TU Darmstadt / ULB / TUbiblio

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

Göbel, Peter and Rüppel, Uwe (2009):
Support Vector Regression Approach for Predicting Groundwater Levels under Variable Pumping and Infiltration Conditions.
In: EnviroInfo 2009: Environmental Informatics and Systems Research, Aachen, Shaker Verlag, In: 23rd International Conference on Informatics for Environmental Protection (EnviroInfo), Berlin, Germany, 09.-11. September 2009, ISBN 978-3-8322-8397-1,
[Conference or Workshop Item]

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.

Item Type: Conference or Workshop Item
Erschienen: 2009
Creators: Göbel, Peter and Rüppel, Uwe
Title: Support Vector Regression Approach for Predicting Groundwater Levels under Variable Pumping and Infiltration Conditions
Language: English
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.

Title of Book: EnviroInfo 2009: Environmental Informatics and Systems Research
Place of Publication: Aachen
Publisher: Shaker Verlag
ISBN: 978-3-8322-8397-1
Divisions: 13 Department of Civil and Environmental Engineering Sciences > Institute of Numerical Methods and Informatics in Civil Engineering
13 Department of Civil and Environmental Engineering Sciences
Event Title: 23rd International Conference on Informatics for Environmental Protection (EnviroInfo)
Event Location: Berlin, Germany
Event Dates: 09.-11. September 2009
Date Deposited: 21 Jan 2015 12:36
Additional Information:

ISBN: 978-3-8322-8397-1

License: [undefiniert]
Export:

Optionen (nur für Redakteure)

View Item View Item