Articles | Volume 15, issue 1
Nonlin. Processes Geophys., 15, 115–126, 2008
https://doi.org/10.5194/npg-15-115-2008

Special issue: Nonlinear and Scaling Processes in Hydrology and Soil...

Nonlin. Processes Geophys., 15, 115–126, 2008
https://doi.org/10.5194/npg-15-115-2008

  15 Feb 2008

15 Feb 2008

Estimation of soil types by non linear analysis of remote sensing data

C. Hahn and R. Gloaguen C. Hahn and R. Gloaguen
  • Remote Sensing Group, Geology Institute, TU Bergakademie Freiberg, 09599 Freiberg, Germany

Abstract. The knowledge of soil type and soil texture is crucial for environmental monitoring purpose and risk assessment. Unfortunately, their mapping using classical techniques is time consuming and costly. We present here a way to estimate soil types based on limited field observations and remote sensing data. Due to the fact that the relation between the soil types and the considered attributes that were extracted from remote sensing data is expected to be non-linear, we apply Support Vector Machines (SVM) for soil type classification. Special attention is drawn to different training site distributions and the kind of input variables. We show that SVM based on carefully selected input variables proved to be an appropriate method for soil type estimation.