Synergistic Acceleration of Adsorbent Material Development by DFT and ML for CO₂ Capture

Abstract The development of high‐performance solid adsorbents for CO 2 capture is crucial for reducing carbon emissions and combating climate change. Density functional theory (DFT) has been widely used to explore the adsorption mechanisms of solid adsorbents, but its computational cost limits large‐scale material screening. Machine learning (ML) as a data‐driven approach promotes materials development. This paper reviews the synergistic integration of DFT and ML in the design and development of solid amine adsorbents, metal‐organic framework materials, and calcium‐based adsorbents. With high‐quality training data generated by DFT, ML models can effectively predict material properties. In addition, the integration of ML accelerates high‐throughput screening, significantly improving the speed and accuracy of material discovery. This review summarizes recent advances and perspectives in the application of computational methods for the rational design of solid adsorbents.