Performance of artifcial neural networks (ANNs), multi-objective group method of data handling (mGMDH) and multivariate linear regression (MLR) was compared for estimating least limiting water range (LLWR). Eleven soil attributes of 188 soil samples (Inceptisols) were used as independent variables to estimate LLWR directly (indicated as LLWRd) and indirectly via moisture coefcients (LLWRi ) by ANNs, mGMDH and MLR methods. ANNs appeared as the most accurate and reliable tool for LLWRd and LLWRi prediction, and mGMDH and MLR ranked in descending order, respectively. For LLWRd, rootmean-square error (RMSE) values decreased from 0.040 to 0.024 (for testing (validation) step), when the method shifted from MLR to ANNs. Accuracy and reliability were both signifcantly improved from MLR to mGMDH and ANNs, but between the two later methods, they were only signifcant at the training step. However, for LLWRi , it was signifcant for testing step, too. For testing step, the r value between LLWRd and LLWRi with the experimental LLWR (LLWRe) was 0.91 and 0.89, respectively, showing the priority of direct estimation of the LLWR. Soil bulk density, organic carbon, calcium carbonate equivalent, dithionate bicarbonate extractable aluminum, clay and sand, respectively, were better predictors for LLWRd..
