The study of aquifers dynamics is a fundamental issue for the analysis of groundwater resources. However, the modeling of aquifer dynamics by means of physically based models is geneally not simple and cheap since a lot of information is necessary in order to define the model. For this reason the use of data-driven modeling approaches, able to return explicit models starting from measured reasonably low cost data, could be a solution to this issue. Thus, this work introduces the use of an evolutionary modeling technique, namely Evolutionary Polynomial Regression (EPR), aimed at the prediction of water table levels for two aquifers located in the same area of south east of Italy. These aquifers are hydrogeologically different, even if located in the same area. The earlier is a surficial porous aquifer, while the latter is a coastal karst aquifer. Even if subject to the same climate conditions, they show different hydrogeological behaviours, in term of different dynamics and responses to rainfall. EPR is used herein to predict groundwater levels for both the aquifers as well as returning equation structures which are consistent with their different dynamics. The obtained results show how EPR is able to correctly interpretate different hydrogeological situations.

Karst and porous aquifer dynamic analysis by EPR

DOGLIONI, Angelo;SIMEONE, Vincenzo;GIUSTOLISI, Orazio
2011-01-01

Abstract

The study of aquifers dynamics is a fundamental issue for the analysis of groundwater resources. However, the modeling of aquifer dynamics by means of physically based models is geneally not simple and cheap since a lot of information is necessary in order to define the model. For this reason the use of data-driven modeling approaches, able to return explicit models starting from measured reasonably low cost data, could be a solution to this issue. Thus, this work introduces the use of an evolutionary modeling technique, namely Evolutionary Polynomial Regression (EPR), aimed at the prediction of water table levels for two aquifers located in the same area of south east of Italy. These aquifers are hydrogeologically different, even if located in the same area. The earlier is a surficial porous aquifer, while the latter is a coastal karst aquifer. Even if subject to the same climate conditions, they show different hydrogeological behaviours, in term of different dynamics and responses to rainfall. EPR is used herein to predict groundwater levels for both the aquifers as well as returning equation structures which are consistent with their different dynamics. The obtained results show how EPR is able to correctly interpretate different hydrogeological situations.
2011
Proceedings of the 4th ASCE-EWRI International Perspective on Water Resources and the Environment
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11589/17855
Citazioni
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact