| 引用本文: | 郑云哲,杨树润,谢智慧,孙鸶,何传书,赖波.数智驱动:高级氧化构效关系解析与催化体系理性构建[J].哈尔滨工业大学学报,2026,58(6):159.DOI:10.11918/202512171 |
| ZHENG Yunzhe,YANG Shurun,XIE Zhihui,SUN Si,HE Chuanshu,LAI Bo.Data intelligence drive: precise analysis of structure-activity relationships and 、rational construction of catalytic systems in advanced oxidation processes[J].Journal of Harbin Institute of Technology,2026,58(6):159.DOI:10.11918/202512171 |
|
| |
|
|
| 本文已被：浏览 1057次 下载 67次 |
码上扫一扫！ |
|
|
| 数智驱动:高级氧化构效关系解析与催化体系理性构建 |
|
郑云哲1,2,杨树润1,2,谢智慧1,2,孙鸶1,2,何传书1,2,赖波1,2
|
|
(1.四川大学 建筑与环境学院,成都 610065;2.四川大学 中德水环境与健康研究中心,成都 610065)
|
|
| 摘要: |
| 新兴污染物（emerging contaminants,ECs）的水环境风险对传统水处理技术构成严峻挑战。高级氧化技术（advanced oxidation processes,AOPs）依赖活性氧物种（reactive oxygen species,ROS）的强氧化效能,但其种类繁多、反应路径复杂且瞬态存在的特性,使得传统实验方法在系统揭示ROS生成规律、作用机制及高效催化剂构效关系方面存在瓶颈。机器学习（Machine Learning,ML）作为一种强大的数据挖掘与模式识别工具,正从根本上改变AOPs的研究范式,为这一复杂体系的精准解析与定向设计提供了前所未有的解决方案。本研究系统总结了ML在AOPs研究中的三大核心应用,即反应过程与ROS动力学的预测与优化,复杂反应途径与微观机理的深度解析,高性能催化剂的智能筛选与理性设计。内容涵盖羟基自由基（HO·）、硫酸根自由基（SO-4·）等自由基途径,以及单线态氧（1O2）、高价金属物种等非自由基体系。结果表明,ML通过整合多源数据与物理化学模型,不仅实现了对AOPs性能的准确预测与优化,更在揭示隐性构效关系、发现新描述符及预测新型催化剂方面展现出强大能力,推动了该领域从“试错法”向“理性设计”的转变。该领域的突破重点将聚焦于开发可解释性更强、融合物理机制的ML模型,并建立标准化数据库,以最终实现AOPs的智能化、定制化设计与应用。 |
| 关键词: 机器学习 新污染物 高级氧化工艺 活性氧物种 污水净化 |
| DOI：10.11918/202512171 |
| 分类号:X703 |
| 文献标识码:A |
| 基金项目:国家自然科学基金(3,5B2160,U24A20561) |
|
| Data intelligence drive: precise analysis of structure-activity relationships and 、rational construction of catalytic systems in advanced oxidation processes |
|
ZHENG Yunzhe1,2,YANG Shurun1,2,XIE Zhihui1,2,SUN Si1,2,HE Chuanshu1,2,LAI Bo1,2
|
|
(1.College of Architecture & Environment, Sichuan University, Chengdu 610065, China; 2.Sino-German Centre for Water and Health Research, Sichuan University, Chengdu 610065, China)
|
| Abstract: |
| The water environmental risks of emerging contaminants (ECs) pose a severe challenge to conventional water treatment technologies. Advanced oxidation processes (AOPs) rely on the potent oxidative efficacy of reactive oxygen species (ROS). However, their vast variety, complex reaction pathways, and transient existence cause significant bottlenecks for traditional experimental methods in systematically elucidating the generation laws and action mechanisms of ROS, as well as the structure-activity relationships of high-efficiency catalysts. As a powerful data mining and pattern recognition tool, machine learning (ML) is fundamentally changing the research paradigm of AOPs, providing unprecedented solutions for the precise analysis and targeted design of this complex system. This paper systematically summarized the three core applications of ML in AOP research, namely, the prediction and optimization of reaction processes and ROS kinetics, the deep analysis of complex reaction pathways and microscopic mechanisms, and the intelligent screening and rational design of high-performance catalysts. The content covers radical pathways such as hydroxyl radicals (HO·) and sulfate radicals (SO-4·), as well as non-radical systems such as singlet oxygen (1O2) and high-valent metal species. The results indicate that by integrating multi-source data and physicochemical models, ML not only achieves the accurate prediction and optimization of the performance of AOPs but also demonstrates strong capabilities in revealing implicit structure-activity relationships, discovering new descriptors, and predicting novel catalysts, promoting the transition of this field from "trial-and-error method" to "rational design". The focus of breakthroughs in this field will be on developing ML models with stronger interpretability and integrated physical mechanisms and establishing standardized databases to ultimately realize the intelligent and customized design and application of AOPs. |
| Key words: machine learning emerging contaminants advanced oxidation process reactive oxygen species wastewater purification |
|
|
|
|
