An evolutionary data mining approach on hydrological data with classifier juries

Wilfried Segretier (1) , Manuel Clergue (1) , Martine Collard (1) , Luis Izquierdo (2)

1 IDC
2 Universidad de La Habana [Cuba]

In this paper, we present an evolutionary approach for extracting a model of flood prediction from hydrological data observed timely on water heights in a river watershed. Since this kind of data recorded by sensors on river basins is highly scarce and hopefully much unbalanced between cases of floods and non-floods, we have adopted the notion of aggregate variables which values are computed as aggregates on raw data. An evolutionary algorithm is involved to allow selecting the best sets - juries of classifiers- of such variables as predictive variables. Two real hydrological data sets are trained and they both show the efficiency of the method compared to traditional solutions for prediction.

Mots clés: Evolutionary Computation; Flood prediction; Data mining

Domaines: Intelligence artificielle [cs.AI]

Wilfried Segretier, Manuel Clergue, Martine Collard, Luis Izquierdo. An evolutionary data mining approach on hydrological data with classifier juries. IEEE Congress on Evolutionary Computation 2012, Jun 2013, Brisbane, Australia. pp.1-8, ⟨10.1109/CEC.2012.6252897⟩. ⟨hal-00840739⟩