arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2501.05903cond-mat.mtrl-scics.LGphysics.comp-ph
收藏

通过机器学习材料空间发现可持续能源材料

Discovery of sustainable energy materials via the machine-learned material space

Institute of Physics(物理研究所);Institute of Micro- and Nanotechnologies(微电子与纳米技术研究所)

Malte Grunert, Max Großmann, Erich Runge

AI总结:

本文提出通过机器学习模型发现可持续能源材料,展示了OptiMate模型在预测材料光学性质和发现可持续替代材料方面的应用。

摘要:

机器学习模型是否真的能够理解材料空间?我们以OptiMate模型为例,该模型是一个图注意力网络,用于预测半导体和绝缘体的光学性质。通过应用UMAP降维技术对其潜在嵌入进行处理,我们证明该模型能够捕捉到材料空间的细致且可解释的表示,反映了化学和物理原理,而无需任何用户引入的偏见。这使得基于光学性质和化学相似性对近10000种材料进行聚类成为可能。此外,我们展示了如何利用学习到的材料空间来识别能源相关技术中关键材料的更可持续替代品,例如光伏技术。这些发现展示了机器学习模型在材料科学中的双重用途:准确预测材料性质的同时,提供对材料空间的见解。该方法展示了利用学习材料空间进行发现和设计材料的更大潜力,并可轻松应用于任何最先进的机器学习模型。

英文摘要:

Does a machine learning model actually gain an understanding of the material space? We answer this question in the affirmative on the example of the OptiMate model, a graph attention network trained to predict the optical properties of semiconductors and insulators. By applying the UMAP dimensionality reduction technique to its latent embeddings, we demonstrate that the model captures a nuanced and interpretable representation of the materials space, reflecting chemical and physical principles, without any user-induced bias. This enables clustering of almost 10,000 materials based on optical properties and chemical similarities. Beyond this understanding, we demonstrate how the learned material space can be used to identify more sustainable alternatives to critical materials in energy-related technologies, such as photovoltaics. These findings demonstrate the dual utility of machine learning models in materials science: Accurately predicting material properties while providing insights into the underlying materials space. The approach demonstrates the broader potential of leveraging learned materials spaces for the discovery and design of materials for diverse applications, and is easily applicable to any state-of-the-art machine learning model.

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。

↑