Npj Comput. Mater.: 材料生長缺失數據—如何科學找補?

知社學術圈 發佈 2024-01-29T10:14:41.800145+00:00

Bayesian optimization with experimental failure for high-throughput materials growth。

近年來,基於機器學習技術如貝葉斯優化和人工神經網絡的材料信息學得到快速發展,這也為加速材料的研究提供了嶄新的機會。缺失數據是材料信息學在分析真實材料時遇到的普遍問題,由於缺失數據在各種材料資料庫中普遍存在,如何處理缺失數據對加速材料的研發至關重要。缺失數據對優化材料生長條件也很關鍵,因為它是在生長參數空間中引起的,當由於生長參數離最佳條件很遠時將無法獲得目標材料。一種可能的解決方案是限制生長參數的搜索空間,以排除實驗失敗而導致數據缺失。然而,這就不能保證目標材料的最佳生長參數存在於此參數空間內。因此,為了最大限度地提高高通量材料生長的效益,必須在廣泛的參數範圍內進行研究,同時補充由於實驗失敗而缺失的數據。


來自日本NTT公司基礎研究所的Yuki K. Wakabayashi等,提出了一種處理材料生長中缺失數據的貝葉斯優化方法。作者通過將虛擬數據模擬和真實材料合成相結合,特別是通過機器學習輔助分子束外延生長鐵磁流體SrRuO3薄膜,來證明了這種貝葉斯優化方法的有效性。作者通過在廣泛三維參數空間中的開發和探索,僅通過運行35次MBE生長,便獲得了具有 80.1 的高殘餘電阻率的拉伸應變 SrRuO3 薄膜,這是迄今為止報導的拉伸應變 SrRuO3 薄膜中最高的,同時也補充了缺失數據。該工作提出的方法為假設實驗失敗的多維參數範圍內提供了一種靈活的優化算法,這將提高高通量材料生長和自主材料生長的效率,同時在各種材料的生長中發揮重要作用。


該文近期發表於npj Computational Materials 8:180(2022),英文標題與摘要如下,原文連結:https://www.nature.com/articles/s41524-022-00859-8



Bayesian optimization with experimental failure for high-throughput materials growth


Yuki K. Wakabayashi, Takuma Otsuka, Yoshiharu Krockenberger, Hiroshi Sawada, Yoshitaka Taniyasu & Hideki Yamamoto


A crucial problem in achieving innovative high-throughput materials growth with machine learning, such as Bayesian optimization (BO), and automation techniques has been a lack of an appropriate way to handle missing data due to experimental failures. Here, we propose a BO algorithm that complements the missing data in optimizing materials growth parameters. The proposed method provides a flexible optimization algorithm that searches a wide multi-dimensional parameter space. We demonstrate the effectiveness of the method with simulated data as well as in its implementation for actual materials growth, namely machine-learning-assisted molecular beam epitaxy (ML-MBE) of SrRuO3, which is widely used as a metallic electrode in oxide electronics. Through the exploitation and exploration in a wide three-dimensional parameter space, while complementing the missing data, we attained tensile-strained SrRuO3 film with a high residual resistivity ratio of 80.1, the highest among tensile-strained SrRuO3 films ever reported, in only 35 MBE growth runs.


關鍵字: