Incorporation of high accuracy surface modeling into machine learning to improve soil organic matter mapping

Incorporation of high accuracy surface modeling into machine learning to improve soil organic matter mapping

Digital soil mapping approaches related to soil organic matter (SOM) are crucial to quantify the process of the carbon cycle in terrestrial ecosystems and thus, can better manage soil fertility. Recently, many studies have compared machine learning (ML) models with traditional statistical models in...

Full description

Bibliographic Details
Main Authors: Bao, Z. (Author), Du, Z. (Author), Li, X. (Author), Wang, Z. (Author), Yue, T. (Author), Zhao, N. (Author)
Format: Article
Language:English
Published: Elsevier B.V. 2021
Subjects:
accuracy assessment
Biogeochemistry
China
Decision trees
Digital soil mappings
Dongzhi loess tableland
Dongzhi Loess Tableland
Gradient boosting modeling
High accuracy surface modeling
High-accuracy
interpolation
Interpolation
Inverse problems
Linear regression
machine learning
Machine learning
Machine-learning
mapping method
Mean square error
Organic compounds
Random forest
Random forests
soil organic matter
Soil organic matter
Soil organic matter contents
Soil organic matters
Soil surveys
Soils
Spatial distribution
spatiotemporal analysis
Surface modeling
terrestrial ecosystem
Online Access:View Fulltext in Publisher

Internet

View Fulltext in Publisher

Similar Items