Extended model prediction of high-resolution soil organic matter over a large area using limited number of field samples

•A two-stage approach was developed to extend model prediction of soil organic matter.•The local SOM model had high model performance but weak capability of generalization.•Building a stable extended model only required 20% of 386 field samples.•The optimal extended model improved model accuracy wit...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Computers and electronics in agriculture 2020-02, Vol.169, p.105172, Article 105172
Hauptverfasser:	Zhao, Zhengyong, Yang, Qi, Sun, Dongxiao, Ding, Xiaogang, Meng, Fan-Rui
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial neural network Artificial neural networks Extended model Forest management Forestry Limited field sample Linear equation Model accuracy Organic matter Root-mean-square errors Slope Soil mapping Soil organic matter Soils Spatial distribution
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!