Improved PMI-based input variable selection approach for artificial neural network and other data driven environmental and water resource models

Input variable selection (IVS) is one of the most important steps in the development of artificial neural network and other data driven environmental and water resources models. Partial mutual information (PMI) is one of the most promising approaches to IVS, but has the disadvantage of requiring kernel density estimates (KDEs) of the data to be obtained, which can become problematic when the data are non-normally distributed, as is often the case for environmental and water resources problems. In order to overcome this issue, preliminary guidelines for the selection of the most appropriate methods for obtaining the required KDEs are determined based on the results of 3780 trials using synthetic data with distributions of varying degrees of non-normality and six different KDE techniques. The validity of the guidelines is confirmed for two semi-real case studies developed based on the forecasting of river salinity and rainfall-runoff modelling problems. •We address the performance of the PMI IVS influenced by the normality of data.•We improved the performance of the PMI IVS for non-normally distributed data.•Conventional PMI IVS performs well only for data following Gaussian distribution.•Bandwidth with reduced Gaussian assumption improves the accuracy of PMI IVS.•Preliminary guidelines are developed for PMI IVS and successfully validated.