Predicting Soil Depth Research Articles

Estimating Soil Depth in Data-Sparse Regions: A Machine Learning Approach for Western India

ABSTRACT Soil depth is essential for eco-hydrological modeling, carbon storage estimation, and land evaluation, yet its spatial variation is often poorly understood and rarely mapped, particularly in complex landscapes with limited sample sizes. Digital soil mapping, employing various machine learning methods, has become crucial in predicting and mapping soil attributes. This study investigates soil depth distribution in Rajasthan and Gujarat, India, using machine learning techniques. A total of 37 environmental variables were examined to identify factors influencing soil depth, utilizing data from 3206 soil profiles. Five machine learning algorithms – Random Forest (RF), Cubist, Support Vector Machines (SVM), extreme gradient boosting (XGBoost), and Partial Least Squares Regression (PLSR) – were evaluated. MODIS, WorldClim, and Digital Elevation Model were used as environmental covariates. Among these, channel network base level, and valley depth were found to be the most significant factors in soil depth modeling. The RF model produced the best results, with an R2 of 0.53, RMSE of 25.19 cm, and MAE of 16.04 cm, outperforming Cubist and other models. Predicted soil depths ranged from 23 to 197 cm in Rajasthan and from 16 to 182 cm in Gujarat. The spatial pattern of soil depth closely matched expectations for the studied regions, demonstrating effective model and variable selection. However, uncertainty assessment revealed significant uncertainty in 60% of the study area due to low soil profile points. This study presents a promising approach to predict soil depth via digital mapping, aiding regional land use planning and potentially informing national and international land resource management strategies.

Utilizing artificial intelligence techniques for soil depth prediction and its influences in landslide hazard modeling

Utilizing artificial intelligence techniques for soil depth prediction and its influences in landslide hazard modeling

Soil Depth Prediction Model Using Terrain Attributes in Gangwon-do, South Korea

Soil depth is a crucial parameter in slope stability analysis in mountainous areas. The drilling survey is the most reliable method for determining soil depth, but it requires a high cost for the vast geographical area. Therefore, this study proposes a soil depth prediction model for mountainous areas that uses Terrain Attributes (TAs) from digital maps. Gangwon-Do, a predominantly mountainous region in South Korea, is selected as the study target area. The study area is classified by parent rock type into igneous rocks, metamorphic rocks, and sedimentary rocks. The correlation with TAs is analyzed through multi-collinearity using drilling data published in the Korea drilling information database. In addition, the most suitable combination of variables is selected through multi-collinearity analysis, and the regression model using STI, TWI, and SLOPE is found to be the most appropriate model (VIF < 10). The proposed model for soil depth shows significance at p < 0.001, and the correlation coefficient (R2) is figured out for igneous rock (0.702), metamorphic rock (0.686), and sedimentary rock (0.693). In addition, the reliability of the proposed model was verified by using data from regions not included in the model development, and the correlation coefficients were igneous rock (0.867), metamorphic rock (0.801), and sedimentary rock (0.814). The model proposed is more suitable for Korean topography than the existing statistical models; it can help to increase the accuracy of slope stability analysis.

Improvement of spatial prediction of soil depth via earth observation

Improvement of spatial prediction of soil depth via earth observation

Predicting soil depth in a humid tropical watershed: A comparative analysis of best-fit regression and geospatial models

Predicting soil depth in a humid tropical watershed: A comparative analysis of best-fit regression and geospatial models

Predicting soil depth in a large and complex area using machine learning and environmental correlations

Soil depth is critical for eco-hydrological modeling, carbon storage calculation and land evaluation. However, its spatial variation is poorly understood and rarely mapped. With a limited number of sparse samples, how to predict soil depth in a large area of complex landscapes is still an issue. This study constructed an ensemble machine learning model, i.e., quantile regression forest, to quantify the relationship between soil depth and environmental conditions. The model was then combined with a rich set of environmental covariates to predict spatial variation of soil depth and straightforwardly estimate the associated predictive uncertainty in the 140 000 km 2 Heihe River basin of northwestern China. A total of 275 soil depth observation points and 26 covariates were used. The results showed a model predictive accuracy with coefficient of determination ( R 2 ) of 0.587 and root mean square error (RMSE) of 2.98 cm (square root scale), i.e., almost 60% of soil depth variation explained. The resulting soil depth map clearly exhibited regional patterns as well as local details. Relatively deep soils occurred in low lying landscape positions such as valley bottoms and plains while shallow soils occurred in high and steep landscape positions such as hillslopes, ridges and terraces. The oases had much deeper soils than outside semi-desert areas, the middle of an alluvial plain had deeper soils than its margins, and the middle of a lacustrine plain had shallower soils than its margins. Large predictive uncertainty mainly occurred in areas with a lack of soil survey points. Both pedogenic and geomorphic processes contributed to the shaping of soil depth pattern of this basin but the latter was dominant. This findings may be applicable to other similar basins in cold and arid regions around the world.

Predicting Soil Depth in a Humid Tropical Watershed: A Comparative Analysis of Best-Fit Regression and Cokriging Models

Predicting Soil Depth in a Humid Tropical Watershed: A Comparative Analysis of Best-Fit Regression and Cokriging Models

Mapping soil depth in southern pampas Argentina using ancillary data and statistical learning

AbstractRestrictive layers such as hardpans limit the soil water and nutrients available for crops. In the southern Argentinean pampas, petrocalcic hardpans are found at variable depth within the field. Mapping the spatial distribution of depth to the petrocalcic hardpan is important for proper land evaluation, use, and management. Intensive grid sampling and spatial interpolation are labor‐intensive and time‐consuming mapping approaches for this soil property. In addition, the spatial distribution of this property is often difficult for interpolation techniques such as kriging. This study's objective was to evaluate the potential of soil electrical conductivity (ECa) and terrain attributes to map within‐field spatial variation of soil depth using statistical learning techniques. Soil depth measurements up to 1‐m depth were taken in eight fields at spatial sampling density ranging from 2 to 12 points ha–1. Spatially dense data of elevation, terrain attributes, and ECa were migrated to soil depth sampling points and also spatially aggregated to include spatial information into the featured space. Then, random forest regression models were used to predict soil depth from colocated ECa and terrain data. Models were cross‐validated using a k‐fold approach using entire fields as folds. The overall model (using all data) resulted in out‐of‐the bag R2 and RMSE of .66 and 22.8 cm respectively. Shallow (0–30 cm) and deep (0–90 cm) ECa values were the most important variables, accounting for variability at different ranges, but the importance varied between the soil types. These results suggested that field‐scale ECa data and terrain attributes have potential to predict soil depth to hardpan. Further research is needed to improve the generalization of these models and improve the representation of spatial effects in order to implement site‐specific management based on soil depth maps.

Digital Terrain Analysis Approach to Improve Soil Depth Prediction with Parent Material Dataset

Digital Terrain Analysis Approach to Improve Soil Depth Prediction with Parent Material Dataset

Spatial prediction of soil depth using environmental covariates by quantile regression forest model.

Prediction of soil depth for larger areas provides primary information on soil depth and its spatial distribution that becomes vital for land resource management, crop, nutrient, and ecosystem modeling. The present study assessed the spatial distribution of soil depth over 160,205 km2 of Andhra Pradesh, India, using 20 covariables by quantile regression forest (QRF). An aggregate of 2854 soil datasets compiled from various physiographic units were randomly partitioned into 80:20 ratio for calibration (2283 samples) and validation (571 samples). Landsat imagery, terrain datasets (8), and bioclimatic factors (11) were utilized as covariates. The QRF model outputs signified that precipitation, multi-resolution index of valley bottom flatness (MrVBF), mean diurnal range, isothermality, and elevation were the most important variables influencing soil depth variability across the landscape. Spatial prediction of soil depth by QRF model yielded a ME of - 1.81cm, RMSE of 34cm, PICP of 90.2, and a R2 value of 42% as compared to ordinary kriging which results in a ME of - 0.14cm, a RMSE of 37cm, and a R2 value of 32%. As soil depth is spatially dynamic and has significant correlation with terrain and environmental covariates, better prediction was possible by the QRF model. However, high-density bioclimatic variables could be utilized along with high-resolution terrain variables to improve the predictive accuracy.

Prediction of Soil Depth in Karnataka Using Digital Soil Mapping Approach

Spatial information of soil depth in regional and national level is essential for arriving crop suitability decisions. In the present study, high-resolution (250 m) soil depth map of Karnataka is prepared using digital soil mapping approach. A total of 5174 Soil legacy datasets studied by NBSS&LUP over a period of 30 years is collected and organized for mapping. Quantile regression forest (QRF) and regression kriging (RK) algorithm is tested to predict the soil depth in Karnataka. Topographic attributes derived from digital elevation model, normalized difference vegetation index, landsat-8 data and climatic variables are used as covariates. For model calibration, 80% of soil depth data is used and 20% of data is used for validation. The classical uncertainty estimates such as coefficient of determination (R2) and root mean square error (RMSE) and bias were calculated for the validation datasets in order to assess the model performance. RK model explained maximum variability for prediction of soil depth (R2 = 30%, RMSE = 34 cm) compared to QRF (R2 = 17%, RMSE = 37 cm). Lithology and elevation are found to be most important variables for prediction of soil depth in Karnataka. The predicted soil depth in Karnataka is ranged from 22 to 173 cm, and the present high-resolution (250 m) soil depth maps are useful in different hydrological, crop modelling and climate change studies.

Comparison and Contrast in Soil Depth Evolution for Steady State and Stochastic Erosion Processes: Possible Implications for Landslide Prediction

AbstractThe importance of gradual erosion relative to landsliding depends predominantly on the slope angle. One factor of critical influence in landsliding along with slope angle and slope shape is the soil depth. Understanding soil depth development on steep topography is fundamental for understanding and predicting the occurrence of landsliding at threshold landscapes. We develop a model to predict soil depth that addresses both threshold and gradual processes. If erosion is a gradual process, soil depth increases until the soil production rate no longer exceeds the erosion rate, and steady state is reached. The predicted soil depth (x) is proportional to the ratio of the infiltration to the erosion rate. Identifying a predictive result for erosion as a function of slope angle (S) allows a test of both the erosion and soil production models with field observations. The same theoretical approach to soil production should be applicable when the principal erosion process is shallow landsliding. After landslides, soil recovery initially follows our predicted power law increase in time, though with increasing time background erosion processes become important. At a time equal to a landslide recurrence interval, the soil depth can exceed the steady state depth by as much as a factor 2. By comparing predicted and observed x(S) results, we show that the accessed result for erosion as a function of slope angle is accurate. Soils deeper than the depth predicted at the landslide recurrence interval are beyond the stability limit. This result suggests an important practical relevance of the new soil production function.

Using multinomial logistic regression for prediction of soil depth in an area of complex topography in Taiwan

Abstract Increasing land developments, unreasonable utilization of land, earthquakes, typhoons, and torrential rain often cause hillside disasters. Soil depth is a crucial parameter influencing the scale of shallow landslides and sustainable land use in hillside areas. This paper presents a statistical model, integrated with environmental factors, for estimating soil depth in a catchment area with complex topography. The study area selected was upstream of the Houlong River in Taiwan. The model was developed using multinomial logistic regression and environmental factors such as hill slope, hill aspect, elevation, topographical curvature, and the normalized difference vegetation index. The results were then compared with those obtained from previous models applying Ordinary Kriging, Regression Kriging, and topographical wetness index methods. A classification error matrix and the Kappa index were then employed to assess the various models. The results showed that, for the data set used for model establishment, the overall accuracy and Kappa index were 76.6% and 0.65, respectively, whereas for the data set used for verification, they were 70.5% and 0.57, respectively. By contrast, the Ordinary Kriging method yielded an overall accuracy and a Kappa index of 45.7% and 0.15, respectively; the Regression Kriging method yielded results of 46.7% and 0.16, respectively; and the topographical wetness index method yielded results of 30.5% and −0.05, respectively. The proposed model was therefore determined to be superior to the others in terms of soil depth estimation accuracy. The proposed model can predict soil depth on a regional scale and serve as a reliable tool that provides reference data for future research on land use and shallow landslides.

Predicting soil depth to bedrock in an anthropogenic landscape: a case study of Phewa Watershed in Panchase region of Central-Western Hills, Nepal

The Soil Depth to Bedrock (SDtB) parameter is highly variable over the landscape and is an important input for soil surface modeling including various types of mass movement that most often ignores the variability of soil depth. In landscapes that have been heavily modified by humans, SDtB parameters do not necessarily depend on natural processes, making it difficult to apply physically-based approaches. This study explored the possibility of using topographic attributes to model the SDtB in the complex topography of Phewa watershed in the Panchase region of Nepal. In June 2017, 865 SDtB points were surveyed along the excavated rural roads (approximately 300 km) within the watershed (111 km2). Topographic attributes such as slope, curvatures, altitude and compound terrain index were derived from a Digital Terrain Model along with Land use land cover attributes derived from recent Landsat remote sensing images. Utilizing these attributes as explanatory variables, we implemented simple kriging (SK) and multiple linear regressions (MLR) to predict SDtB for the watershed. The results showed that the MLR predicted SDtB map was statistically significant (R2 = 68%, EC = 0.93) over the SK (R2 = 12%, EC = -0.46). We concluded that the MLR approach in predicting SDtB for the complex geo-morphologic landscape such as the Phewa watershed in the Panchase region of Nepal can effectively be used, helping to inform the evolution of land-use as the region continues to develop.

Application of Elastic Wave Velocity for Estimation of Soil Depth

Because soil depth is a crucial factor for predicting the stability at landslide and debris flow sites, various techniques have been developed to determine soil depth. The objective of this study is to suggest the graphical bilinear method to estimate soil depth through seismic wave velocity. Seismic wave velocity rapidly changes at the interface of two different layers due to the change in material type, packing type, and contact force of particles and thus, it is possible to pick the soil depth based on seismic wave velocity. An area, which is susceptible to debris flow, was selected, and an aerial survey was performed to obtain a topographic map and digital elevation model. In addition, a seismic survey and a dynamic cone penetration test were performed in this study. The comparison between the soil depth based on dynamic cone tests and the graphical bilinear method shows good agreement, indicating that the newly suggested soil depth estimating method may be usefully applied to predict soil depth.

Selection of optimal scales for soil depth prediction on headwater hillslopes: A modeling approach

Abstract Landform attributes derived from digital elevation models (DEMs) are the most commonly used factors to predict soil depths on hillslopes. However, the selection of an appropriate algorithm to calculate terrain attributes and identify an optimal DEM resolution remains ambiguous. In this study, we propose a method to use high-resolution DEM and spatial soil depth data to obtain terrain attributes and identify the optimal DEM resolution to predict soil depths at hillslope scales. A geophysical method (ground penetrating radar, GPR) was used to investigate the reasons for the optimal DEM resolution findings. Point-scale soil depth from 116 sites and elevation data were collected from two adjacent headwater hillslopes (H1: 0.42 ha and H2: 0.31 ha) at the Hemuqiao hydrological experimental station in Southeast China. The elevation datasets were collected using a total station at a variable spacing level and were then used to derived DEMs at nine spatial resolutions: 0.25, 0.50, 0.75, 1.00, 2.00, 3.50, 5.00, 7.50 and 10.00 m. Nine primary and secondary topographic attributes using the nine spatial resolution DEMs were then derived. Two different algorithms (D8 and D ∞) for calculating contributing areas and related secondary topographic attributes were compared. We used and compared both linear (multiple linear regression, MLR) and non-linear (artificial neural network, ANN) models for soil depth prediction. Results demonstrated that the two models performed well for predicting soil depth. Specifically, MLR performed better than the non-linear model of ANNs. Additionally, we found that the multiple-direction algorithm (D ∞) allowed flow divergence and avoided abrupt changes in soil depth predictions (orphan cells) and should be adopted for model construction. The D ∞ algorithm performed better in divergent areas, such as ridges and side slopes, and the D ∞ algorithm also worked well in convergent areas, such as valleys. Moreover, our results demonstrated that moderate (e.g., 2.00 m) resolution topographic attributes, instead of the finest resolution, achieved the best prediction with the lowest root mean square error (RMSE) and mean absolute error (MAE) and the highest values of the coefficient of determination (R2). Moreover, the GPR results indicated that the valley accumulated more soils than side-slope areas, and a sharp increase in soil depth was found in areas adjacent to the valley. Comparing the optimal DEM resolution and valley width obtained by GPR, we found that average valley width (AVW) should be considered a good measure for choosing the optimal DEM resolution for soil depth prediction.

Estimating effective soil depth at regional scales: Legacy maps versus environmental covariates

AbstractSoil depth reflects the quantity and ecosystem service functions of soil resources. However, there is no universal standard to measure soil depth at present, and digital soil mapping approaches for predicting soil depth at the regional scale remain immature. Using observation of soil profile morphology, we compared the soil depth nomenclatures from the World Reference Base for Soil Resources, Chinese Soil Taxonomy, and Soil Taxonomy. For this study, shallow soils were defined as those with an effective soil depth < 100 cm. Based on legacy data and field soil survey, the spatial distribution of shallow soils in Xinjiang, China, and the main controlling environmental factors were explored. Results showed that shallow soils in Xinjiang are mainly distributed in high altitude regions such as the Tian Mountains. At the regional scale, significant correlations were observed between soil depth and climate factors, as well as between soil depth and vegetation fractional coverage. Contrary to previous conclusions at small spatial scales, terrain attributes could not explain soil depth variation at the regional scale. This study addressed knowledge gaps on soil depth prediction at regional scales while elucidating climate‐vegetation‐soil coevolution.

Soil depth modelling using terrain analysis and satellite imagery: the case study of Qeshlaq mountainous watershed (Kurdistan, Iran)

Soil depth is a major soil characteristic, which is commonly used in distributed hydrological modelling in order to present watershed subsurface attributes. This study aims at developing a statistical model for predicting the spatial pattern of soil depth over the mountainous watershed from environmental variables derived from a digital elevation model (DEM) and remote sensing data. Among the explanatory variables used in the models, seven are derived from a 10 m resolution DEM, namely specific catchment area, wetness index, aspect, slope, plan curvature, elevation and sediment transport index. Three variables landuse, NDVI and pca1 are derived from Landsat8 imagery, and are used for predicting soil depth by the models. Soil attributes, soil moisture, topographic curvature, training samples for each landuse and major vegetation types are considered at 429 profiles within four subwatersheds. Random forests (RF), support vector machine (SVM) and artificial neural network (ANN) are used to predict soil depth using the explanatory variables. The models are run using 336 data points in the calibration dataset with all 31 explanatory variables, and soil depth as the response of the models. Mean decrease permutation accuracy is performed on Variable selection. Testing dataset is done with the model soil depth values at testing locations (93 points) using different efficiency criteria. Prediction error is computed for both the calibration and testing datasets. Results show that the variables landuse, specific surface area, slope, pca1, NDVI and aspect are the most important explanatory variables in predicting soil depth. RF and SVM models are appropriate for the mountainous watershed areas that have been limited in the depth of the soil and ANN model is more suitable for watershed with the fields of agricultural and deep soil depth.

Soil depth spatial prediction by fuzzy soil-landscape model

Soil depth is a soil property that influences land use, land suitability, and earth surface processes. This article presents a simple method for predicting soil depth by constructing a membership function based on fuzzy C-means. This paper incorporates the soil type map, the land use map, and one type of DEM data to construct a soil-landscape model for soil depth prediction. It compares a fuzzy C-means classifier that includes expert judgment with a conditional autoregressive (CAR) model. Prediction efficiency was evaluated in the Three Gorges area of China using the root-mean-square error (RMSE) and the agreement coefficient (AC) of predictions at validation points. The prediction stability of soil depth values from the fuzzy model is close to the regression model; the AC value indicates a better agreement by the fuzzy C-means method (0.428) than when using the regression model (0.420). The purposive sampling approach was provided by our method by the centroid where the fuzzy membership value is above 0.85, which improves the efficiency of the field sampling. The expansibility of our method is limited as the typical centroid sample location is dependent on the study area. The fuzzy membership value must be recalculated to provide a new typical centroid for field sample when enlarging the study area. The results indicate that the soil-landscape model constructed by the fuzzy membership value with fuzzy C-means method and the conventional soil map provides better quality soil depth spatial information on soil depth.

Predicting soil depth using simple ground-based measurements of stem shape and taper in the butt swell section of individual Pinus radiata trees

ABSTRACTPredicting soil depth using simple ground-based measurements of the tree stem has multiple benefits for precision (site-specific) forest management and estimating carbon stocks of plantation forests. Current methods of mapping soil depth rely on collecting a sufficient density of direct soil measurements, which is expensive and typically not feasible over extensive forest areas. The availability of detailed soil depth information under forest plantations is consequently sparse and this presents a significant impediment to precision forest management and the ability to estimate forest soil carbon stocks. In this study, we propose that the relationship between stem shape and taper in the butt swell of individual Pinus radiata trees and soil depth can be described in a simple empirical model. We demonstrate that shape and taper of the butt-swell section of the tree stem are as robust predictors of soil depth as individual tree height, and also have the advantage of being easy to measure from the ground. This finding has potential benefits for reducing the cost of soil data collection and improving fine-scale forest soil mapping.