Spatial prediction of soil depth using environmental covariates by quantile regression forest model
Authors:
- 18 September 2021
- journal article
- research article
- Published by Springer Nature in Environmental Monitoring and Assessment
- Vol. 193 (10) , 1-10
Abstract
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 − 1.81 cm, RMSE of 34 cm, PICP of 90.2, and a R2 value of 42% as compared to ordinary kriging which results in a ME of − 0.14 cm, a RMSE of 37 cm, 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.Keywords
This publication has 21 references indexed in Scilit:
- Parameterizing a physically based shallow landslide model in a data poor regionEarth Surface Processes and Landforms, 2009
- Newer Classification and Regression Tree Techniques: Bagging and Random Forests for Ecological PredictionEcosystems, 2006
- Analyzing Digital Terrain Attributes to Predict Soil Attributes for a Relatively Large AreaSoil Science Society of America Journal, 2005
- On digital soil mappingGeoderma, 2003
- Soil Mapping Using GIS, Expert Knowledge, and Fuzzy LogicSoil Science Society of America Journal, 2001
- Soil–landform relationships at within-field scales: an investigation using continuous classificationGeoderma, 1999
- A rudimentary mechanistic model for soil production and landscape developmentGeoderma, 1999
- A process‐based model for colluvial soil depth and shallow landsliding using digital elevation dataHydrological Processes, 1995
- Factors of Soil Formation: A System of Quantitative PedologyGeographical Review, 1945
- Factors of Soil FormationSoil Science, 1941