A method to avoid spatial overfitting in estimation of grassland above-ground biomass on the Tibetan Plateau

A method to avoid spatial overfitting in estimation of grassland above-ground biomass on the Tibetan Plateau

Accurate assessments of grassland above-ground biomass (AGB) are crucial for the sustainable utilization and protection of grassland resources and the eco-environment. In this study, a random forest (RF) model combined with the forward feature selection (FFS) and leave-location-out cross-validation...

Full description

Bibliographic Details
Main Authors: Chai, Y. (Author), Feng, Q. (Author), Liang, T. (Author), Niu, L. (Author), Wang, W. (Author), Wu, Y. (Author), Yu, H. (Author)
Format: Article
Language:English
Published: Elsevier B.V. 2021
Subjects:
Above ground biomass
aboveground biomass
Above-ground biomass
accuracy assessment
Alpine grassland
China
Cross-validation
Decision trees
dry matter
Eco-environments
Forecasting
Forward feature selections
grassland
Grassland resource
habitat conservation
Learning algorithms
Location
machine learning
Machine learning
Mean absolute error
Mean square error
Overfitting
Predictive accuracy
Qinghai-Xizang Plateau
Random forest
Root mean square errors
spatial analysis
spatial distribution
Sustainable utilization
Online Access:View Fulltext in Publisher

Internet

View Fulltext in Publisher

Similar Items