arXiv 2204.081512022-04cond-mat.mtrl-sci

固态合成条件的机器学习合理化和预测

Machine-learning rationalization and prediction of solid-state synthesis conditions

Haoyan Huo, Christopher J. Bartel, Tanjin He, Amalie Trewartha, Alexander Dunn, Bin Ouyang, Anubhav Jain, Gerbrand Ceder

发表信息：: Chemistry of Materials, 2022
DOI：: 10.1021/acs.chemmater.2c01293

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

摘要：

目前还没有定量方法来确定固态合成的合适条件。这不仅阻碍了新材料的实验实现，而且使固态反应机制的解释和理解变得复杂。在这里，我们展示了一种机器学习方法，该方法使用从科学期刊文章中挖掘的大型固态合成数据集来预测合成条件。使用特征重要性排序分析，我们发现最佳加热温度与使用熔点和形成能（$ΔG_f$，$ΔH_f$）量化的前体材料的稳定性具有强相关性。与此相反，从合成相关的反应的热力学衍生的功能没有直接相关的选择的加热温度。最佳固态加热温度和前体稳定性之间的这种相关性将塔曼规则从金属间化合物扩展到氧化物系统，表明反应动力学在确定合成条件中的重要性。加热时间与所选的实验程序和仪器设置密切相关，这可能表明数据集中的人为偏见。利用这些预测特征，我们构建了具有良好性能和普遍适用性的机器学习模型，以预测合成不同化学体系所需的条件。本工作中使用的代码和数据可以在https://github.com/CederGroupHub/s4上找到。

英文摘要：

There currently exist no quantitative methods to determine the appropriate conditions for solid-state synthesis. This not only hinders the experimental realization of novel materials but also complicates the interpretation and understanding of solid-state reaction mechanisms. Here, we demonstrate a machine-learning approach that predicts synthesis conditions using large solid-state synthesis datasets text-mined from scientific journal articles. Using feature importance ranking analysis, we discovered that optimal heating temperatures have strong correlations with the stability of precursor materials quantified using melting points and formation energies ($ΔG_f$, $ΔH_f$). In contrast, features derived from the thermodynamics of synthesis-related reactions did not directly correlate to the chosen heating temperatures. This correlation between optimal solid-state heating temperature and precursor stability extends Tamman's rule from intermetallics to oxide systems, suggesting the importance of reaction kinetics in determining synthesis conditions. Heating times are shown to be strongly correlated with the chosen experimental procedures and instrument setups, which may be indicative of human bias in the dataset. Using these predictive features, we constructed machine-learning models with good performance and general applicability to predict the conditions required to synthesize diverse chemical systems. Codes and data used in this work can be found at: https://github.com/CederGroupHub/s4.

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。

摘要：

英文摘要：

相关论文