Prognostication of advanced CO2 capture using tunable solvents with an ensemble learning-based decision tree model

Abstract This study presents a robust method for predicting CO2 solubility in Deep Eutectic Solvents (DESs) using the stochastic gradient boosting (SGB) algorithm. DESs, promising green solvents for CO2 capture, require precise solubility data for practical applications in industrial and environment...

Full description

Saved in:
Bibliographic Details
Main Authors: Reza Soleimani, Amir Hossein Saeedi Dehaghani, Ziba Behtouei, Hamidreza Farahani, Seyyed Mohsen Hashemi
Format: Article
Language:English
Published: Nature Portfolio 2025-06-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-04318-4
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850223962558038016
author Reza Soleimani
Amir Hossein Saeedi Dehaghani
Ziba Behtouei
Hamidreza Farahani
Seyyed Mohsen Hashemi
author_facet Reza Soleimani
Amir Hossein Saeedi Dehaghani
Ziba Behtouei
Hamidreza Farahani
Seyyed Mohsen Hashemi
author_sort Reza Soleimani
collection DOAJ
description Abstract This study presents a robust method for predicting CO2 solubility in Deep Eutectic Solvents (DESs) using the stochastic gradient boosting (SGB) algorithm. DESs, promising green solvents for CO2 capture, require precise solubility data for practical applications in industrial and environmental settings. The model incorporates key parameters such as temperature, pressure, mole percent of salt and hydrogen bond donor (HBD) compounds, HBD melting points, molecular weights of salts and HBDs, and other critical factors. Using a dataset of 1951 experimental data points spanning temperatures (293.15–343.15 K) and pressures (26.3–12,730 kPa), the SGB model demonstrated excellent predictive accuracy, achieving an R2 of 0.9928 and an AARD% of 2.3107. Variable importance analysis identified pressure as the most influential factor. The model’s applicability, confirmed through William’s plot, encompassed 97.5% of data points within a safety margin, ensuring reliability, versatility, and broad applicability. Moreover, the SGB model outperformed previous methods, including ANN, RF, and thermodynamic models like PR-EoS and COSMO-RS, as validated by statistical metrics. This research highlights the SGB model’s potential as a superior and practical tool for evaluating CO2 solubility in DESs, advancing the field of green solvent development for sustainable and efficient CO2 capture technologies.
format Article
id doaj-art-2b05ddf1f63c43bf91482d0e307b2193
institution OA Journals
issn 2045-2322
language English
publishDate 2025-06-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-2b05ddf1f63c43bf91482d0e307b21932025-08-20T02:05:46ZengNature PortfolioScientific Reports2045-23222025-06-0115111910.1038/s41598-025-04318-4Prognostication of advanced CO2 capture using tunable solvents with an ensemble learning-based decision tree modelReza Soleimani0Amir Hossein Saeedi Dehaghani1Ziba Behtouei2Hamidreza Farahani3Seyyed Mohsen Hashemi4Department of Chemical Engineering, Faculty of Chemical Engineering, Tarbiat Modares UniversityDepartment of Petroleum Engineering, Faculty of Chemical Engineering, Tarbiat Modares UniversitySchool of Computing and Informatics, University of Louisiana at LafayetteDepartment of Computer Engineering, Damavand Branch, Islamic Azad UniversityDepartment of Computer Engineering, Science and Research Branch, Islamic Azad UniversityAbstract This study presents a robust method for predicting CO2 solubility in Deep Eutectic Solvents (DESs) using the stochastic gradient boosting (SGB) algorithm. DESs, promising green solvents for CO2 capture, require precise solubility data for practical applications in industrial and environmental settings. The model incorporates key parameters such as temperature, pressure, mole percent of salt and hydrogen bond donor (HBD) compounds, HBD melting points, molecular weights of salts and HBDs, and other critical factors. Using a dataset of 1951 experimental data points spanning temperatures (293.15–343.15 K) and pressures (26.3–12,730 kPa), the SGB model demonstrated excellent predictive accuracy, achieving an R2 of 0.9928 and an AARD% of 2.3107. Variable importance analysis identified pressure as the most influential factor. The model’s applicability, confirmed through William’s plot, encompassed 97.5% of data points within a safety margin, ensuring reliability, versatility, and broad applicability. Moreover, the SGB model outperformed previous methods, including ANN, RF, and thermodynamic models like PR-EoS and COSMO-RS, as validated by statistical metrics. This research highlights the SGB model’s potential as a superior and practical tool for evaluating CO2 solubility in DESs, advancing the field of green solvent development for sustainable and efficient CO2 capture technologies.https://doi.org/10.1038/s41598-025-04318-4Stochastic gradient boostingCO2 captureDeep eutectic solventsSolubilityPrediction
spellingShingle Reza Soleimani
Amir Hossein Saeedi Dehaghani
Ziba Behtouei
Hamidreza Farahani
Seyyed Mohsen Hashemi
Prognostication of advanced CO2 capture using tunable solvents with an ensemble learning-based decision tree model
Scientific Reports
Stochastic gradient boosting
CO2 capture
Deep eutectic solvents
Solubility
Prediction
title Prognostication of advanced CO2 capture using tunable solvents with an ensemble learning-based decision tree model
title_full Prognostication of advanced CO2 capture using tunable solvents with an ensemble learning-based decision tree model
title_fullStr Prognostication of advanced CO2 capture using tunable solvents with an ensemble learning-based decision tree model
title_full_unstemmed Prognostication of advanced CO2 capture using tunable solvents with an ensemble learning-based decision tree model
title_short Prognostication of advanced CO2 capture using tunable solvents with an ensemble learning-based decision tree model
title_sort prognostication of advanced co2 capture using tunable solvents with an ensemble learning based decision tree model
topic Stochastic gradient boosting
CO2 capture
Deep eutectic solvents
Solubility
Prediction
url https://doi.org/10.1038/s41598-025-04318-4
work_keys_str_mv AT rezasoleimani prognosticationofadvancedco2captureusingtunablesolventswithanensemblelearningbaseddecisiontreemodel
AT amirhosseinsaeedidehaghani prognosticationofadvancedco2captureusingtunablesolventswithanensemblelearningbaseddecisiontreemodel
AT zibabehtouei prognosticationofadvancedco2captureusingtunablesolventswithanensemblelearningbaseddecisiontreemodel
AT hamidrezafarahani prognosticationofadvancedco2captureusingtunablesolventswithanensemblelearningbaseddecisiontreemodel
AT seyyedmohsenhashemi prognosticationofadvancedco2captureusingtunablesolventswithanensemblelearningbaseddecisiontreemodel