TU Darmstadt / ULB / TUbiblio

Support Vector Regression Approach for Predicting Groundwater Levels under Variable Pumping and Infiltration Conditions

Göbel, Peter ; Rüppel, Uwe :
Support Vector Regression Approach for Predicting Groundwater Levels under Variable Pumping and Infiltration Conditions.
In: 23rd International Conference on Informatics for Environmental Protection (EnviroInfo), 09.-11. September 2009, Berlin, Germany. EnviroInfo 2009: Environmental Informatics and Systems Research Shaker Verlag , Aachen
[ Konferenzveröffentlichung] , (2009)

Kurzbeschreibung (Abstract)

Regression problems in environmental engineering can be tackled in principle by fundamentally different approaches, e.g., physically based numerical modeling or methods of machine learning. Appliance of the machine learning method Support Vector Machines (SVM) for regression is called Support Vector Regression (SVR). The feasibility of SVR for predicting groundwater levels in complex groundwater systems under variable pumping and infiltration conditions is demonstrated in a representative study area of groundwater management. Real-world data were used to train SVR models to predict transient groundwater levels in response to changing pumping and infiltration conditions. The SVR models were then validated with twelve sequential months. The prognoses of one year in monthly periods were compared against measured groundwater levels. Although the experiments are still in an early state, the best SVR models so far already achieve in groundwater level prognosis of twelve months an average monthly deviation of about 0,029 m between the SVR predicted and the measured water level. While different SVR models can retain unlike qualities in terms of diverse scenarios and the climate scenario that serves as input data for the prediction horizon is uncertain within a certain scope, more than one SVR model and climate scenarios may be combined in an ensemble fashion. To put it in a nutshell, it is to say that the deployment of SVR technology in groundwater prediction holds the fundamental potential to improve management strategies and sound decision-making for hydro geological problems.

Typ des Eintrags: Konferenzveröffentlichung
Erschienen: 2009
Autor(en): Göbel, Peter ; Rüppel, Uwe
Titel: Support Vector Regression Approach for Predicting Groundwater Levels under Variable Pumping and Infiltration Conditions
Sprache: Englisch
Kurzbeschreibung (Abstract):

Regression problems in environmental engineering can be tackled in principle by fundamentally different approaches, e.g., physically based numerical modeling or methods of machine learning. Appliance of the machine learning method Support Vector Machines (SVM) for regression is called Support Vector Regression (SVR). The feasibility of SVR for predicting groundwater levels in complex groundwater systems under variable pumping and infiltration conditions is demonstrated in a representative study area of groundwater management. Real-world data were used to train SVR models to predict transient groundwater levels in response to changing pumping and infiltration conditions. The SVR models were then validated with twelve sequential months. The prognoses of one year in monthly periods were compared against measured groundwater levels. Although the experiments are still in an early state, the best SVR models so far already achieve in groundwater level prognosis of twelve months an average monthly deviation of about 0,029 m between the SVR predicted and the measured water level. While different SVR models can retain unlike qualities in terms of diverse scenarios and the climate scenario that serves as input data for the prediction horizon is uncertain within a certain scope, more than one SVR model and climate scenarios may be combined in an ensemble fashion. To put it in a nutshell, it is to say that the deployment of SVR technology in groundwater prediction holds the fundamental potential to improve management strategies and sound decision-making for hydro geological problems.

Buchtitel: EnviroInfo 2009: Environmental Informatics and Systems Research
Ort: Aachen
Verlag: Shaker Verlag
Fachbereich(e)/-gebiet(e): 13 Fachbereich Bau- und Umweltingenieurwissenschaften > Institut für Numerische Methoden und Informatik im Bauwesen
13 Fachbereich Bau- und Umweltingenieurwissenschaften
Veranstaltungstitel: 23rd International Conference on Informatics for Environmental Protection (EnviroInfo)
Veranstaltungsort: Berlin, Germany
Veranstaltungsdatum: 09.-11. September 2009
Hinterlegungsdatum: 21 Jan 2015 12:36
Zusätzliche Informationen:

ISBN: 978-3-8322-8397-1

Export:

Optionen (nur für Redakteure)

Eintrag anzeigen Eintrag anzeigen