Neural Networks: From Black Box towards Transparent Box Application to Evapotranspiration Modeling

Neural networks are well known for their ability to model non linear functions, but as statistical methods usually does, they use a no parametric approach thus, a priori knowledge is not obvious to be taken into account no more than the a posteriori knowledge. In order to deal with these problematics, an original way to encode the knowledge inside the architecture is proposed. This method is applied to the problem of the evapotranspiration inside karstic aquifer which is a problem of huge utility in order to deal with water resource. Keywords—Neural-Networks, Hydrology, Evapotranpiration, Hidden Function Modeling.

[1]  Anne Johannet,et al.  Modelling non Measurable Processes by Neural Networks: Forecasting Underground Flow Case Study of the Cèze Basin (Gard - France) , 2007 .

[2]  Bedri Kurtulus,et al.  Evaluation of the ability of an artificial neural network model to simulate the input-output responses of a large karstic aquifer: the La Rochefoucauld aquifer (Charente, France) , 2007 .

[3]  Young-Oh Kim,et al.  Rainfall‐runoff models using artificial neural networks for ensemble streamflow prediction , 2005 .

[4]  Edward R. Dougherty,et al.  Mathematical methods for artificial intelligence and autonomous systems , 1988 .

[5]  Elie Bienenstock,et al.  Neural Networks and the Bias/Variance Dilemma , 1992, Neural Computation.

[6]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[7]  Paulin Coulibaly,et al.  Groundwater level forecasting using artificial neural networks , 2005 .

[8]  J. Nash,et al.  River flow forecasting through conceptual models part I — A discussion of principles☆ , 1970 .

[9]  F. Anctil,et al.  Which potential evapotranspiration input for a lumped rainfall-runoff model?. Part 2: Towards a simple and efficient potential evapotranspiration model for rainfall-runoff modelling , 2005 .

[10]  Kumpati S. Narendra,et al.  Gradient methods for the optimization of dynamical systems containing neural networks , 1991, IEEE Trans. Neural Networks.

[11]  Paul J. Werbos,et al.  Backpropagation Through Time: What It Does and How to Do It , 1990, Proc. IEEE.

[12]  Adrian J. Shepherd,et al.  Second-Order Methods for Neural Networks , 1997 .

[13]  Kuolin Hsu,et al.  Improved streamflow forecasting using self-organizing radial basis function artificial neural networks , 2004 .

[14]  Asaad Y. Shamseldin,et al.  Development of rainfall–runoff models using Takagi–Sugeno fuzzy inference systems , 2006 .

[15]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[16]  Gérard Dreyfus,et al.  How to be a gray box: dynamic semi-physical modeling , 2001, Neural Networks.