arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2010.00532cond-mat.mtrl-scics.LGmath.ATphysics.comp-ph
收藏

具有持久同源性和化学词嵌入的机器学习提高了金属有机框架的预测准确性和可解释性

Machine learning with persistent homology and chemical word embeddings improves prediction accuracy and interpretability in metal-organic frameworks

Lawrence Berkeley National Laboratory(劳伦斯伯克利国家实验室);Toyota Research Institute(丰田研究院);IMDEA Materials Institute(IMDEA材料研究所)

Aditi S. Krishnapriyan, Joseph Montoya, Maciej Haranczyk, Jens Hummelshøj, Dmitriy Morozov

摘要:

机器学习已经成为材料发现的一种强大方法。它的主要挑战是选择创建可解释的材料表示的功能,在多个预测任务中有用。我们引入了一个端到端的机器学习模型,该模型自动生成描述符,以捕获材料结构和化学的复杂表示。这种方法建立在计算拓扑技术(即持久同源性)和自然语言处理的词嵌入基础上。它直接从材料系统自动封装几何和化学信息。我们通过预测不同条件下的甲烷和二氧化碳吸附,在多个纳米多孔金属有机框架数据集上展示了我们的方法。我们的研究结果表明,与从常用的手动策划特征构建的模型相比,目标之间的准确性和可转移性都有相当大的提高,始终实现均方根偏差平均降低25-30%,R2得分平均增加40-50%。我们的方法的一个关键优势是可解释性:我们的模型确定了在不同压力下与吸附最相关的孔,这有助于理解材料设计的原子级结构-性能关系。

英文摘要:

Machine learning has emerged as a powerful approach in materials discovery. Its major challenge is selecting features that create interpretable representations of materials, useful across multiple prediction tasks. We introduce an end-to-end machine learning model that automatically generates descriptors that capture a complex representation of a material's structure and chemistry. This approach builds on computational topology techniques (namely, persistent homology) and word embeddings from natural language processing. It automatically encapsulates geometric and chemical information directly from the material system. We demonstrate our approach on multiple nanoporous metal-organic framework datasets by predicting methane and carbon dioxide adsorption across different conditions. Our results show considerable improvement in both accuracy and transferability across targets compared to models constructed from the commonly-used, manually-curated features, consistently achieving an average 25-30% decrease in root-mean-squared-deviation and an average increase of 40-50% in R2 scores. A key advantage of our approach is interpretability: Our model identifies the pores that correlate best to adsorption at different pressures, which contributes to understanding atomic-level structure--property relationships for materials design.

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。

↑