Theory-Guided Machine Learning in Materials Science

By Nicholas Wagner, James M. Rondinelli. 2016

Materials scientists are increasingly adopting the use of machine learning tools to discover hidden trends in data and make predictions. Applying concepts from data science without foreknowledge of their limitations and the unique qualities of materials data, however, could lead to errant conclusions. The differences that exist between various kinds of experimental and calculated data require careful choices of data processing and machine learning methods. Here, we outline potential pitfalls involved in using machine learning without robust protocols. We address some problems of overfitting to training data using decision trees as an example, rational descriptor selection in the field of perovskites, and preserving physical interpretability in the application of dimensionality reducing techniques such as principal component analysis. We show how proceeding without the guidance of domain knowledge can lead to both quantitatively and qualitatively incorrect predictive models.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Theory-Guided Data Science: A New Paradigm for Scientific Discovery from Data (2016, background): “For example, while predicting the elastic modulus using bond energy and melting point, Lasso may favor melting point over bond energy even though a direct causal link exists between bond energy and the modulus [31].”
The promise of implementing machine learning in earthquake engineering: A state-of-the-art review (2020, background): “As previously investigated in diverse disciplines (Faghmous and Kumar, 2014; Fischer et al., 2006; Wagner and Rondinelli, 2016), theory-guided ML can be developed through a variety of approaches (Karpatne et al., 2017).”
Digital Twin: Values, Challenges and Enablers From a Modeling Perspective (2019, unknown): “[367] N.”
Physics-Informed Neural Network for Modelling the Thermochemical Curing Process of Composite-Tool Systems During Manufacture (2020, background): “This theory-guided machine learning approach [20–23] requires a significant amount of training data from expensive high-fidelity simulations.”
A Physics-Informed Machine Learning Approach for Solving Heat Transfer Equation in Advanced Manufacturing and Engineering Applications (2020, methodology): “5 - Theory-guided ML models trained using a combination of governing physical laws, numerical data and physical data: It has been shown that by combining several data streams, and designing architecture and features of ML models based on governing physical laws, some limitations of previous approach”