Home // ADVCOMP 2012, The Sixth International Conference on Advanced Engineering Computing and Applications in Sciences // View article

Application of the Stacking Regression in Context of the Soil-Water Modelling

Authors:
Milan Cisty
Juraj Bezak
Jana Skalova

Keywords: soil-water modelling; pedotransfer function; data-driven model; stacking

Abstract:
Modelling water transport in soil has become an important tool in simulating hydrological systems and agricultural productivity. Some of the data necessary for this modelling are usually easily available in competent institutions, but hydraulic soil properties (namely water retention curve) are only rarely easily available. The aim of this paper is to contribute to solving this deficit by evaluating so-called pedotransfer functions by data-driven modeling methods. Multi-linear regression, artificial neural networks, support vector machines and combination of these three methods in stacking model was evaluated. Work proves that stacking model yields more precise results than individual data-driven models and could be suggested for soil water modelling.

Pages: 23 to 26

Copyright: Copyright (c) IARIA, 2012

Publication date: September 23, 2012

Published in: conference

ISSN: 2308-4499

ISBN: 978-1-61208-237-0

Location: Barcelona, Spain

Dates: from September 23, 2012 to September 28, 2012