Modelling magnetic material properties with uncertainty-aware neural networks
For materials scientists using machine learning to discover novel magnets, this work provides practical uncertainty estimation strategies to assess prediction confidence, though the results are incremental.
The paper benchmarks uncertainty quantification methods for predicting magnetic material properties, showing that Gaussian negative log-likelihood loss and dropout-based Bayesian approximation improve model reliability and are transferable across tasks.
Machine learning is increasingly applied to accelerate the discovery of novel materials by exploring large compositional and structural design spaces. Yet, the scarcity of high-quality data and the frequent need for out-of-distribution prediction introduce substantial uncertainty, making the assessment of model reliability essential. In this work, we investigate uncertainty quantification as a means to evaluate model confidence in the context of permanent magnet research. In a first study, we benchmark classical and modern machine learning models for predicting intrinsic magnetic properties, focusing on the quality of their uncertainty estimates. We apply Gaussian negative log-likelihood loss and dropout-based Bayesian approximation as practical strategies for estimating predictive uncertainty. In a second study, we transfer these architectural features for uncertainty estimation to a more complex task: predicting coercivity from microstructural information using a graph neural network. Together, these studies demonstrate that uncertainty quantification not only enhances the trustworthiness of predictions but is also transferable across different modeling tasks.