Methodology for predicting material performance by context-based modeling: A case study on solid amine CO2 adsorbents
Shuangjun Li,
Zhixin Huang,
Yuanming Li,
Shuai Deng,
Xiangkun Elvis Cao
Affiliations
Shuangjun Li
Department of Chemical and Biological Engineering, Korea University, 145 Anam-ro, Seongbuk-gu, Seoul 02841, South Korea
Zhixin Huang
State Key Laboratory of Engines, Tianjin University, Tianjin 300350, China; International Cooperation Research Centre of Carbon Capture in Ultra-low Energy-consumption, Tianjin 300350, China
Yuanming Li
School of Electrical Engineering, Korea University, 145 Anam-ro, Seongbuk-gu, Seoul 02841, South Korea; Corresponding author.
Shuai Deng
State Key Laboratory of Engines, Tianjin University, Tianjin 300350, China; International Cooperation Research Centre of Carbon Capture in Ultra-low Energy-consumption, Tianjin 300350, China; Corresponding author at: State Key Laboratory of Engines, Tianjin University, Tianjin 300350, China.
Xiangkun Elvis Cao
Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge 02139, USA; Corresponding author.
Traditional materials informatics leverages big data and machine learning (ML) to forecast material performance based on structural features but often overlooks valuable textual information. In this work, we proposed a novel methodology for predicting material performance through context-based modeling using large language models (LLMs). This method integrates both numerical and textual information, enhancing predictive accuracy and scalability. In the case study, the approach is applied to predict the performance of solid amine CO2 adsorbents under direct air capture (DAC) conditions. ChatGPT 4o model was used to employ in-context learning to predict CO2 adsorption uptake based on input features, including material properties and experimental conditions. The results show that context-based modeling can reduce prediction error in comparison to traditional ML models in the prediction task. We adopted Sapley Additive exPlanations (SHAP) to further elucidate the importance of various input features. This work highlights the potential of LLMs in materials science, offering a cost-effective, efficient solution for complex predictive tasks.
