Search

The Internet of Things (IoT) sustainable solutions are the next generation of methods for managing and monitoring valuable natural resources such as water. Research has focused on smart IoT-based water management and monitoring system designs for various types of applications, including agricultural, industrial, residential, and crude oil exploration sectors. To this end, unlike other surveys available in the literature, this work presents an all-encompassing analysis of 43 papers published between 2014 and 2022 for systems proposed to manage and monitor water in four different sectors: agricultural, industrial, residential, and oilfield sectors. In this work, we also propose a new optical water management system to address a gap in the literature, particularly for oilfield processes that require significant amounts of water to stimulate oil production. The proposed system employs an advanced optical technique for sensing and transmitting collected data. Overall, this work provides a seminal guide for future research efforts focused on integrating IoT in the field of water management and monitoring.

Transforming a vast array of candidate materials into membranes with suitable morphologies and improved molecular separation performance is an arduous and costly endeavor for membrane scientists. With the advancement made in artificial intelligence and machine-learning in recent years, it is timely to ask: can machine learning methods guide gas separation membranes Fabrication? The answer is “YES”, and this article explains the justifications for this answer by systematically reviewing and analyzing the up-to-date research efforts in the field. This work aimed to explore the potential of ML algorithms as an effective and cost-saving tool in guiding the experimental process of developing the next generation polymeric membranes, and in addressing the critical needs in the field. Findings demonstrate that training Heteropolymers instead of Homopolymers, synthesizing novel polymers by an inverse design approach, and using reliable datasets that are created under the same conditions, are the most crucial factors to achieve the design intent. A path from A to Z for anyone who intends to use ML algorithms in the membranes’ synthesis process is offered. The article concludes with a brief discussion on future development prospects and open issues that are yet to be addressed for ML‐driven polymeric‐based membranes design and optimization.

Abstract A reliable and practical determination of a chemical species’ solubility in water continues to be examined using empirical observations and exhaustive experimental studies alone. Predictions of chemical solubility in water using data-driven algorithms can allow us to create a rationally designed, efficient, and cost-effective tool for next-generation materials and chemical formulations. We present results from two machine learning (ML) modeling studies to adequately predict various species’ solubility using data for over 8400 compounds. Molecular-descriptors, the most used method in previous studies, and Morgan fingerprint, a circular-based hash of the molecules' structures, were applied to produce water solubility estimates. We trained all models on 80% of the total datasets using the Random Forest (RFs) technique as the regressor and tested the prediction performance using the remaining 20%, resulting in coefficient of determination (R2) test values of 0.88 and 0.81 and root-mean-square deviation (RMSE) test values 0.64 and 0.80 for the descriptors and circular fingerprint methods, respectively. We interpreted the produced ML models and reported the most effective features for aqueous solubility measures using the Shapley Additive exPlanations (SHAP) and thermodynamic analysis. Low error, ability to investigate the molecular-level interactions, and compatibility with thermodynamic quantities made the fingerprint method a distinct model compared to other available computational tools. However, it is worth emphasizing that physicochemical descriptor model outperformed the fingerprint model in achieving better predictive accuracy for the given test set.