Skip to Main content Skip to Navigation
Journal articles

Predicting solubility of nitrous oxide in ionic liquids using machine learning techniques and gene expression programming

Abstract : Background: - Nitrous oxide (N2O), as a potent greenhouse gas, is increasingly becoming a major multidisciplinary concern in recent years. Therefore, the removal of N2O using powerful green solvents such as ionic liquids (ILs) has turned into an attractive way to reduce the amount of N2O in the atmosphere. Methods: -The aim of this study was to establish rigorous models that can predict the solubility of N2O in various ILs. To achieve this, three advanced soft-computing methods, viz. cascaded forward neural network (CFNN), radial basis function neural network (RBFNN), and gene expression programming (GEP) were trained and tested using comprehensive experimental measurements. Significant Findings: - The obtained results demonstrated that the newly implemented models can predict the solubility of N2O in ILs with high accuracy. Besides, it was found that the CFNN model optimized using Levenberg-Marquardt (LM) algorithm was the best predictive paradigm (R2=0.9994 and RMSE=0.0047). Lastly, the Leverage technique was carried out, and the statistical validity of the newly implemented model was documented as more than 96% of data were located in the applicability realm of this paradigm.
Complete list of metadata

https://hal-univ-pau.archives-ouvertes.fr/hal-03348879
Contributor : Sylvie Blanc Connect in order to contact the contributor
Submitted on : Monday, September 20, 2021 - 10:08:22 AM
Last modification on : Tuesday, September 21, 2021 - 3:23:47 AM

Identifiers

Collections

Citation

Menad Nait Amar, Mohammed Abdelfetah Ghriga, Mohamed El Amine Ben Seghier, Hocine Ouaer. Predicting solubility of nitrous oxide in ionic liquids using machine learning techniques and gene expression programming. Journal of the Taiwan Institute of Chemical Engineers, Elsevier, 2021, ⟨10.1016/j.jtice.2021.08.042⟩. ⟨hal-03348879⟩

Share

Metrics

Record views

12