Modelling Soil Water Retention Using Support Vector Machines with Genetic Algorithm Optimisation

This work presents point pedotransfer function (PTF) models of the soil water retention curve. The developed models allowed for estimation of the soil water content for the specified soil water potentials: –0.98, –3.10, –9.81, –31.02, –491.66, and –1554.78 kPa, based on the following soil characteri...

Full description

Saved in:
Bibliographic Details
Main Authors: Krzysztof Lamorski, Cezary Sławiński, Felix Moreno, Gyöngyi Barna, Wojciech Skierucha, José L. Arrue
Format: Article
Language:English
Published: Wiley 2014-01-01
Series:The Scientific World Journal
Online Access:http://dx.doi.org/10.1155/2014/740521
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850177397257666560
author Krzysztof Lamorski
Cezary Sławiński
Felix Moreno
Gyöngyi Barna
Wojciech Skierucha
José L. Arrue
author_facet Krzysztof Lamorski
Cezary Sławiński
Felix Moreno
Gyöngyi Barna
Wojciech Skierucha
José L. Arrue
author_sort Krzysztof Lamorski
collection DOAJ
description This work presents point pedotransfer function (PTF) models of the soil water retention curve. The developed models allowed for estimation of the soil water content for the specified soil water potentials: –0.98, –3.10, –9.81, –31.02, –491.66, and –1554.78 kPa, based on the following soil characteristics: soil granulometric composition, total porosity, and bulk density. Support Vector Machines (SVM) methodology was used for model development. A new methodology for elaboration of retention function models is proposed. Alternative to previous attempts known from literature, the ν-SVM method was used for model development and the results were compared with the formerly used the C-SVM method. For the purpose of models’ parameters search, genetic algorithms were used as an optimisation framework. A new form of the aim function used for models parameters search is proposed which allowed for development of models with better prediction capabilities. This new aim function avoids overestimation of models which is typically encountered when root mean squared error is used as an aim function. Elaborated models showed good agreement with measured soil water retention data. Achieved coefficients of determination values were in the range 0.67–0.92. Studies demonstrated usability of ν-SVM methodology together with genetic algorithm optimisation for retention modelling which gave better performing models than other tested approaches.
format Article
id doaj-art-befa98024dda4f3f8abe3981a38d5255
institution OA Journals
issn 2356-6140
1537-744X
language English
publishDate 2014-01-01
publisher Wiley
record_format Article
series The Scientific World Journal
spelling doaj-art-befa98024dda4f3f8abe3981a38d52552025-08-20T02:18:58ZengWileyThe Scientific World Journal2356-61401537-744X2014-01-01201410.1155/2014/740521740521Modelling Soil Water Retention Using Support Vector Machines with Genetic Algorithm OptimisationKrzysztof Lamorski0Cezary Sławiński1Felix Moreno2Gyöngyi Barna3Wojciech Skierucha4José L. Arrue5Department of Metrology and Modelling of Agrophysical Processes, Institute of Agrophysics, Polish Academy of Sciences, Doświadczalna 4, 20-290 Lublin, PolandDepartment of Metrology and Modelling of Agrophysical Processes, Institute of Agrophysics, Polish Academy of Sciences, Doświadczalna 4, 20-290 Lublin, PolandInstitute for Natural Resources and Agrobiology (IRNAS-CSIC), P.O. Box 1052, 41080 Sevilla, SpainDepartment of Crop Production and Soil Science, Georgikon Faculty, University of Pannonia, Deák Ferenc Street 16, Keszthely, 8360, HungaryDepartment of Metrology and Modelling of Agrophysical Processes, Institute of Agrophysics, Polish Academy of Sciences, Doświadczalna 4, 20-290 Lublin, PolandAula Dei Experimental Station (EEAD-CSIC), P.O. Box 13034, 50080 Zaragoza, SpainThis work presents point pedotransfer function (PTF) models of the soil water retention curve. The developed models allowed for estimation of the soil water content for the specified soil water potentials: –0.98, –3.10, –9.81, –31.02, –491.66, and –1554.78 kPa, based on the following soil characteristics: soil granulometric composition, total porosity, and bulk density. Support Vector Machines (SVM) methodology was used for model development. A new methodology for elaboration of retention function models is proposed. Alternative to previous attempts known from literature, the ν-SVM method was used for model development and the results were compared with the formerly used the C-SVM method. For the purpose of models’ parameters search, genetic algorithms were used as an optimisation framework. A new form of the aim function used for models parameters search is proposed which allowed for development of models with better prediction capabilities. This new aim function avoids overestimation of models which is typically encountered when root mean squared error is used as an aim function. Elaborated models showed good agreement with measured soil water retention data. Achieved coefficients of determination values were in the range 0.67–0.92. Studies demonstrated usability of ν-SVM methodology together with genetic algorithm optimisation for retention modelling which gave better performing models than other tested approaches.http://dx.doi.org/10.1155/2014/740521
spellingShingle Krzysztof Lamorski
Cezary Sławiński
Felix Moreno
Gyöngyi Barna
Wojciech Skierucha
José L. Arrue
Modelling Soil Water Retention Using Support Vector Machines with Genetic Algorithm Optimisation
The Scientific World Journal
title Modelling Soil Water Retention Using Support Vector Machines with Genetic Algorithm Optimisation
title_full Modelling Soil Water Retention Using Support Vector Machines with Genetic Algorithm Optimisation
title_fullStr Modelling Soil Water Retention Using Support Vector Machines with Genetic Algorithm Optimisation
title_full_unstemmed Modelling Soil Water Retention Using Support Vector Machines with Genetic Algorithm Optimisation
title_short Modelling Soil Water Retention Using Support Vector Machines with Genetic Algorithm Optimisation
title_sort modelling soil water retention using support vector machines with genetic algorithm optimisation
url http://dx.doi.org/10.1155/2014/740521
work_keys_str_mv AT krzysztoflamorski modellingsoilwaterretentionusingsupportvectormachineswithgeneticalgorithmoptimisation
AT cezarysławinski modellingsoilwaterretentionusingsupportvectormachineswithgeneticalgorithmoptimisation
AT felixmoreno modellingsoilwaterretentionusingsupportvectormachineswithgeneticalgorithmoptimisation
AT gyongyibarna modellingsoilwaterretentionusingsupportvectormachineswithgeneticalgorithmoptimisation
AT wojciechskierucha modellingsoilwaterretentionusingsupportvectormachineswithgeneticalgorithmoptimisation
AT joselarrue modellingsoilwaterretentionusingsupportvectormachineswithgeneticalgorithmoptimisation