Hydraulic head interpolation in an aquifer unit using ANFIS and Ordinary Kriging

Bedri Kurtulus (1) , Nicolas Flipo (2) , Patrick Goblet (2) , Guillaume Vilain (3) , Julien Tournebize (4) , Gaëlle Tallec (4)

1 Geological Engineering Department
2 GEOSCIENCES - Centre de Géosciences
3 SISYPHE - Structure et fonctionnement des systèmes hydriques continentaux
4 UR HBAN - Hydrosystèmes et Bioprocédés

In this study, Ordinary Kriging (ok), and Adaptive Neuro Fuzzy based Inference System (anfis) are evaluated for assessing hydraulic head distribution in an aquifer unit covering 40 km2. Cartesian coordinates of the samples were used as inputs of anfis. Calibrated models are used to interpolate the hydraulic head distribution on a 50 m square - grid. Both simulations have realistic pattern (R2 > 0.97) even if ok performs slightly better than anfis at sampling location. The two methods capture different patterns. The Comparison of the two distributions allows for identifying area of estimate uncertainty, what can be used to improve the sampling network.

Domaines: Planète et Univers [physics]; Sciences de la Terre; Hydrologie; Sciences de l'environnement; Milieux et Changements globaux; Informatique [cs]; Intelligence artificielle [cs.AI]; Statistiques [stat]; Applications [stat.AP]

Bedri Kurtulus, Nicolas Flipo, Patrick Goblet, Guillaume Vilain, Julien Tournebize, et al.. Hydraulic head interpolation in an aquifer unit using ANFIS and Ordinary Kriging. Studies in Computational Intelligence, springer, pp.265-276, 2011, Studies in Computational Intelligence, ⟨10.1007/978-3-642-20206-3_18⟩. ⟨hal-00598875⟩