Exploring the chemical space of ionic liquids for CO2 dissolution through generative machine learning models

For discovering uncharted chemical space of ionic liquids (ILs) for CO2 dissolution, a reliable generative framework combining re-balanced variational autoencoder (VAE), artificial neural network (ANN), and particle swarm optimization (PSO) is developed based on a comprehensive experimental solubili...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiuxian Chen, Guzhong Chen, Kunchi Xie, Jie Cheng, Jiahui Chen, Zhen Song, Zhiwen Qi
Format: Article
Language:English
Published: KeAi Communications Co. Ltd. 2025-09-01
Series:Green Chemical Engineering
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2666952824000414
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849325857312604160
author Xiuxian Chen
Guzhong Chen
Kunchi Xie
Jie Cheng
Jiahui Chen
Zhen Song
Zhiwen Qi
author_facet Xiuxian Chen
Guzhong Chen
Kunchi Xie
Jie Cheng
Jiahui Chen
Zhen Song
Zhiwen Qi
author_sort Xiuxian Chen
collection DOAJ
description For discovering uncharted chemical space of ionic liquids (ILs) for CO2 dissolution, a reliable generative framework combining re-balanced variational autoencoder (VAE), artificial neural network (ANN), and particle swarm optimization (PSO) is developed based on a comprehensive experimental solubility database from literature. The re-balanced VAE transforms the chemical space of ILs into continuous latent space, which is demonstrated by t-distributed stochastic neighbor embedding (t-SNE) visualization and sampled ions of the latent space. ANN is connected with the re-balanced VAE to predict the CO2 solubility and the resultant VAE-ANN model achieves a low mean absolute error (MAE) of 0.022 on the test set. Lastly, the PSO algorithm is employed to search the latent space for optimal IL structures with the highest predicted solubility. A total of 5120 ILs are generated and optimized through 10 parallel runs of PSO. Their CO2 solubilities are predicted and compared to those of the 3735 ILs combined with the already-known cations and anions in the CO2 solubility database under 298.15 K and 100 kPa. The results demonstrate a notably larger distribution of higher CO2 solubility in optimized ILs after PSO, which effectively points out the significance and directions for exploring the wide IL chemical space.
format Article
id doaj-art-ff42740a19f14b59a74b18f12f6c3097
institution Kabale University
issn 2666-9528
language English
publishDate 2025-09-01
publisher KeAi Communications Co. Ltd.
record_format Article
series Green Chemical Engineering
spelling doaj-art-ff42740a19f14b59a74b18f12f6c30972025-08-20T03:48:18ZengKeAi Communications Co. Ltd.Green Chemical Engineering2666-95282025-09-016333534310.1016/j.gce.2024.06.005Exploring the chemical space of ionic liquids for CO2 dissolution through generative machine learning modelsXiuxian Chen0Guzhong Chen1Kunchi Xie2Jie Cheng3Jiahui Chen4Zhen Song5Zhiwen Qi6State Key Laboratory of Chemical Engineering, School of Chemical Engineering, East China University of Science and Technology, Shanghai, 200237, ChinaState Key Laboratory of Chemical Engineering, School of Chemical Engineering, East China University of Science and Technology, Shanghai, 200237, ChinaState Key Laboratory of Chemical Engineering, School of Chemical Engineering, East China University of Science and Technology, Shanghai, 200237, ChinaState Key Laboratory of Chemical Engineering, School of Chemical Engineering, East China University of Science and Technology, Shanghai, 200237, ChinaState Key Laboratory of Chemical Engineering, School of Chemical Engineering, East China University of Science and Technology, Shanghai, 200237, ChinaCorresponding author.; State Key Laboratory of Chemical Engineering, School of Chemical Engineering, East China University of Science and Technology, Shanghai, 200237, ChinaCorresponding author.; State Key Laboratory of Chemical Engineering, School of Chemical Engineering, East China University of Science and Technology, Shanghai, 200237, ChinaFor discovering uncharted chemical space of ionic liquids (ILs) for CO2 dissolution, a reliable generative framework combining re-balanced variational autoencoder (VAE), artificial neural network (ANN), and particle swarm optimization (PSO) is developed based on a comprehensive experimental solubility database from literature. The re-balanced VAE transforms the chemical space of ILs into continuous latent space, which is demonstrated by t-distributed stochastic neighbor embedding (t-SNE) visualization and sampled ions of the latent space. ANN is connected with the re-balanced VAE to predict the CO2 solubility and the resultant VAE-ANN model achieves a low mean absolute error (MAE) of 0.022 on the test set. Lastly, the PSO algorithm is employed to search the latent space for optimal IL structures with the highest predicted solubility. A total of 5120 ILs are generated and optimized through 10 parallel runs of PSO. Their CO2 solubilities are predicted and compared to those of the 3735 ILs combined with the already-known cations and anions in the CO2 solubility database under 298.15 K and 100 kPa. The results demonstrate a notably larger distribution of higher CO2 solubility in optimized ILs after PSO, which effectively points out the significance and directions for exploring the wide IL chemical space.http://www.sciencedirect.com/science/article/pii/S2666952824000414Ionic liquidsCO2 solubilityVariational autoencoderParticle swarm optimizationChemical space exploration
spellingShingle Xiuxian Chen
Guzhong Chen
Kunchi Xie
Jie Cheng
Jiahui Chen
Zhen Song
Zhiwen Qi
Exploring the chemical space of ionic liquids for CO2 dissolution through generative machine learning models
Green Chemical Engineering
Ionic liquids
CO2 solubility
Variational autoencoder
Particle swarm optimization
Chemical space exploration
title Exploring the chemical space of ionic liquids for CO2 dissolution through generative machine learning models
title_full Exploring the chemical space of ionic liquids for CO2 dissolution through generative machine learning models
title_fullStr Exploring the chemical space of ionic liquids for CO2 dissolution through generative machine learning models
title_full_unstemmed Exploring the chemical space of ionic liquids for CO2 dissolution through generative machine learning models
title_short Exploring the chemical space of ionic liquids for CO2 dissolution through generative machine learning models
title_sort exploring the chemical space of ionic liquids for co2 dissolution through generative machine learning models
topic Ionic liquids
CO2 solubility
Variational autoencoder
Particle swarm optimization
Chemical space exploration
url http://www.sciencedirect.com/science/article/pii/S2666952824000414
work_keys_str_mv AT xiuxianchen exploringthechemicalspaceofionicliquidsforco2dissolutionthroughgenerativemachinelearningmodels
AT guzhongchen exploringthechemicalspaceofionicliquidsforco2dissolutionthroughgenerativemachinelearningmodels
AT kunchixie exploringthechemicalspaceofionicliquidsforco2dissolutionthroughgenerativemachinelearningmodels
AT jiecheng exploringthechemicalspaceofionicliquidsforco2dissolutionthroughgenerativemachinelearningmodels
AT jiahuichen exploringthechemicalspaceofionicliquidsforco2dissolutionthroughgenerativemachinelearningmodels
AT zhensong exploringthechemicalspaceofionicliquidsforco2dissolutionthroughgenerativemachinelearningmodels
AT zhiwenqi exploringthechemicalspaceofionicliquidsforco2dissolutionthroughgenerativemachinelearningmodels