Transferable and robust machine learning model for predicting stability of Si anodes for multivalent cation batteries
Transferable and robust machine learning model for predicting stability of Si anodes for multivalent cation batteries
复制标题
DOI：
10.1007/s10853-023-08705-y
复制
发表时间：
2023-06
影响因子：
4.5
通讯作者：
Joy Datta;D. Datta;Vidushi Sharma
中科院分区：
文献类型：
--
作者：
Joy Datta;D. Datta;Vidushi Sharma
数据驱动方法已成为计算预测材料性能的关键工具。目前，由于为高精度机器学习模型生成足够的训练数据的计算要求，这些技术的价格很高。在这项研究中，我们提出了一种基于支持向量回归（SVR）的机器学习模型来预测硅（Si）-碱金属合金的稳定性，重点强调该模型对具有不同电子构型和结构的新硅合金的可转移性。我们详细说明了结构描述符的作用，赋予可转移性的模型，训练有限的数据（~ 750硅合金）来自材料项目数据库。三个流行的描述符，即X射线衍射（XRD），正弦库仑矩阵（SCM），和轨道场矩阵（OFM），评价代表硅合金。材料结构由SVR模型中的描述符表示，再加上超参数调整技术，如网格搜索CV和贝叶斯优化，以找到用于预测Si合金系统的总能量、形成能和堆积分数的最佳性能模型。这些模型在具有锂（Li）、钠（Na）、钾（K）、镁（Mg）、钙（Ca）和铝（Al）金属的Si合金上进行训练，其中Si-Na和Si-Al系统用作测试结构。我们的研究结果表明，XRD，实验衍生的表征结构，执行最可靠的描述符的总能量预测的新硅合金。该研究表明，通过定性地选择训练数据，使用超参数调整方法，并采用适当的结构描述符，可以降低稳健和准确的ML模型的数据要求。
Data-driven methodology has become a key tool in computationally predicting material properties. Currently, these techniques are priced high due to computational requirements for generating sufficient training data for high-precision machine learning models. In this study, we present a support vector regression (SVR)-based machine learning model to predict the stability of silicon (Si)–alkaline metal alloys, with a strong emphasis on the transferability of the model to new silicon alloys with different electronic configurations and structures. We elaborate on the role of the structural descriptor in imparting transferability to the model that is trained on limited data (~ 750 Si alloys) derived from the Material Project database. Three popular descriptors, namely X-ray diffraction (XRD), sine coulomb matrix (SCM), and orbital field matrix (OFM), are evaluated for representing Si alloys. The material structures are represented by descriptors in the SVR model, coupled with hyperparameter tuning techniques like Grid Search CV and Bayesian optimization, to find the best performing model for predicting total energy, formation energy and packing fraction of the Si alloy systems. The models are trained on Si alloys with lithium (Li), sodium (Na), potassium (K), magnesium (Mg), calcium (Ca), and aluminum (Al) metals, where Si–Na and Si–Al systems are used as test structures. Our results show that XRD, an experimentally derived characterization of structures, performs most reliably as a descriptor for total energy prediction of new Si alloys. The study demonstrates that by qualitatively selection of training data, using hyperparameter tuning methods, and employing appropriate structural descriptors, the data requirements for robust and accurate ML models can be reduced.