Cargando…

A machine learning-based nano-photocatalyst module for accelerating the design of Bi(2)WO(6)/MIL-53(Al) nanocomposites with enhanced photocatalytic activity

It is a great challenge to acquire novel Bi(2)WO(6)/MIL-53(Al) (BWO/MIL) nanocomposites with excellent catalytic activity by the trial-and-error method in the vast untapped synthetic space. The degradation rate of Rhodamine B dye (DR(RhB)) can be used as the main parameter to evaluate the catalytic...

Descripción completa

Detalles Bibliográficos
Autores principales: Zhai, Xiuyun, Chen, Mingtong
Formato: Online Artículo Texto
Lenguaje:English
Publicado: RSC 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10408574/
https://www.ncbi.nlm.nih.gov/pubmed/37560433
http://dx.doi.org/10.1039/d3na00122a
_version_ 1785086191512584192
author Zhai, Xiuyun
Chen, Mingtong
author_facet Zhai, Xiuyun
Chen, Mingtong
author_sort Zhai, Xiuyun
collection PubMed
description It is a great challenge to acquire novel Bi(2)WO(6)/MIL-53(Al) (BWO/MIL) nanocomposites with excellent catalytic activity by the trial-and-error method in the vast untapped synthetic space. The degradation rate of Rhodamine B dye (DR(RhB)) can be used as the main parameter to evaluate the catalytic activity of BWO/MIL nanocomposites. In this work, a machine learning-based nano-photocatalyst module was developed to speed up the design of BWO/MIL with desirable performance. Firstly, the DR(RhB) dataset was constructed, and four key features related to the synthetic conditions of BWO/MIL were filtered by the forward feature selection method based on support vector regression (SVR). Secondly, the SVR model with radical basis function for predicting the DR(RhB) of BWO/MIL was established with the key features and optimal hyperparameters. The correlation coefficients (R) between predicted and experimental DR(RhB) were 0.823 and 0.884 for leave-one-out cross-validation (LOOCV) and the external test, respectively. Thirdly, potential BWO/MIL nanocomposites with higher DR(RhB) were discovered by inverse projection, the prediction model, and virtual screening from the synthesis space. Meanwhile, an online web service (http://1.14.49.110/online_predict/BWO2) was built to share the model for predicting the DR(RhB) of BWO/MIL. Moreover, sensitivity analysis was brought into boosting the model's explainability and illustrating how the DR(RhB) of BWO/MIL changes over the four key features, respectively. The method mentioned here can provide valuable clues to develop new nanocomposites with the desired properties and accelerate the design of nano-photocatalysts.
format Online
Article
Text
id pubmed-10408574
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher RSC
record_format MEDLINE/PubMed
spelling pubmed-104085742023-08-09 A machine learning-based nano-photocatalyst module for accelerating the design of Bi(2)WO(6)/MIL-53(Al) nanocomposites with enhanced photocatalytic activity Zhai, Xiuyun Chen, Mingtong Nanoscale Adv Chemistry It is a great challenge to acquire novel Bi(2)WO(6)/MIL-53(Al) (BWO/MIL) nanocomposites with excellent catalytic activity by the trial-and-error method in the vast untapped synthetic space. The degradation rate of Rhodamine B dye (DR(RhB)) can be used as the main parameter to evaluate the catalytic activity of BWO/MIL nanocomposites. In this work, a machine learning-based nano-photocatalyst module was developed to speed up the design of BWO/MIL with desirable performance. Firstly, the DR(RhB) dataset was constructed, and four key features related to the synthetic conditions of BWO/MIL were filtered by the forward feature selection method based on support vector regression (SVR). Secondly, the SVR model with radical basis function for predicting the DR(RhB) of BWO/MIL was established with the key features and optimal hyperparameters. The correlation coefficients (R) between predicted and experimental DR(RhB) were 0.823 and 0.884 for leave-one-out cross-validation (LOOCV) and the external test, respectively. Thirdly, potential BWO/MIL nanocomposites with higher DR(RhB) were discovered by inverse projection, the prediction model, and virtual screening from the synthesis space. Meanwhile, an online web service (http://1.14.49.110/online_predict/BWO2) was built to share the model for predicting the DR(RhB) of BWO/MIL. Moreover, sensitivity analysis was brought into boosting the model's explainability and illustrating how the DR(RhB) of BWO/MIL changes over the four key features, respectively. The method mentioned here can provide valuable clues to develop new nanocomposites with the desired properties and accelerate the design of nano-photocatalysts. RSC 2023-06-06 /pmc/articles/PMC10408574/ /pubmed/37560433 http://dx.doi.org/10.1039/d3na00122a Text en This journal is © The Royal Society of Chemistry https://creativecommons.org/licenses/by-nc/3.0/
spellingShingle Chemistry
Zhai, Xiuyun
Chen, Mingtong
A machine learning-based nano-photocatalyst module for accelerating the design of Bi(2)WO(6)/MIL-53(Al) nanocomposites with enhanced photocatalytic activity
title A machine learning-based nano-photocatalyst module for accelerating the design of Bi(2)WO(6)/MIL-53(Al) nanocomposites with enhanced photocatalytic activity
title_full A machine learning-based nano-photocatalyst module for accelerating the design of Bi(2)WO(6)/MIL-53(Al) nanocomposites with enhanced photocatalytic activity
title_fullStr A machine learning-based nano-photocatalyst module for accelerating the design of Bi(2)WO(6)/MIL-53(Al) nanocomposites with enhanced photocatalytic activity
title_full_unstemmed A machine learning-based nano-photocatalyst module for accelerating the design of Bi(2)WO(6)/MIL-53(Al) nanocomposites with enhanced photocatalytic activity
title_short A machine learning-based nano-photocatalyst module for accelerating the design of Bi(2)WO(6)/MIL-53(Al) nanocomposites with enhanced photocatalytic activity
title_sort machine learning-based nano-photocatalyst module for accelerating the design of bi(2)wo(6)/mil-53(al) nanocomposites with enhanced photocatalytic activity
topic Chemistry
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10408574/
https://www.ncbi.nlm.nih.gov/pubmed/37560433
http://dx.doi.org/10.1039/d3na00122a
work_keys_str_mv AT zhaixiuyun amachinelearningbasednanophotocatalystmoduleforacceleratingthedesignofbi2wo6mil53alnanocompositeswithenhancedphotocatalyticactivity
AT chenmingtong amachinelearningbasednanophotocatalystmoduleforacceleratingthedesignofbi2wo6mil53alnanocompositeswithenhancedphotocatalyticactivity
AT zhaixiuyun machinelearningbasednanophotocatalystmoduleforacceleratingthedesignofbi2wo6mil53alnanocompositeswithenhancedphotocatalyticactivity
AT chenmingtong machinelearningbasednanophotocatalystmoduleforacceleratingthedesignofbi2wo6mil53alnanocompositeswithenhancedphotocatalyticactivity