Soil moisture estimation using classification and regression trees and neural networks

Gwangseob Kim, Jung A. Park

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

In this paper, a soil moisture estimation model was developed to calculate the nationwide soil moisture fields using on site soil moisture observation, precipitation, surface temperature, MODIS NDVI and a data mining technique, Classification And Regression Tree (CART) algorithm and neural networks. The model was applied to the Yong-dam dam basin since the soil moisture observations of the Yong-dam dam basin were reliable. Soil moisture observations of 4 sites were used for the model calibration and that of a site was used for the model validation. Results showed that the soil moisture estimation using a data mining technique and ancillary data allow us to get reasonable soil moisture fields which are suitable for the hydrologic model application.

Original languageEnglish
Title of host publication6th IASME/WSEAS Int. Conf. on Continuum Mechanics, CM'11, 6th IASME/WSEAS Int. Conf. on Water Resources, Hydraulics and Hydrology, WHH'11, 5th IASME/WSEAS Int. Conf. on Geology and Seismology, GES'11
Pages57-60
Number of pages4
StatePublished - 2011
Event6th IASME / WSEAS International Conference on Continuum Mechanics, CM'11, 6th IASME / WSEAS International Conference on Water Resources, Hydraulics and Hydrology, WHH'11, 5th IASME / WSEAS International Conference on Geology and Seismology, GES'11 - Cambridge, United Kingdom
Duration: 23 Feb 201125 Feb 2011

Publication series

Name6th IASME/WSEAS Int. Conf. on Continuum Mechanics, CM'11, 6th IASME/WSEAS Int. Conf. on Water Resources, Hydraulics and Hydrology, WHH'11, 5th IASME/WSEAS Int. Conf. on Geology and Seismology, GES'11

Conference

Conference6th IASME / WSEAS International Conference on Continuum Mechanics, CM'11, 6th IASME / WSEAS International Conference on Water Resources, Hydraulics and Hydrology, WHH'11, 5th IASME / WSEAS International Conference on Geology and Seismology, GES'11
Country/TerritoryUnited Kingdom
CityCambridge
Period23/02/1125/02/11

Keywords

  • CART
  • MODIS
  • NDVI
  • Neural networks
  • Precipitation
  • Soil moisture
  • Surface temperature

Fingerprint

Dive into the research topics of 'Soil moisture estimation using classification and regression trees and neural networks'. Together they form a unique fingerprint.

Cite this