Scientific Data · 2020 · 243 citations · 27 references
Natural SciencesEarth SciencesSoil SciencesGeomorphologyRemote SensingSoil ScienceGeological ModelingSoil MappingAccuracyBedrock DepthDepth To Bedrock EstimationDepth-to-bedrock DeterminationGradient BoostingGradient Boosting TreesQuantile RegressionRandom Forests
Depth to bedrock influences or controls many of the Earth's physical and chemical processes. It plays important roles in soil science, geology, hydrology, land surface processes, civil engineering, and other related fields. However, information about depth to bedrock in China is very deficient, and there is no independent map of depth to bedrock in China currently. This paper describes the materials and methods to produce high-resolution (100 m) depth-to-bedrock maps of China. For different research and application needs, two sets of data are provided for users. One is the prediction by the ensemble of the random forests and gradient boosting tree models, and the other is the prediction and the uncertainty of prediction based on quantile regression forests model. In comparison with depth-to-bedrock maps of China extracted from previous global predictions, our predictions showed higher accuracy and more spatial details. These data sets can provide more accurate information for Earth system research compared with previous depth-to-bedrock maps.
27
Leo Breiman · Machine Learning · 2001 · 126.2K citations · Full text
SoilGrids250m: Global gridded soil information based on machine learning
Tomislav Hengl, Jorge Mendes de Jesus, G.B.M. Heuvelink et al. · PLoS ONE · 2017 · 4.7K citations · Full text
Alex B. McBratney, Maria de Lourdes Mendonça-Santos, Budiman Minasny · Geoderma · 2003 · 3.6K citations
Factors of Soil Formation: A System of Quantitative Pedology
Rosemary L. Pendleton, Hans Jenny · Geographical Review · 1945 · 1.8K citations