A multi-task deep learning neural network for predicting flammability-related properties from molecular structures-Reference-Cited by-同舟云学术

A multi-task deep learning neural network for predicting flammability-related properties from molecular structures

Published:2021 Issue:12 Volume:23 Page:4451-4465
ISSN:1463-9262
Container-title:Green Chemistry
language:en
Short-container-title:Green Chem.

Author:

Yang Ao¹²³⁴⁵^ORCID,Su Yang¹²³⁴⁶^ORCID,Wang Zihao¹²³⁴^ORCID,Jin Saimeng¹²³⁴^ORCID,Ren Jingzheng⁵⁷⁸⁴,Zhang Xiangping⁹¹⁰¹¹¹²¹³^ORCID,Shen Weifeng¹²³⁴^ORCID,Clark James H.¹⁴¹⁵¹⁶¹⁷^ORCID

Affiliation:

1. School of Chemistry and Chemical Engineering

2. Chongqing University

3. Chongqing 400044

4. China

5. Department of Industrial and Systems Engineering

6. School of Intelligent Technology and Engineering

7. The Hong Kong Polytechnic University

8. Hong Kong SAR

9. Beijing Key Laboratory of Ionic Liquids Clean Process

10. CAS Key Laboratory of Green Process and Engineering

11. Institute of Process Engineering

12. Chinese Academy of Sciences

13. Beijing

14. Green Chemistry Centre of Excellence

15. University of York

16. York YO105D

17. UK

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.

Funder

National Natural Science Foundation of China

Publisher

Royal Society of Chemistry (RSC)

Subject

Pollution,Environmental Chemistry

Link

http://pubs.rsc.org/en/content/articlepdf/2021/GC/D1GC00331C

Reference57 articles.

1. Review of Existing QSAR/QSPR Models Developed for Properties Used in Hazardous Chemicals Classification System

2. Group-contribution+ (GC+) based estimation of properties of pure components: Improved property estimation and uncertainty analysis

3. Group-contribution based property estimation and uncertainty analysis for flammability-related properties