Skip to content

Machine learning-based optimization strategy for comprehensive toxicity regulation in catalytic ozonation systems.

Oct 2026 · Water Research · Vol 309 Pt A, pp. 127124 · 0 citations · 53 references
Medicine

TL;DR

A hyperparameter-optimized random forest model provides a model-guided basis for identifying catalyst-condition combinations associated with lower predicted toxicity within the represented chemical space.

Abstract

Heterogeneous catalytic ozonation mitigates aquatic toxicity, yet comprehensive regulation strategies encompassing catalyst properties, reaction conditions, and pollutant molecular descriptors remain largely unexplored. In this study, three feature categories were quantitatively correlated with comprehensive toxicity using a hyperparameter-optimized random forest model. Carbon number and HOMO defined intrinsic pollutant response, whereas pH, reaction time, and catalyst metal identity represented adjustable variables for engineering regulation. Within the represented chemical space, low-carbon/high-HOMO pollutants exhibited lower predicted toxicity in model-identified regions associated with lower-atomic-number metal catalysts, near-neutral pH, and reaction times below 40 min or above 100 min. Together, these molecular, catalyst, and operational features characterize a coupled multivariable response pattern in predicted comprehensive toxicity. Metal identity, statistically represented by atomic number, was associated with distinct toxicity responses. Density functional theory calculations of two selected representative catalysts, Fe2O3 and SnO2, linked their contrasting O3 activation to differences in local electronic structure and interfacial charge transfer, with Fe2O3 showing stronger O3 adsorption and charge transfer. Furthermore, carbon number and highest occupied molecular orbital (HOMO) energy jointly influence electron distribution in pollutants, governing selectivity of bond cleavage. Low-carbon/high-HOMO pollutants localize electrons at electron-rich functional groups, favoring electrophilic 1O2/•OH attack and more directed transformation toward low-toxicity products. Conversely, high-carbon/low-HOMO pollutants contain dispersed electron-rich and electron-deficient moieties, requiring •OH/O2•--dominated oxidation to limit pathway branching and drive transformation to lower predicted toxicity. These findings provide a model-guided basis for identifying catalyst-condition combinations associated with lower predicted toxicity within the represented chemical space.

View source

Similar papers

Nov 2026

Interpretable Machine-Learning Prediction of Pollutant Adsorption and Degradation by MnO2 in Aqueous Systems

Manganese dioxide (MnO2) is a key redox-active mineral governing pollutant migration and transformation, making quantitative prediction of MnO2–pollutant interactions essential for evaluating contaminant fate. Here, we compiled two data sets covering MnO2 adsorption and abiotic degradation across 7 MnO2 structural ca...

Xiao-Cheng Song, Jia-Ning Lin, Yi-Qing Sun et al. · 0 citations
#graph neural networks Review Open access Nov 2026

Artificial Intelligence Framework Predicts Residual Ecotoxicity During Advanced Oxidation Water Treatment

General Background Advanced oxidation processes (AOPs) efficiently degrade structurally resistant contaminants of emerging concern (CECs) in tertiary wastewater treatment. Specific Background Conventional performance metrics rely on the disappearance of the parent compound, ignoring the formation of transformation prod...

R. Abbas, E. M. Ati, Maarb Salih Al-Maoula et al. · 0 citations
#graph neural networks Review Open access Oct 2026

Quantitative Structure–Activity Relationships for Predicting Organic Contaminant Reactivity in Electrochemical Advanced Oxidation Processes: Descriptors, Kinetics, and Machine Learning Frontiers

Electrochemical advanced oxidation processes (EAOPs) have become a prominent tool in wastewater remediation of refractory organic pollutants due to their versatility and ability to generate powerful, in situ oxidant species—predominantly hydroxyl radicals (•OH). Concurrently, quantitative structure–activity relat...

M. Cerro-López, N. Vega · 0 citations
#graph neural networks Review Oct 2026

Machine Learning for NOx Abatement Catalysts: From Data and Descriptors to Predictive Models and Inverse Design

This article systematically review research on NOx catalysts from the four perspectives of data, descriptors, models, and applications, and introduces representative and transferable case studies from other materials systems to summarize the current status and methodological progress of ML in NOx abatement catalysis an...

Chao-Shu Duan, Zheng-Yuan An, Ruo-Chen Tang et al. · 0 citations
Oct 2026

Prediction and verification of emerging contaminants catalytic degradation based on machine learning and molecular fingerprint.

Faced with the increasing presence of recalcitrant emerging contaminants (ECs) in aquatic environments, the development of highly efficient and environmentally friendly treatment technologies has become particularly urgent. Density functional theory (DFT) calculations offer unparalleled value in mechanistic studies by...

Ren-Lan Liu, Jin-Tao Feng, Xue-Jie Guo et al. · 0 citations
Open access Sep 2026

Pareto Optimization of a Cobalt Carbide Catalyst for Syngas Conversion: Balancing Activity and Selectivity via Interpretable Active Learning

An active-learning (AL)-assisted machine-learning (ML) framework was developed to predict the CO conversion and light-hydrocarbon selectivity over cobalt carbide catalysts, and the predicted Pareto-optimal catalyst configurations showed good agreement with representative reported experimental catalysts.

Jia-Qing Lv, Jia-Yi Zhang, Xue Jia et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.