Deep learning models have gained great popularity in statistical modeling because they lead to very competitive regression models, often outperforming classical such as generalized linear models. The disadvantage of deep is that their solutions are difficult interpret and explain, variable selection not easily possible solve feature engineering internally a nontransparent way. Inspired by the a...

High groundwater As concentrations in oxidizing systems are generally associated with As adsorption onto hydrous metal (Al, Fe or Mn) oxides and mobilization with increased pH. The objective of this study was to evaluate the distribution, sources and mobilization mechanisms of As in the Southern High Plains (SHP) aquifer, Texas, relative to those in other semiarid, oxidizing systems. Elevated g...

While neural networks have been achieving increasingly significant excitement in solving classification tasks such as natural language processing, their lack of interpretability becomes a great challenge for to be deployed certain high-stakes human-centered applications. To address this issue, we propose new approach generating interpretable predictions by inferring simple three-layer network w...

The unmanaged groundwater extraction and inadequate aquifer recharge is the major cause of groundwater depletion in different parts of the world. In this study, the groundwater flow system of Mahvelat-Feizabad aquifer (NE of Iran) has been numerically simulated using MODFLOW code in the GMS interface. The model, primarily, calibrated for steady state condition for the mean hydraulic values of o...