In this paper, a quantitative structureÂproperty relationships (QSPR) study based on feed-forward artificial neural network (ANN) with back-propagation learning rule and multiple linear regression (MLR) methods has been carried out to predict the Solubility behavior of pesticides. Accurate description of thewater Solubility of 38 compounds including commonly used insecticides, herbicides and fungicides and some metabolites is successfully achieved. The Stepwise SPSS was used for the selection of the variables that resulted in the best-fitted models.The regression coefficients of prediction for training and test sets for ANN model were 0.997 and 0.992 respectively. The proposed nonlinear QSPR model (ANN) exhibits a high degree of correlation between observed and computed water Solubility and a good predictive performance that supports its application for the prediction of the Solubility behavior of unknown pesticides. A multiple linear regression (MLR) based on the same selected descriptors shows a significantly worse predictive capability.