現代工程應用正在推動定製有多功能特性的異質材料的需求。通常，這些性質取決於微觀結構。近年來，人們一直將注意力集中在對微結構敏感的設計上。這裏所說的設計就是確定能產生所需性能的定製微結構。但如何利用機器學習建立這一設計的途徑尚待深入研究。

來自美國愛荷華州立大學機械工程系的Soumik Sarkar教授和Baskar Ganapathysubramanian教授等，訓練了一種形態分類器，可將有機光伏形態和短路電流關聯到一起。他們測試了幾種深度和寬度不同的學習框架，這些學習框架可以從給定的一組形態及其標籤中學習，最後的結果發現該學習框架具有很高的準確性和F1得分。爲了區分這些同樣表現良好的模型並對它們進行排序，作者使用了兩個額外的附加度量。首先是揭示習得的結構-性質關係的概括性。他們確定了網絡架構，可以用可用的數據集概括地圖，並根據“將未看到的形態投射到已學習過的分佈上”的能力進行量化，並做出了良好的預測。其次是可解釋性。這是理解工程系統行爲的相當重要的指標。他們引入了一種稱爲DLSP(結構屬性查詢深度學習)的方法，用於從數據中學習結構-性能之間的構效關係。作者認爲這種方法可廣泛應用於各種對微結構敏感的設計問題。

該文近期發表於npj Computational Materials 5: 95 (2019)，英文標題與摘要如下，點擊https://www.nature.com/articles/s41524-019-0231-y”可以自由獲取論文PDF。

Interpretable deep learning for guided microstructure-property explorations in photovoltaics

Balaji Sesha Sarath Pokuri, Sambuddha Ghosal, Apurva Kokate, Soumik Sarkar & Baskar Ganapathysubramanian

The microstructure determines the photovoltaic performance of a thin film organic semiconductor film. The relationship between microstructure and performance is usually highly non-linear and expensive to evaluate, thus making microstructure optimization challenging. Here, we show a data-driven approach for mapping the microstructure to photovoltaic performance using deep convolutional neural networks. We characterize this approach in terms of two critical metrics, its generalizability (has it learnt a reasonable map?), and its intepretability (can it produce meaningful microstructure characteristics that influence its prediction?). A surrogate model that exhibits these two features of generalizability and intepretability is particularly useful for subsequent design exploration. We illustrate this by using the surrogate model for both manual exploration (that verifies known domain insight) as well as automated microstructure optimization. We envision such approaches to be widely applicable to a wide variety of microstructure-sensitive design problems.