Download all files (5.97 MB)

Collection

Citation

Description:

This study presents a viable approach for designing eco-friendly ionic liquids (ILs) with enhanced CO2 solubility using language models, specifically GPT-2 in conjunction with SMILES-X. The GPT-2 model was fine-tuned on a relatively small, unlabeled IL dataset and subsequently used to generate diverse IL structures. SMILES-X models, trained on IL datasets labeled with CO2 solubility and eco-toxicity values, were employed to predict the properties of the generated ILs. Trends observed in the predicted IL properties were validated using density functional theory (DFT) and COSMO-RS calculations. The GPT-2 model was then fine-tuned iteratively, with the training data updated by including the top generated ILs from previous cycles. This iterative process led to a gradual improvement in the properties of the generated ILs. It was also observed, however, that continuously adding curated generated ILs to the training data eventually caused the model to produce correct but unrealistic IL structures. These findings highlight both the potential and limitations of language models in designing novel chemicals. Additionally, the CO2 adsorption capacity of a surrogate IL was experimentally measured, demonstrating the potential of this approach in advancing decarbonization technologies.

Rights:

• Creative Commons BY Attribution 4.0 International
  

Keyword: Generative model, GPT, Prediction, SMILES, Decarbonization

Date published: 2025-05-22

Publisher: Elsevier BV

Journal:

• Artificial Intelligence Chemistry (ISSN: 29497477) vol. 3 issue. 1 100089

Funding:

• International Institute for Carbon-Neutral Energy Research, Kyushu University WPI-I2CNER
• Ministry of Education, Culture, Sports, Science and Technology 251FP-22667

Manuscript type: Publisher's version (Version of record)

MDR DOI:

First published URL: https://doi.org/10.1016/j.aichem.2025.100089

Related item:

Other identifier(s):

Contact agent:

Updated at: 2025-12-10 08:30:26 +0900

Published on MDR: 2025-12-10 08:23:46 +0900