Pin-Wen Guan
Papers
1
Total Citations
25
H-Index
1
About
Pin-Wen Guan is at the forefront of applying geometric deep learning to accelerate energy materials discovery, with a primary focus on next-generation battery electrolytes. Their landmark work, "Differentiable modeling and optimization of non-aqueous Li-based battery electrolyte solutions using geometric deep learning" (2024, 25 citations), introduces DiffM—a differentiable geometric deep learning model for chemical mixtures. This breakthrough enables end-to-end optimization of electrolyte formulations by directly predicting key properties like ionic conductivity and solvation structure, bypassing costly trial-and-error experiments. By bridging molecular geometry and machine learning, Guan's approach offers a powerful new paradigm for designing high-performance liquid electrolytes critical for lithium-ion and beyond-lithium batteries. Their research uniquely combines computational chemistry, deep learning, and materials engineering to solve pressing challenges in energy storage. With this work already gaining rapid attention, Guan is establishing themselves as a rising leader in the emerging field of differentiable materials modeling, where AI not only predicts but actively designs functional chemical systems.
Research Focus
Key Achievements
Top Papers
- 1