Premium
Dissection of trained neural network hydrologic models for knowledge extraction
Author(s) -
Jain Ashu,
Kumar Sumant
Publication year - 2009
Publication title -
water resources research
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.863
H-Index - 217
eISSN - 1944-7973
pISSN - 0043-1397
DOI - 10.1029/2008wr007194
Subject(s) - computer science , artificial neural network , machine learning , process (computing) , artificial intelligence , set (abstract data type) , variety (cybernetics) , black box , scale (ratio) , data mining , data science , physics , quantum mechanics , programming language , operating system
Artificial neural networks (ANNs) are powerful tools for the modeling and forecasting of complex engineering systems and have been exploited by researchers to solve a variety of problems over the last couple of decades. In spite of their proven ability to provide superior model performance compared to traditional modeling approaches, they have not become popular among decision makers for operational use. It is probably because of their perceived black box nature that does not explain or consider the underlying physical processes involved. This paper presents the results of a study aimed at a systematic dissection of the massively parallel architectures of trained ANN hydrologic models to determine if they learn the underlying physical subprocesses during training. This has been achieved using simple qualitative and quantitative techniques. The data derived from three contrasting catchments at two different time scales were employed to develop ANN models and test the methodologies employed for knowledge extraction. The results obtained in this study indicate that the number of hidden neurons determined during training for a particular data set correspond to certain subprocesses of the overall physical process being modeled. It has been found that the time scale of the data employed has an effect on optimum ANN architecture and knowledge extracted.