Prediction of second-order rate constants between carbonate radical and organics by deep neural network combined with molecular fingerprints

Status and future trends in wastewater management strategies using artificial intelligence and machine learning techniques

The two main things needed to fulfill the world's impending need for water in the face of the widespread water crisis are collecting water and recycling. To do this, the present study has placed a greater focus on water management strategies used in a variety of contexts areas. To distribute water effectively, save it, and satisfy water quality requirements for a variety of uses, it is imperative to apply intelligent water management mechanisms while keeping in mind the population density index. The present review unveiled the latest trends in water and wastewater recycling, utilizing several Artificial Intelligence (AI) and machine learning (ML) techniques for distribution, rainfall collection, and control of irrigation models. The data collected for these purposes are unique and comes in different forms. An efficient water management system could be developed with the use of AI, Deep Learning (DL), and the Internet of Things (IoT) structure. This study has investigated several water management methodologies using AI, DL and IoT with case studies and sample statistical assessment, to provide an efficient framework for water management.

Experimental determination and QSAR analysis of the rate constants for SO5•- reactions with aromatic micropollutants in water

S(IV)-based systems used for advanced oxidation processes (AOPs) have been constructed for the degradation of organic contaminants via oxysulfur radicals, including SO3•-, SO4•-, and SO5•-. Although SO5•- is proposed as an active species in AOPs processes, research on the reactivity of SO5•- has remained unclear. In this work, 53 target aromatic micropollutants (AMPs), including 13 phenols, 27 amines, and 13 PPCPs were selected to determine the second-order reaction rate constants for SO5•- using the competitive kinetics method, in which the [Formula: see text] values, observed at pH 4 ranged from (2.44 ± 0.00) × 105 M-1 s-1 to (4.41 ± 0.28) × 107 M-1 s-1. Quantitative structure-activity relationship (QSAR) models for the oxidation of AMPs by SO5•- were developed based on 40 [Formula: see text] values of amines and phenols, and their molecular descriptors, using the stepwise multiple linear regression method. This comprehensive model exhibited the excellent goodness-of-fit (Radj2 = 0.802), robustness (QLOO2 = 0.749), and predictability (Qext2 = 0.656), and the one-electron oxidation potential (Eox), energy of the highest occupied molecular orbital energy (EHOMO), and most positive net atomic charge on the carbon atoms (qC+) were considered the most influential descriptors for the comprehensive model, indicating that SO5•- oxidizes pollutants via single electron transfer reaction and exhibits a strong oxidation capacity, especially for pollutants containing electron-donating groups. Moreover, the [Formula: see text] values of 13 PPCPs were predicted using this comprehensive model, which suggested the practical application significance of the QSAR model. This study emphasizes the direct oxidation capacity of SO5•-, which is important to evaluate and simulate AOPs based on S(IV).

Prediction of free radical reactions toward organic pollutants with easily accessible molecular descriptors

Machine learning (ML) is becoming an efficient tool for predicting the fate of aquatic contaminants owing to the preponderance of big data. However, whether ML can "learn" the differences in reactivity among different free radicals has not yet been tested. In this work, the effectiveness of combining ML algorithms with molecular fingerprints to predict the reactivity of three free radicals was evaluated. First, a dataset containing 211 organic pollutants and their respective rate constants with the carbonate radical (CO3•-) was used to develop predictive models using both linear regression and ML methods. The use of topological atomic alignment information, in the form of the molecular access system (MACCS) and Morgan Fingerprint, and the electronic structure features (energy levels of the lowest unoccupied and highest occupied molecular orbitals, ELUMO and EHOMO, and the energy gap between ELUMO and EHOMO) gave satisfactory predictive performances (ML model with Random Forest algorithm with MACCS: RMSEtest = 0.787; linear regression model with energy levels: RMSEtest = 0.641). Additionally, the model interpretation correctly described that the key reactivity features for CO3•- were relatively close to those for SO4•- rather than those for •OH. These results suggest that combination of ML algorithms with easily accessible molecular fingerprints would be a powerful tool to accurately predict the radical reactions towards organic compounds.

Property Prediction and Structural Feature Extraction of Polyimide Materials Based on Machine Learning

The construction of material prediction models using machine learning algorithms can aid in the polyimide structural design and screening of materials as well as accelerate the development of new materials. There is a lack of research on predicting the optical properties of polyimide materials and the interpretation of the structural features. Here, we collected 652 polyimide molecular structures and used seven popular machine learning algorithms to predict the glass transition temperature and cut-off wavelength of polyimide materials and extract key feature information of repeating unit structures. The results showed that the root mean square error of the glass transition temperature prediction model was 33.92 °C, and the correlation coefficient was 0.861. The root mean square error of the cut-off wavelength prediction model was 17.18 nm, and the correlation coefficient was 0.837. The elasticity of the molecular structure was also found to be the key factor affecting glass transition temperature, and the presence and location of heterogeneous atoms had a significant effect on the cut-off wavelengths. Finally, eight polyimide materials were synthesized to test the accuracy of the prediction models, and the experimental characterization values agreed with the predicted values. The results would contribute to the development of polyimide structural design and materials preparation for flexible display.

Simulating and Comparing CO2/CH4 Separation Performance of Membrane-Zeolite Contactors by Cascade Neural Networks

Separating carbon dioxide (CO₂) from gaseous streams released into the atmosphere is becoming critical due to its greenhouse effect. Membrane technology is one of the promising technologies for CO₂ capture. SAPO-34 filler was incorporated in polymeric media to synthesize mixed matrix membrane (MMM) and enhance the CO₂ separation performance of this process. Despite relatively extensive experimental studies, there are limited studies that cover the modeling aspects of CO₂ capture by MMMs. This research applies a special type of machine learning modeling scenario, namely, cascade neural networks (CNN), to simulate as well as compare the CO₂/CH₄ selectivity of a wide range of MMMs containing SAPO-34 zeolite. A combination of trial-and-error analysis and statistical accuracy monitoring has been applied to fine-tune the CNN topology. It was found that the CNN with a 4-11-1 topology has the highest accuracy for the modeling of the considered task. The designed CNN model is able to precisely predict the CO₂/CH₄ selectivity of seven different MMMs in a broad range of filler concentrations, pressures, and temperatures. The model predicts 118 actual measurements of CO₂/CH₄ selectivity with an outstanding accuracy (i.e., AARD = 2.92%, MSE = 1.55, R = 0.9964).