Interpretable Spectral Features Predict Conductivity in Self-Driving Doped Conjugated Polymer Labs
Ankush Kumar Mishra, Jacob P. Mauthe, Nicholas Luke, Aram Amassian, Baskar Ganapathysubramanian
自动驾驶实验室(SDL)通过将自动化与机器学习耦合,有望更快地发现材料,但一个核心挑战是预测从廉价、可自动化的读数中获得昂贵的、缓慢测量的属性。 我们通过从光学光谱学中学习可解释的光谱指纹来预测电导率,从而解决了掺注共轭聚合物的问题。 光学光谱是快速,非破坏性,对聚合和电荷生成敏感;我们通过将遗传算法(GA)与弯曲下区域(AUC)计算与自适应选择的光谱窗口相结合来自动化它们的功能化。 这些数据驱动的光谱特征以及处理参数用于训练将光学响应和处理与电导率联系起来的定量结构-属性关系(QSPR)。 为了提高小数据机制的准确性和可解释性,我们添加了基于域知识的功能扩展,并应用了SHAP引导的选择来保留紧凑的、物理上有意义的功能集。 该管道在无泄漏的列车/测试协议下进行评估,GA重复评估特征稳定性。 数据驱动的模型与由专家策划的描述符构建的基线的性能相匹配,同时减少实验工作(约33个)
Self-driving labs (SDLs) promise faster materials discovery by coupling automation with machine learning, but a central challenge is predicting costly, slow-to-measure properties from inexpensive, automatable readouts. We address this for doped conjugated polymers by learning interpretable spectral fingerprints from optical spectroscopy to predict electrical conductivity. Optical spectra are fast, non-destructive, and sensitive to aggregation and charge generation; we automate their featurizatio...
