CAS OpenIR
A multi-task deep learning neural network for predicting flammability-related properties from molecular structures
Yang, Ao1,2; Su, Yang1,3; Wang, Zihao1; Jin, Saimeng1; Ren, Jingzheng2; Zhang, Xiangping4; Shen, Weifeng1; Clark, James H.5
2021-05-19
Source PublicationGREEN CHEMISTRY
ISSN1463-9262
Pages15
Abstract

It is significant that hazardous properties of chemicals including replacements for banned or restricted products are assessed at an early stage of product and process design. This work proposes a new strategy of modeling quantitate structure-property relationships based on multi-task deep learning for simultaneously predicting four flammability-related properties including lower and upper flammable limits, auto-ignition point temperature and flash point temperature. A multi-task deep neural network (MDNN) has been developed to extract molecular features automatically and correlate multiple properties integrating a Tree-LSTM neural network with multiple feedforward neural networks. Molecular features are encoded in molecular tree graphs, calculated and extracted without manual actions of the user or preliminary molecular descriptor calculation. Two methods, joint training and alternative training, were both employed to train the proposed MDNN, which could capture the relevant information and commonality among multiple target properties. The outlier detection and determination of applicability domain were also introduced into the evaluation of deep learning models. Since the proposed MDNN utilized data more efficiently, the finally obtained model performs better than the multi-task partial least squares model on predicting the flammability-related properties. The proposed framework of multi-task deep learning provides a promising tool to predict multiple properties without calculating descriptors.

DOI10.1039/d1gc00331c
Language英语
WOS KeywordFlash-point Temperature ; Organic-compounds ; Pure Compounds ; Models ; Limit ; Chemicals ; Air ; Descriptor ; Design
Funding ProjectNational Natural Science Foundation of China[21878028] ; Beijing Hundreds of Leading Talents Training Project of Science and Technology[Z171100001117154] ; Joint Supervision Scheme with the Chinese Mainland, Taiwan and Macao Universities - Other Chinese Mainland, Taiwan and Macao Universities[SB2S]
WOS Research AreaChemistry ; Science & Technology - Other Topics
WOS SubjectChemistry, Multidisciplinary ; Green & Sustainable Science & Technology
Funding OrganizationNational Natural Science Foundation of China ; Beijing Hundreds of Leading Talents Training Project of Science and Technology ; Joint Supervision Scheme with the Chinese Mainland, Taiwan and Macao Universities - Other Chinese Mainland, Taiwan and Macao Universities
WOS IDWOS:000655200700001
PublisherROYAL SOC CHEMISTRY
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ipe.ac.cn/handle/122111/48983
Collection中国科学院过程工程研究所
Corresponding AuthorShen, Weifeng
Affiliation1.Chongqing Univ, Sch Chem & Chem Engn, Chongqing 400044, Peoples R China
2.Hong Kong Polytech Univ, Dept Ind & Syst Engn, Hong Kong, Peoples R China
3.Chongqing Univ Sci & Technol, Sch Intelligent Technol & Engn, Chongqing 401331, Peoples R China
4.Chinese Acad Sci, Inst Proc Engn, Beijing Key Lab Ion Liquids Clean Proc, CAS Key Lab Green Proc & Engn, Beijing 100190, Peoples R China
5.Univ York, Green Chem Ctr Excellence, York YO1 05D, N Yorkshire, England
Recommended Citation
GB/T 7714
Yang, Ao,Su, Yang,Wang, Zihao,et al. A multi-task deep learning neural network for predicting flammability-related properties from molecular structures[J]. GREEN CHEMISTRY,2021:15.
APA Yang, Ao.,Su, Yang.,Wang, Zihao.,Jin, Saimeng.,Ren, Jingzheng.,...&Clark, James H..(2021).A multi-task deep learning neural network for predicting flammability-related properties from molecular structures.GREEN CHEMISTRY,15.
MLA Yang, Ao,et al."A multi-task deep learning neural network for predicting flammability-related properties from molecular structures".GREEN CHEMISTRY (2021):15.
Files in This Item:
File Name/Size DocType Version Access License
A multi-task deep le(4103KB)期刊论文出版稿限制开放CC BY-NC-SAApplication Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Yang, Ao]'s Articles
[Su, Yang]'s Articles
[Wang, Zihao]'s Articles
Baidu academic
Similar articles in Baidu academic
[Yang, Ao]'s Articles
[Su, Yang]'s Articles
[Wang, Zihao]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Yang, Ao]'s Articles
[Su, Yang]'s Articles
[Wang, Zihao]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.