Statistical information review of CO<inf>2</inf> photocatalytic reduction via bismuth-based photocatalysts using artificial neural network
Issued Date
2024-12-01
Resource Type
ISSN
11100168
Scopus ID
2-s2.0-85200231583
Journal Title
Alexandria Engineering Journal
Volume
108
Start Page
354
End Page
363
Rights Holder(s)
SCOPUS
Bibliographic Citation
Alexandria Engineering Journal Vol.108 (2024) , 354-363
Suggested Citation
Limpachanangkul P., Liu L., Nimmmanterdwong P., Pruksathorn K., Piumsomboon P., Chalermsinsuwan B. Statistical information review of CO<inf>2</inf> photocatalytic reduction via bismuth-based photocatalysts using artificial neural network. Alexandria Engineering Journal Vol.108 (2024) , 354-363. 363. doi:10.1016/j.aej.2024.07.120 Retrieved from: https://repository.li.mahidol.ac.th/handle/20.500.14594/100383
Title
Statistical information review of CO<inf>2</inf> photocatalytic reduction via bismuth-based photocatalysts using artificial neural network
Corresponding Author(s)
Other Contributor(s)
Abstract
An artificial neural network (ANN) was applied to construct the relationship between the CO2 photocatalyst variables. A total of 147 data points from 38 research publications related to photocatalytic CO2 reduction via bismuth-based photocatalysts were used to develop, validate and test the developed model. The most important variable for the yield of the obtained product is irradiation time. The longer irradiation time the higher obtained product yield. Whereas the type of main product and band gap energy had the strongest effect on product yield in the positive and negative directions, respectively, in the Pearson correlation analysis. The ANN model was successfully tested to predict other literature datasets. The ANN model can then be used to estimate the yield of the obtained product, which reflects the CO2 photocatalytic reduction efficiency.