inscription
PORTAIL D'INFORMATION GÉOGRAPHIQUE

Spatially distributed modeling of soil organic matter across China : An application of artificial neural network approach

Auteur(s) et Affiliation(s)

LI, Q.-Q.
College of Resources and Environment, Sichuan Agricultural Univ., Chengdu, Chine
Inst. of Geographic Sciences and Natural Resources Research, Beijing, Chine
YUE, T.-X.
Inst. of Geographic Sciences and Natural Resources Research, Beijing, Chine
WANG, C.-Q.
College of Resources and Environment, Sichuan Agricultural Univ., Chengdu, Chine
ZHANG, W.-J.
State Key Lab. of Hydraulics and Mountain River Engineering, Sichuan Univ., Chengdu, Chine
YU, Y.
College of Forestry, Agricultural Univ., Yaan, Chine
LI, B.
College of Resources and Environment, Sichuan Agricultural Univ., Chengdu, Chine
YANG, J.
College of Resources and Environment, Sichuan Agricultural Univ., Chengdu, Chine
BAI, G.-C.
College of Resources and Environment, Sichuan Agricultural Univ., Chengdu, Chine


Description :
This study proposed a radial basis function neural networks model (RBFNN), combined with principal component analysis (PCA), to predict the spatial distribution of soil organic matter (SOM) content across China. To assess its feasibility, 6 241 soil samples collected during the second national soil survey period were used. This approach obtained lower prediction errors than multiple linear regression and regression kriging. This approach also produced a more realistic spatial pattern of soil organic matter. The result suggests that the proposed method can play a vital role in improving prediction accuracy of SOM within a large area.


Type de document :
Article de périodique

Source :
Catena (Giessen), issn : 0341-8162, 2013, vol. 104, p. 210-218, nombre de pages : 9, Références bibliographiques : 37 ref.

Date :
2013

Editeur :
Pays édition : Allemagne, Cremlingen-Destedt, Catena

Langue :
Anglais
Droits :
Tous droits réservés © Prodig - Bibliographie Géographique Internationale (BGI)