DEM) in predicting the soil properties using machine learning has been traced back. It has been found that, overall, the use of multispectral features is more important than the use of DEM derivatives with a ration, on average, of 60% versus 40%.

A comprehensive understanding of soil salinity distribution in arid regions is essential for making informed decisions regarding agricultural suitability, water resource management, and land use planning. A methodology was developed to identify soil salinity in Sudan by utilizing optical and radar-based satellite data as well as variables obtained from digital elevation models that are known to indicate variations in soil salinity. The methodology includes the transfer of models to areas where similar conditions prevail. A geographically coordinated database was established, incorporating a variety of environmental variables based on Google Earth Engine (GEE) and Electrical Conductivity (EC) measurements from the saturation extract of soil samples collected at three different depths (0–30, 30–60, and 60–90 cm). Thereafter, Multinomial Logistic Regression (MNLR) and Gradient Boosting Algorithm (GBM), were utilized to spatially classify the salinity levels in the region. To determine the applicability of the model trained at the reference site to the target area, a Multivariate Environmental Similarity Surface (MESS) analysis was conducted. The producer’s accuracy, user’s accuracy, and Tau index parameters were used to evaluate the model’s accuracy, and spatial confusion indices were computed to assess uncertainty. At different soil depths, Tau index values for the reference area ranged from 0.38 to 0.77, whereas values for target area samples ranged from 0.66 to 0.88, decreasing as the depth increased. Clay normalized ratio (CLNR), Salinity Index 1, and SAR data were important variables in the modeling. It was found that the subsoils in the middle and northwest regions of both the reference and target areas had a higher salinity level compared to the topsoil. This study highlighted the effectiveness of model transfer as a means of identifying and evaluating the management of regions facing significant salinity-related challenges. This approach can be instrumental in identifying alternative areas suitable for agricultural activities at a regional level.

The North China agro–pastoral zone is a large, ecologically fragile zone in the arid and semi-arid regions. Quantitative remote sensing inversion of soil organic carbon (SOC) in this region can facilitate understanding of the current status of degraded land restoration and provide data support for carbon cycling research in the region. Deep learning (DNN) for SOC inversion has been W.a hot topic over the past decade, but there have been few studies at the regional scale in the arid and semi-arid zones. In this study, a DNN model with five hidden layers and five skip connections was established using 644 spatially distributed SOC samples and Landsat 8 OLI imagery. The model was compared with the random forest algorithm in terms of generalization ability. The main conclusions were as follows: 1. The DNN algorithm can establish a high-precision SOC inversion model (R2 = 0.52, RMSE = 0.7), with 90% of errors concentrated in the range of −2.5 to 2.5 kg·C/m2; 2. the Boruta variable-screening algorithm can effectively improve the model accuracy of the random forest algorithm, but due to the DNN’s better ability to mine hidden information in the data, the improvement effect on the DNN model accuracy is limited; 3. the SOC samples in arid and semi-arid areas are highly positively skewed, with a significant impact on the modeling accuracy of DNN, and conversion is required to obtain a model with better generalization ability; and 4. in arid and semi-arid regions, SOC has a weak correlation with vegetation indices but a stronger correlation with temperature, elevation, and aridity. This study established a reliable deep learning model for SOC density in a large arid and semi-arid region, providing a reference and framework for the establishment of SOC inversion models in other regions.

Airborne geophysical data (AGD) have great potential to represent soil-forming factors. Because of that, the objective of this study was to evaluate the importance of AGD in predicting soil attributes such as aluminum saturation (ASat), base saturation (BS), cation exchange capacity (CEC), clay, and organic carbon (OC). The AGD predictor variables include total count (μR/h), K (potassium), eU (uranium equivalent), and eTh (thorium equivalent), ratios between these elements (eTh/K, eU/K, and eU/eTh), factor F or F-parameter, anomalous potassium (Kd), anomalous uranium (Ud), anomalous magnetic field (AMF), vertical derivative (GZ), horizontal derivatives (GX and GY), and mafic index (MI). The approach was based on applying predictive modeling techniques using (1) digital elevation model (DEM) covariates and Sentinel-2 images with AGD; and (2) DEM covariates and Sentinel-2 images without the AGD. The study was conducted in Bom Jardim, a county in Rio de Janeiro-Brazil with an area of 382,430 km², with a database of 208 soil samples to a predefined depth (0–30 cm). Non-explanatory covariates for the selected soil attributes were excluded. Through the selected covariables, the random forest (RF) and support vector machine (SVM) models were applied with separate samples for training (75%) and validation (25%). The model’s performance was evaluated through the R-squared (R2), root mean square error (RMSE), and mean absolute error (MAE), as well as null model values and coefficient of variation (CV%). The RF algorithm showed better performance with AGD (R2 values ranging from 0.15 to 0.23), as well as the SVM model (R2 values ranging from 0.08 to 0.23) when compared to RF (R2 values ranging from 0.10 to 0.20) and SVM (R2 values ranging from 0.04 to 0.10) models without AGD. Overall, the results suggest that AGD can be helpful for soil mapping. Nevertheless, it is crucial to acknowledge that the accuracy of AGD in predicting soil properties could vary depending on various common factors in DSM, such as the quality and resolution of the covariates and available soil data. Further research is needed to determine the optimal approach for using AGD in soil mapping.

Accurate digital mapping of farmland soil organic carbon (SOC) contributes to sustainable agricultural development and climate change mitigation. Farmland landscape pattern has changed greatly under anthropogenic influence, which should be considered an environmental variable to characterize the impact of human activities on SOC. In this study, we verified the feasibility of integrating landscape patterns in SOC prediction on Lower Liaohe Plain. Specifically, ten variables (climate, topographic, and landscape pattern variables) were selected for prediction with Random Forest (RF) and Support Vector Machines (SVMs). The effectiveness of landscape metrics was verified by establishing different variable combinations: (1) natural variables, and (2) natural and landscape pattern variables. The results confirmed that landscape variables improved mapping accuracy compared with natural variables. R2 of RF and SVM increased by 20.63% and 20.75%, respectively. RF performed better than SVM with smaller prediction error. Ranking of importance of variables showed that temperature and precipitation were the most important variables. The Aggregation Index (AI) contributed more than elevation, becoming the most important landscape variable. The Mean Contiguity Index (CONTIG-MN) and Landscape Contagion Index (CONTAG) also contributed more than other topographic variables. We conclude that landscape patterns can improve mapping accuracy and support SOC sequestration by optimizing farmland landscape management policies.

Numerous applications in agriculture, climate, ecology, hydrology, and the environment are severely constrained by the lack of detailed information on soil texture. The purpose of this study was to predict soil particle-size fractions (PSF) in the Ri-Bhoi district of Meghalaya state, India, using a random forest model (RF). For the modeling of soil particle-size fractions, we employed 95 soil profiles (456 depth-wise layers) gathered from a recent national land resource inventory as well as currently accessible environmental variables. Sand, silt, and clay content were predicted using the Random Forest model at varied depths of 0–5, 5–15, 30–60, 60–100, and 100–200 cm. Our results showed the R2 for sand was found to be 0.30 (0–5 cm), 0.28 (5–15 cm), and 0.21 (15–30 cm). For the sand, silt, and clay fractions, respectively, the concordance correlation coefficient (CCC) was found to be greater in the 0–30 cm, 0–60 cm, and 0–15 cm depths. When there is a reasonably close monitoring of the coverage probability with a confidence level along the 1:1 line, prediction interval coverage probability (PICP) gives a decent indicator of what to anticipate. The most crucial variables for the prediction of sand and silt were channel network base level (CNBL) and LS-Factor, whereas Min Temperature of Coldest Month (°C) (BIO6) was discovered for clay prediction. For all three soil texture fractions, the range between the 5% lower and 95% higher prediction bounds was large, indicating that the existing spatial predictions may be improved. The maps of soil texture were significantly more precise, and they accurately depicted the spatial variations of particle-size fractions. Additionally, there is still a need to investigate novel methodologies for extensive digital soil mapping, which will be very advantageous for many international initiatives.

Agriculture is essential to a flourishing economy. Although soil is essential for sustainable food production, its quality can decline as cultivation becomes more intensive and demand increases. The importance of healthy soil cannot be overstated, as a lack of nutrients can significantly lower crop yield. Smart soil prediction and digital soil mapping offer accurate data on soil nutrient distribution needed for precision agriculture. Machine learning techniques are now driving intelligent soil prediction systems. This article provides a comprehensive analysis of the use of machine learning in predicting soil qualities. The components and qualities of soil, the prediction of soil parameters, the existing soil dataset, the soil map, the effect of soil nutrients on crop growth, as well as the soil information system, are the key subjects under inquiry. Smart agriculture, as exemplified by this study, can improve food quality and productivity.

Accurate soil organic carbon (SOC) maps are helpful for guiding forestry production and management. Different ecological landscape areas within a large region may have different soil–landscape relationships, so models specifically for these areas may capture these relationships more accurately than the global model for the entire study area. The aim of this study was to investigate the role of zonal modelling in predicting forest SOC and to produce highly accurate forest SOC distribution maps. The prediction objects were SOC at five soil depths (0–20, 20–40, 40–60, 60–80, and 80–100 cm). First, the forest type map and soil texture class map were used to divide the relative homogeneous regions in Shaoguan City, Guangdong Province, China. Second, seven terrain variables derived from a 12.5-m digital elevation model (DEM) and five vegetation variables generated from 10-m Sentinel-2 remote sensing images were used as predictors to develop regional artificial neural network (ANN) models for each homogeneous region, as well as a global ANN model for the entire study area (1000 sample points). Finally, 10-fold cross-validation was used to assess the ANN prediction model performance, and independent validation was used to evaluate the produced forest SOC prediction maps (194 additional samples). The cross-validation results showed that the accuracies of the regional models were better than that of the global model. Independent validation results also showed that the precision (R2) of 0- to 100-cm forest SOC maps generated by forest type modelling had an improvement of 0.05–0.15, and that by soil texture class modelling had an improvement of 0.07–0.13 compared to the map generated by the global model. In conclusion, delineating relatively homogeneous regions via simple methods can improve prediction accuracy when undertaking soil predictions over large areas, especially with complex forest landscapes. In addition, SOC in the study area is generally more abundant in broadleaf forest and clay areas, with overall levels decreasing with soil depth. Accurate SOC distribution information can provide references for fertilization and planting. Plants with particularly high soil fertility requirements may perhaps be planted in broadleaf forests or clay areas, and plants with particularly developed roots may require furrow application of a small amount of SOC.

This article aims to explore the use of machine learning (ML) methods for mapping the distribution of mercury (Hg) content in topsoil, using the city of Ufa (Russia) and adjacent areas as an example. For this purpose, a soil dataset of 250 points sampled from a 0–20 cm depth on different land uses, including residential, industrial and undisturbed (forests and parks), was used. Random Forest (RF), Extreme Gradient Boosting (XGboost), Cubist and k-Nearest Neighbor (kNN) ML techniques were employed to model and map the Hg concentrations. We used remote sensing data (RSD) and topographic attributes as explanatory variables. ML models were calibrated and validated using the leave-one-out cross-validation approach. The Hg content varied from 0.005 to 0.58 mg/kg and was characterized by very high variability. According to the MAE and RMSE metrics, the RF method resulted in the most accurate spatial prediction for the Hg content (0.029 and 0.065 mg/kg, respectively), while the XGBoost approach showed the lowest prediction efficiency (0.032 and 0.073 mg/kg, respectively). The results showed that the slope map, spectral index MSI and Sentinel-2A band B11 were the key variables in explaining the variability of Hg content. We found that higher uncertainty values of soil Hg were found in croplands, urban residential and industrial areas, which supports the view that spatial modelling of HM in urban landscapes is challenging. The present study provides insights into the potential of digital soil mapping techniques in combination with RSD and terrain variables for identifying areas at risk of Hg contamination in urban areas, which can inform land-use planning and management strategies to protect human health and the environment.

Soil total nitrogen (STN) is a crucial component of the ecosystem’s nitrogen pool, and accurate prediction of STN content is essential for understanding global nitrogen cycling processes. This study utilized the measured STN content of 126 sample points and 40 extracted remote sensing variables to predict the STN content and map its spatial distribution in the northeastern coastal region of Hebei Province, China, employing the random forest (RF), gradient boosting machine (GBM), and extreme gradient boosting (XGBoost) methods. The purpose was to compare the ability of remote sensing images (Landsat-8, Sentinel-1, and Sentinel-2) with different machine learning methods for predicting STN content. The research results show the following: (1) The three machine learning methods accurately predicted the STN content and the optimal model provided by the XGBoost method, with an R2 of 0.627, RMSE of 0.127 g·kg−1, and MAE of 0.092 g·kg−1. (2) The combination of optical and synthetic aperture radar (SAR) images improved prediction accuracy, with the R2 improving by 45.5%. (3) The importance of optical images is higher than that of SAR images in the RF, GBM, and XGBoost methods, with optical images accounting for 87%, 76%, and 77% importance, respectively. (4) The spatial distribution of STN content predicted by the three methods is similar. Higher STN contents are distributed in the northern part of the study area, while lower STN contents are distributed in coastal areas. The results of this study can be very useful for inventories of soil nitrogen and provide data support and method references for revealing nitrogen cycling.

Reliable estimation of the forest soil nitrogen spatial distribution is necessary for effective forest ecosystem management. This study aimed to develop high-resolution digital soil maps of forest soil nitrogen across South Korea using three powerful machine learning methods to better understand the spatial variations of forest soil nitrogen and its environmental drivers. To achieve this, the study used national-level forest soil nitrogen data and environmental data to construct various geographic and environmental variables including geological, topographic, and vegetation factors for digital soil mapping. The results show that of the machine learning methods, the random forest model had the best performance at predicting total soil nitrogen in the A and B horizons, closely followed by the extreme gradient-boosting model. The most critical predictors were found to be geographic variables, quantitatively confirming the significant role of spatial autocorrelation in predicting soil nitrogen. The digital soil maps revealed that areas with high elevation, concave slopes, and deciduous forests had high nitrogen contents. This finding highlights the potential usefulness of digital soil maps in supporting forest management decision-making and identifying the environmental drivers of forest soil nitrogen distribution.

Satellite-based soil organic carbon content (SOC) mapping over wide regions is generally hampered by the low soil sampling density and the diversity of soil sampling periods. Some unfavorable topsoil conditions, such as high moisture, rugosity, the presence of crop residues, the limited amplitude of SOC values and the limited area of bare soil when a single image is used, are also among the influencing factors. To generate a reliable SOC map, this study addresses the use of Sentinel-2 (S2) temporal mosaics of bare soil (S2Bsoil) over 6 years jointly with soil moisture products (SMPs) derived from Sentinel 1 and 2 images, SOC measurement data and other environmental covariates derived from digital elevation models, lithology maps and airborne gamma-ray data. In this study, we explore (i) the dates and periods that are preferable to construct temporal mosaics of bare soils while accounting for soil moisture and soil management; (ii) which set of covariates is more relevant to explain the SOC variability. From four sets of covariates, the best contributing set was selected, and the median SOC content along with uncertainty at 90% prediction intervals were mapped at a 25-m resolution from quantile regression forest models. The accuracy of predictions was assessed by 10-fold cross-validation, repeated five times. The models using all the covariates had the best model performance. Airborne gamma-ray thorium, slope and S2 bands (e.g., bands 6, 7, 8, 8a) and indices (e.g., calcareous sedimentary rocks, “calcl”) from the “late winter–spring” time series were the most important covariates in this model. Our results also indicated the important role of neighboring topographic distances and oblique geographic coordinates between remote sensing data and parent material. These data contributed not only to optimizing SOC mapping performance but also provided information related to long-range gradients of SOC spatial variability, which makes sense from a pedological point of view.

The problem of salinization/spreading of saline soils is becoming more urgent in many regions of the world, especially in context of climate change. The monitoring of salt-affected soils’ properties is a necessary procedure in land management and irrigation planning and is aimed to obtain high crop harvest and reduce degradation processes. In this work, a machine learning method was applied for modeling of the spatial distribution of topsoil (0–20 cm) properties—in particular: soil organic carbon (SOC), pH, and salt content (dry residue). A random forest (RF) machine learning approach was used in combination with environmental variables to predict soil properties in a semi-arid area (Trans-Ural steppe zone). Soil, salinity, and texture maps; topography attributes; and remote sensing data (RSD) were used as predictors. The coefficient of determination (R2) and the root mean square error (RMSE) were used to estimate the performance of the RF model. The cross-validation result showed that the RF model achieved an R2 of 0.59 and an RMSE of 0.68 for SOM; 0.36 and 0.65, respectively, for soil pH; and 0.78 and 1.21, respectively for dry residue prediction. The SOC content ranged from 0.8 to 2.8%, with an average value of 1.9%; soil pH ranged from 5.9 to 8.4, with an average of 7.2; dry residue varied greatly from 0.04 to 16.8%, with an average value of 1.3%. A variable importance analysis indicated that remote sensing variables (salinity indices and NDVI) were dominant in the spatial prediction of soil parameters. The importance of RSD for evaluating saline soils and their properties is explained by their absorption characteristics/reflectivity in the visible and near-infrared spectra. Solonchak soils are distinguished by a salt crust on the land surface and, as a result, reduced SOC contents and vegetation biomass. However, the change in saline and non-saline soils over a short distance with mosaic structure of soil cover requires high-resolution RSD or aerial images obtained from unmanned aerial vehicle/drones for successful digital mapping of soil parameters. The presented results provide an effective method to estimate soil properties in saline landscapes for further land management/reclamation planning of degraded soils in arid and semi-arid regions.

Cation exchange capacity (CEC) is a soil property that significantly determines nutrient availability and effectiveness of fertilizer applied in lands under different managements. CEC’s accurate and high-resolution spatial information is needed for the sustainability of agricultural management on farms in the Nagaland state (northeast India) which are fragmented and intertwined with the forest ecosystem. The current study applied the digital soil mapping (DSM) methodology, based on the CEC values determined in soil samples obtained from 305 points in the region, which is mountainous and difficult to access. Firstly, digital auxiliary data were obtained from three open-access sources, including indices generated from the time series Landsat 8 OLI satellite, topographic variables derived from a digital elevation model (DEM), and the WorldClim dataset. Furthermore, the CEC values and the auxiliary were used data to model Lasso regression (LR), stochastic gradient boosting (GBM), support vector regression (SVR), random forest (RF), and K-nearest neighbors (KNN) machine learning (ML) algorithms were systematically compared in the R-Core Environment Program. Model performance were evaluated with the square root mean error (RMSE), determination coefficient (R2), and mean absolute error (MAE) of 10-fold cross-validation (CV). The lowest RMSE was obtained by the RF algorithm with 4.12 cmolc kg−1, while the others were in the following order: SVR (4.27 cmolc kg−1) c kg−1) c kg−1) c kg−1). In particular, WorldClim-based climate covariates such as annual mean temperature (BIO-1), annual precipitation (BIO-12), elevation, and solar radiation were the most important variables in all algorithms. High uncertainty (SD) values have been found in areas with low soil sampling density and this finding is to be considered in future soil surveys.

To overcome spatial, spectral and temporal constraints of different remote sensing products, data fusion is a good technique to improve the prediction capability of soil prediction models. However, few studies have analyzed the effects of image fusion on digital soil mapping (DSM) models. This research fused multispectral (MS) and panchromatic Landsat 8 (L8) bands, and MS Sentinel 2 (S2) and panchromatic L8 bands using the Brovey, Intensity–Hue–Saturation and Gram–Schmidt methods in an agricultural area in Yellow River Basin, China. To analyze the effects of image fusion on DSM models, various SOC prediction models derived from remote sensing image datasets were established by the random forest method. Soil salinity indices and spectral reflectance from all the remote sensing data had relatively strong negative correlations with SOC, and vegetation indices and water indices from all the remote sensing data had relatively strong positive correlations with SOC. Soil moisture and vegetation were the main controlling factors of the SOC spatial pattern in the study area. More spectral indices derived from pansharpened L8 and fused S2–L8 images by all three image fusion methods had stronger relationships with SOC compared with those from MS L8 and MS S2, respectively. All the SOC models established by pansharpened L8 and fused S2–L8 images had higher prediction accuracy than those established by MS L8 and MS S2, respectively. The fusion between S2 and L8 bands had stronger effects on enhancing the prediction accuracy of SOC models compared with the fusion between panchromatic and MS L8 bands. It is concluded that digital soil mapping and image fusion can be utilized to increase the prediction performance of SOC spatial prediction models.

The rapid acquisition of high-resolution spatial distribution of soil organic matter (SOM) at the field scale is essential for precision agriculture. The UAV imaging hyperspectral technology, with its high spatial resolution and timeliness, can fill the research gap between ground-based monitoring and remote sensing. This study aimed to test the feasibility of using UAV hyperspectral data (400–1000 nm) with a small-sized calibration sample set for mapping SOM at a 1 m resolution in typical low-relief black soil areas of Northeast China. The experiment was conducted in an approximately 20 ha field. For calibration, 20 samples were collected using a 100 × 100 m grid sampling strategy, while 20 samples were randomly collected for independent validation. UAV captured hyperspectral images with a spatial resolution of 0.05 × 0.05 m. The extracted spectra within every 1 × 1 m were then averaged to represent the spectra of that grid; this procedure was also performed across the whole field. Upon applying various spectral pretreatments, including absorbance conversion, multiple scattering correction, Savitzky–Golay smoothing filtering, and first-order differentiation, the absolute maximum values of the correlation coefficients of the spectra for SOM increased from 0.41 to 0.58. Importance analysis from the optimal random forest (RF) model showed that the characterized bands of SOM were located in the 450–600 and 750–900 nm regions. When the RF model was used, the UAV hyperspectra data (UAV-RF) were able to successfully predict SOM, with an R2 of 0.53 and RMSE of 1.48 g kg−1. The prediction accuracy was then compared with that obtained using ordinary kriging (OK) and the RF model based on proximal sensing (PS-RF) with the same number of calibration samples. However, the OK method failed to predict the SOM accuracy (RMSE = 2.17 g kg−1; R2 = 0.02) due to a low sampling density. The semi-covariance function was unable to describe the spatial variability of SOM effectively. When the sampling density was increased to 50 × 50 m, OK successfully predicted SOM, with RMSE = 1.37 g kg−1 and R2 = 0.59, and its results were comparable to those of UAV-RF. The prediction accuracy of PS-RF was generally consistent with that of UAV-RF, with RMSE values of 1.41 g kg−1 and 1.48 g kg−1 and R2 values of 0.57 and 0.53, respectively, which indicated that SOM prediction based on UAV-RF is feasible. Additionally, compared with the PS platforms, the UAV hyperspectral technology could simultaneously provide spectral information of tens or even hundreds of continuous bands and spatial information at the same time. This study provides a reference for further research and development of UAV hyperspectral techniques for fine-scale SOM mapping using a small number of samples.

Accurate understanding of spatial distribution and variability of soil total nitrogen (TN) is critical for the site-specific nitrogen management. Based on 4337 newly obtained soil observations and 33 covariates, this study applied the random forest (RF) algorithm and modified regression kriging (RF combined with residual kriging: RFK, hereafter) model to spatially predict and map topsoil TN content in agricultural areas of Henan Province, central China. According to the RFK prediction, topsoil TN content ranged from 0.52 to 1.81 g kg−1, and the farmland with the topsoil TN contents of 1.00–1.23 g kg−1 and 0.80–1.23 g kg−1 accounted for 48.2% and 81.2% of the total farmland area, respectively. Spatially, the topsoil TN in the study area was generally higher in the west and lower in the east. By using the Boruta variable selection algorithm, soil organic matter (SOM) and available potassium contents in topsoil, nitrogen deposition, average annual precipitation, livestock discharges, and topsoil pH were identified as the main factors driving the spatial distribution and variation of soil TN in the study area. The RF and RFK models used showed the expected performance and achieved acceptable TN prediction accuracy. In comparison, RFK performed slightly better than the RF model. The R2 and RMSE achieved by the RFK model were improved by 4.5% and 4.5%, respectively, compared with that by the RF model. However, the results suggest that RFK was inferior to the RF model in quantifying prediction uncertainty and thus may have a slight disadvantage in model reliability.

Thermo-erosion gullies (TGs) are typical thermokarst features in upland permafrost; the soil organic carbon (SOC) of TGs has an important influence on soil quality in cold regions. The objectives of this study were to estimate the spatial distribution of SOC content in a typical TG on the northeastern Tibetan Plateau in China by using soil properties from seven different TGs and covariates from unmanned aerial vehicle (UAV) images, and to characterize the SOC content changes in four representative landscape regions (NO-Slumping, Slumping1, Slumping2, and Slumped) within this typical TG. The support vector machine (SVM) was the optimal machine learning algorithm for SOC content prediction, which explained 53.06% (R2) of the SOC content variation. Silt content was the most influential factor which demonstrated a positive relationship with SOC content in different TGs. In addition, the SOC content in the TGs was related to the landscapes. Severe Slumping (Slumping2: 150.79 g·kg−1) had a lower SOC content than NO-Slumped (163.29 g·kg−1) and the initial slumping stage (Slumping1: 169.08 g·kg−1). The results suggested that SVM was an effective algorithm to obtain a profound understanding of the SOC content over space, while future research needs to pay more attention to the SOC content distribution in the different TGs.

In the last 30 years, severe soil acidification has been found in China due to acid deposition and nitrogen fertilizer overuse. Understanding the spatial pattern and vertical variations in base saturation percentage (BSP) and exchangeable cations (Ca2+, Mg2+, K+, Na+, H+ and Al3+) can directly benefit fertilization management and ecological protection. Here, 1253 soil profiles were surveyed in tropical and subtropical regions in China to investigate the spatial variations in BSP and exchangeable cations at three soil depths of 0–20 cm, 20–50 cm and 50–100 cm. The spatial distributions were interpolated by using advanced machine learning techniques. We found that the exchangeable Ca2+ (Exch. Ca), Mg2+ (Exch. Mg) and BSP were significantly higher in paddy fields and uplands than in forests and gardens, regardless of soil depth, while the exchangeable K (Exch. K) did not significantly differ between various land-use types. The Exch. Ca and BSP in Anthrosols were significantly higher than those in Ferrosols, Argosols and Cambosols in the three soil layers. The spatial prediction results indicated that exchangeable cations and BSP were generally characterized by strong heterogeneity, and the Exch. Ca, Exch. K and exchangeable H+ (Exch. H) contents and BSP declined with increasing soil depth. This study helps us understand the spatial variation in BSP and exchangeable cations in the study area and benefits fertilization management and environmental protection.

Soil scientists can aid in an essential part of ecological conservation and rehabilitation by quantifying soil properties, such as soil organic carbon (SOC), and is stock (SOCs) SOC is crucial for providing ecosystem services, and, through effective C-sequestration, the effects of climate change can be mitigated. In remote mountainous areas with complex terrain, such as the northern Maloti-Drakensberg in South Africa and Lesotho, direct quantification of stocks or even obtaining sufficient data to construct predictive Digital Soil Mapping (DSM) models is a tedious and expensive task. Extrapolation of DSM model and algorithms from a relatively accessible area to remote areas could overcome these challenges. The aim of this study was to determine if calibrated DSM models for one headwater catchment (Tugela) can be extrapolated without re-training to other catchments in the Maloti-Drakensberg region with acceptable accuracy. The selected models were extrapolated to four different headwater catchments, which included three near the Motete River (M1, M2, and M3) in Lesotho and one in the Vemvane catchment adjacent to the Tugela. Predictions were compared to measured stocks from the soil sampling sites (n = 98) in the various catchments. Results showed that based on the mean results from Universal Kriging (R2 = 0.66, NRMSE = 0.200, and ρc = 0.72), least absolute shrinkage and selection operator or LASSO (R2 = 0.67, NRMSE = 0.191, and ρc = 0.73) and Regression Kriging with cubist models (R2 = 0.61, NRMSE = 0.184, and ρc = 0.65) had the most satisfactory outcome, whereas the soil-land inference models (SoLIM) struggled to predict stocks accurately. Models in the Vemvane performed the worst of all, showing that that close proximity does not necessarily equal good similarity. The study concluded that a model calibrated in one catchment can be extrapolated. However, the catchment selected for calibration should be a good representation of the greater area, otherwise a model might over- or under-predict SOCs. Successfully extrapolating models to remote areas will allow scientists to make predictions to aid in rehabilitation and conservation efforts of vulnerable areas.

Acidic soils (pH < 5.5) cover roughly 30% of Sub-Saharan Africa. Low nitrogen fertilizer application (15 kg N ha−1 yr−1) has no effect on soil acidification in Sub-Saharan Africa (SSA). However, the effect of optimized fertilizer use on soil acidification (H+) in SSA crops remains unknown. This study intended to predict the spatial variation of H+ caused by optimized fertilizer use using data from 5782 field trials in SSA cropland. We used ensemble machine learning to predict spatial variation (H+) after measuring the inputs and outputs of major elements and their effect on H+ production. The results revealed that H+ ranged spatially from 0 to 16 keq H+ ha−1 yr−1. The most protons (H+) were produced by cassava, banana, and Irish potatoes systems with 12.0, 9.8, and 8.9 keq H+ ha−1 yr−1, respectively. The results of the 10-fold cross validation for the soil acidification model were a coefficient of determination (R2) of 0.6, a root mean square error (RMSE) of 2.1, and a mean absolute error (MAE) of 1.4. Net basic cation loss drives soil acidification under optimized fertilizer application and climate covariates had a higher relative importance than other covariates. Digital soil mapping can produce soil acidification maps for sustainable land use and management plans.

Sustainable agricultural landscape management needs reliable and accurate soil maps and updated geospatial soil information. Recently, machine learning (ML) models have commonly been used in digital soil mapping, together with limited data, for various types of landscapes. In this study, we tested linear and nonlinear ML models in predicting and mapping soil properties in an agricultural lowland landscape of Lombardy region, Italy. We further evaluated the ability of an ensemble learning model, based on a stacking approach, to predict the spatial variation of soil properties, such as sand, silt, and clay contents, soil organic carbon content, pH, and topsoil depth. Therefore, we combined the predictions of the base learners (ML models) with two meta-learners. Prediction accuracies were assessed using a nested cross-validation procedure. Nonetheless, the nonlinear single models generally performed well, with RF having the best results; the stacking models did not outperform all the individual base learners. The most important topographic predictors of the soil properties were vertical distance to channel network and channel network base level. The results yield valuable information for sustainable land use in an area with a particular soil water cycle, as well as for future climate and socioeconomic changes influencing water content, soil pollution dynamics, and food security.

Precise knowledge about the soil organic carbon (SOC) content in cropland soils is one requirement to design and execute effective climate and food policies. In digital soil mapping (DSM), machine learning algorithms are used to predict soil properties from covariates derived from traditional soil mapping, digital elevation models, land use, and Earth observation (EO). However, such DSM models are trained for a specific dataset and region and have so far only allowed limited general statements to be made that would enable the models to be transferred to different regions. In this study, we test the transferability of SOC models for cropland soils using five different covariate groups: multispectral soil reflectance composites (satellite), soil legacy data (soil), digital elevation model derivatives (terrain), climate parameters (climate), and combined models (combined). The transferability was analyzed using data from two federal states in southern Germany: Bavaria and Baden-Wuerttemberg. First, baseline models were trained for each state with combined models performing best in both cases (R2 = 0.68/0.48). Next, the models were transferred and tested with soil samples from the other state whose data were not used during model calibration. Only satellite and combined models were transferable, but accuracy declined in both cases. In the final step, models were trained with samples from both states (mixed-data models) and applied to each state separately. This process significantly improved the accuracies of satellite, terrain, and combined models, while it showed no effect on climate models and decreased the models based on soil covariates. The experiment underlines the importance of EO for the transfer and extrapolation of DSM models.

Soil organic matter (SOM), as the greatest carbon storage in the terrestrial environment, is inextricably related to the global carbon cycle and global climate change. Accurate estimation and mapping of SOM content are crucial for guiding agricultural output and management, as well as controlling the climate issue. Traditional chemical analysis is unable to satisfy the dynamic estimation of SOM due to its low timeliness. Remote and proximal sensing have significant advantages in terms of ease of use, estimation accuracy, and geographical resolution. In this study, we developed a framework based on machine learning to estimate SOM with high accuracy and resolution using Fourier mid-infrared attenuation total reflectance spectroscopy (FTIR-ATR), Sentinel-2 images, and DEM derivatives. This framework’s performance was evaluated on a regional scale using 245 soil samples from northeast China. Results indicated that the calibration size could be shrunk to 50% while achieving a fair prediction performance for SOM content. The Lasso, partial least squares (PLS), support vector regression (SVR), and convolutional neural networks (CNN) performed well in predicting SOM from FTIR-ATR spectra, and the performance was enhanced further by using Sentinel-2 images and DEM derivates. The PLS, SVR, and CNN models created SOM maps with higher spatial resolution and variation than the Kriging approach. The PLS and SVR models provided enough variety and were more realistic in the local SOM map, making them usable at the field scale, and the suggested framework took a fresh look at high-resolution SOM mapping.

Applying fertilizers to soil in a site-specific way that maximizes yields and minimizes environmental damage is an important goal. Developing soil management zones (MZs) is a suitable method for achieving sustainable agricultural production. Thus, this work aims to investigate MZs delineated based on the different soil properties using machine learning methods. To achieve these, 202 soil samples were collected at the agricultural land of pomegranate, pistachio, and saffron. A “random forest” model was applied to map soil properties based on environmental covariates. The predicted “Lin’s concordance correlation coefficient” values in validation soil properties varied from 0.65 to 0.79. The maps indicated low amounts of soil organic carbon, available potassium, available phosphate, and total nitrogen in most of the region. Furthermore, the study identified four different MZs according to relationships between soil properties and environmental covariates. Generally, the ranking of zones in terms of soil fertility was MZ4 > MZ1 > MZ3 > MZ2 based on the investigated soil properties and the soil quality (SQ) map. The five grades of SQ (i.e., very high, high, moderate, low, and very low) indicated that there was heterogeneous SQ in each MZ in the study area. There were 1.65 ha identified in MZ4 with very low SQ. This result is important in determining the amount of fertilizer to add to the soil in the different areas. It confirms the need for more specific regional management of agriculture lands in this region.

For better soil management in terms of salinization to ensure sustainable agriculture, a soil salinity mapping and prediction study based on the measurement of apparent electrical conductivity using an electromagnetic instrument (EM38) combined with geostatistical interpolation (kriging) is proposed herein for the soil of the semi-arid region of Beni Amir (2060 ha), Tadla, Morocco. This solution is efficient and quick to use, with the ability to provide reliable information for assessing the spatial distribution of soil salinity. The results of measurements through a spatial analysis offered us the possibility of identifying several classes of salinity that can be used for the sustainable management of land and water.