| 机器学习在碳基环境功能材料领域的应用研究进展 |
| |
| 引用本文： | 刘艳彪,乔建质,尤世界.机器学习在碳基环境功能材料领域的应用研究进展[J].环境工程,2022,40(6):182-187. |
| |
| 作者姓名： | 刘艳彪 乔建质 尤世界 |
| |
| 作者单位： | 1. 东华大学 环境科学与工程学院 国家环境保护纺织工业污染防治工程技术中心, 上海 201620; |
| |
| 基金项目： | 国家自然科学基金面上项目(52170068)； |
| |
| 摘 要： | 随着环境功能材料领域产生的数据量及其数据复杂性急剧增加,高成本、长周期的传统实验手段已无法迎合目前功能材料的发展趋势。近年来迅速发展的机器学习能对数据进行深入挖掘和解析,有望为此类问题提供有效的解决方案。机器学习具备效率高、精度高等优势,有效弥补了传统"试错"方式的不足。介绍了机器学习的基本工作原理和算法,从预测理化性质、辅助微观表征和指导新型材料合成3个方面简述了机器学习在环境碳基功能材料领域中的应用研究进展,分析了机器学习在该领域的问题与挑战,展望了机器学习方法在环境碳基功能材料领域的前景与发展趋势。
|
| 关 键 词： | 机器学习 环境功能材料 性质预测 结构表征 设计合成 |
| 收稿时间： | 2022-01-17 |
RESEARCH PROGRESS ON APPLICATIONS OF MACHINE LEARNING IN CARBON-BASED ENVIRONMENTAL FUNCTIONAL MATERIALS |
| |
| Affiliation: | 1. Textile Pollution Controlling Engineering Center of the Ministry of Ecology and Environment, College of Environmental Science and Engineering, Donghua University, Shanghai 201620, China;2. Shanghai Institute of Pollution Control and Ecological Security, Shanghai 201620, China;3. State Key Laboratory of Urban Water Resource and Environment, School of Environment, Harbin Institute of Technology, Harbin 150090, China |
| |
| Abstract: | With the rapid increase in the capacity and complexity of data generated in the field of environmental functional materials,the high cost and long cycle time of traditional experimental methods can no longer meet the current trend of functional materials.The rapid development of machine learning in recent years can dig deeper and analyze the data,which provides an effective solution.Machine learning has the advantages of high efficiency and accuracy,which effectively compensates for the shortcomings of the traditional "trial and error" strategy.This paper outlines the basic working principles and algorithms of machine learning,summarizes the recent advances in machine learning in the field of carbon-based environmental functional materials (e.g.,predicting physicochemical properties,assisting structural characterization as well as guiding the synthesis of advanced functional materials),and presents the existing problems and challenges of machine learning in this field.Future perspectives of machine learning in environmental functional materials is analyzed as well. |
| |
| Keywords: | |
|
| 点击此处可从《环境工程》浏览原始摘要信息 |
|
点击此处可从《环境工程》下载全文 |
|
