从有限且噪声数据中预测金属有机框架的自旋翻转行为：基于分位数主动学习
Predicting Spin-Crossover Behavior in Metal-Organic Frameworks from Limited and Noisy Data Using Quantile Active Learning
AI总结：
通过分位数主动学习策略，从有限噪声数据中高效识别SCO MOFs，实现高置信度候选筛选。
摘要：
自旋翻转（SCO）金属有机框架（MOFs）在传感、自旋电子学和气体相关应用中具有巨大潜力，然而，在已合成的数千种MOFs中，只有极少数SCO活性示例是已知的。通过计算筛选增强的机器学习方法提供了一条强有力的途径，能够比试错实验更快地揭示这些隐藏的候选者。然而，进展受到获得准确绝热能差的计算复杂性的限制，因为这些通常需要对两种自旋状态分别进行几何优化，这一过程在技术上具有挑战性，容易出现收敛失败，并且在大规模上难以自动化。为缓解这些问题，我们引入了一种基于分位数回归树的主动学习策略，旨在在大规模化学空间中导航的同时，保持对从未放松几何结构中获得的噪声和稀缺标签的鲁棒性。在主动选择200个代表性MOFs进行电子结构评估后，一个在该数据上训练的随机森林回归器能够准确识别SCO相关候选者，尽管存在标签噪声，仍能恢复82%的真阳性，仅产生两个假阴性。将模型应用于未标记数据集，得到一个新的高置信度SCO MOFs集合，我们称之为pSCO-105。本工作表明，通过智能训练集选择，可以从有限且不完美的数据中可靠地识别自旋翻转，从而加速SCO MOFs的筛选。
英文摘要：
Spin-crossover (SCO) metal-organic frameworks (MOFs) hold great promise for sensing, spintronics, and gas-related applications, however, only a small number of SCO-active examples are known among the thousands of MOFs already synthesized. Computational screening enhanced by machine learning offers a powerful route to uncover these hidden candidates much more rapidly than trial-and-error experiments. However, progress is limited by the computational complexity of obtaining accurate adiabatic energy differences, as these typically require separate geometry optimizations for both spin states, a process that is technically challenging, prone to convergence failures, and difficult to automate at scale. To mitigate these issues, we introduce a data-efficient strategy based on Quantile Regression Tree-based Active Learning, designed to navigate large chemical spaces while remaining robust to noisy and scarce labels obtained from unrelaxed geometries. After actively selecting a 200-sized subset of representative MOFs for electronic-structure evaluation, a Random Forest regressor trained on this data accurately identifies SCO-relevant candidates despite label noise, recovering 82% of true positives with only two false negatives. Applying the model to the unlabeled dataset yields a new collection of high-confidence SCO MOFs, which we denote pSCO-105. This work shows that spin crossover can be reliably identified from limited and imperfect data through smart training-set selection, enabling accelerated screening of SCO MOFs.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
