Symbolic regression in materials science
Symbolic regression in materials science
复制标题
DOI：
10.1557/mrc.2019.85
复制
发表时间：
2019-09-01
影响因子：
1.9
通讯作者：
Rondinelli, James M.
中科院分区：
文献类型：
--
作者：
Wang, Yiqun;Wagner, Nicholas;Rondinelli, James M.
作者展示了符号回归作为材料研究中使用的分析方法的潜力。首先，作者简要介绍了目前国家的最先进的方法，遗传编程为基础的符号回归（GPSR），和最近的进展，符号回归技术。接下来，作者讨论了符号回归的工业应用及其在材料科学中的潜在应用。然后，作者提出了两个GPSR用例：制定一个转换动力学定律，并显示学习计划发现了著名的约翰逊-梅尔-阿夫拉米-科尔莫戈罗夫形式，并学习钙钛矿LaNiO 3中位移倾斜跃迁的朗道自由能泛函形式。最后，作者提出，材料科学家应该考虑将符号回归技术作为其他基于机器学习的回归模型的替代方案，以从数据中学习。
The authors showcase the potential of symbolic regression as an analytic method for use in materials research. First, the authors briefly describe the current state-of-the-art method, genetic programming-based symbolic regression (GPSR), and recent advances in symbolic regression techniques. Next, the authors discuss industrial applications of symbolic regression and its potential applications in materials science. The authors then present two GPSR use-cases: formulating a transformation kinetics law and showing the learning scheme discovers the well-known Johnson-Mehl-Avrami-Kolmogorov form, and learning the Landau free energy functional form for the displacive tilt transition in perovskite LaNiO3. Finally, the authors propose that symbolic regression techniques should be considered by materials scientists as an alternative to other machine learning-based regression models for learning from data.