AI 中文总结
本研究以光催化为案例，用机器学习结合强化学习、CGCNN模型及预测器漏斗系统，设计出性能优异的新型MOFs，提升了计算效率，还揭示了关键设计模式，为多目标材料优化提供新方法。
AI 中文摘要
许多关键过程过于复杂，无法通过计算建模实现，需借助实验筛选有潜力的材料。本文提出一种材料设计方法，并以光催化作为具体案例。金属有机框架（MOFs）是极具前景的多孔纳米材料子集，应用于多种无法建模的场景。本研究采用强化学习生成60000种针对CO/H₂O选择性优化的新型MOFs，构建预测器漏斗系统，迭代剔除低分MOFs，最终得到10986种潜在候选材料，计算效率提升276%。训练后的晶体图卷积神经网络（CGCNN）模型用于预测特征，构建兼顾稳定性、催化能力、材料成本、可持续性及应用特定设计准则的适应度函数。该函数提供了模拟光催化性能的计算方法，筛选出两种符合多项合成准则的MOFs：第一种为Cr基MOF，其光催化剂评分比对照组高230%；第二种为Zn基MOF，在所有相关指标上均优于最优对照组，展现出对可变适应度函数的鲁棒性。本研究共设计20种材料，每种在该应用中比对照组性能提升125%。此外，分析揭示了金属簇N262对催化性能的显著影响等有价值的设计模式，为后续缩小化学空间提供了方法。通过纳入材料成本、稳定性等工业适用特征，本研究成功在药物递送等原本无法建模的过程中设计出具有工业前景的材料，同时开辟了比现有工作多纳入260%特征的多目标优化方法。
英文摘要
Many crucial processes are too complex for computational modeling, requiring experimentation to identify promising materials. Here, a methodology for material design is presented, while photocatalysis is presented as a specific case-study. Metal-Organic Frameworks (MOFs) are a subset of highly promising porous nanomaterials, used in a variety of unmodellable applications. Reinforcement learning generated 60,000 novel MOFs optimized for CO/H20 selectivity. A predictor funnel system was created, iteratively removing low-scoring MOFs to 10,986 potential candidates, improving computational efficiency by 276%. While trained Crystal Graph Convolutional Neural Network (CGCNN) models predicted features for creating a fitness function incorporating stability, catalytic ability, material cost, sustainability, and adsorption while allowing the inclusion of application specific design criterion. This designed function provides a computational method to model photocatalytic performance- and filtered down to two promising MOFs which each pass a myriad of synthesis criteria, first a Cr-based MOF with photocatalyst score 230% higher than the control. Second, a Zn-based MOF outperforms the best control across all relevant metrics, demonstrating robustness against variable fitness functions. This work designed 20 materials, each 125% better than the control for this application. Furthermore, analysis revealed insightful design patterns, such as the significant influence of metal cluster N262 on catalytic performance, providing a method for future work to narrow the chemical space. By incorporating industrially applicable features such as cost or stability of the material, this work successfully designs industrially promising materials in otherwise unmodellable processes such as drug delivery, while paving a method for multi-objective optimization incorporating 260% more features than prior work.
Comments8 pages, 7 figures. ISTAS 2025 Conference Paper
Journal refProc. 2025 IEEE International Symposium on Technology and Society (ISTAS), Santa Clara, CA, USA, 2025
DOI：10.1109/ISTAS65609.2025.11269612
