aiqbench analysis
This research applies uncertainty-aware machine learning techniques, specifically Bayesian neural networks and graph neural networks, to model intrinsic properties of permanent magnets like Nd2Fe14B. By benchmarking different probabilistic methods against standard point-prediction metrics, the study demonstrates that quantifying prediction confidence is critical for reliable materials discovery in data-scarce regimes. This approach bridges computational materials science with advanced AI safety practices, ensuring that structural and compositional predictions are robust before experimental validation.
Modelling magnetic material properties with uncertainty-aware neural networks
arXiv:2606.11870v2 Announce Type: replace-cross Abstract: Machine learning is increasingly used to accelerate materials discovery across large compositional and structural design spaces, but limited and heterogeneous data make reliable uncertainty estimation essential. In this work, we investigate uncertainty quantification for permanent magnet modeling across three complementary studies. First, on a public Curie temperature surrogate dataset, we benchmark Gaussian process regression, random forest bagging, and dropout-based Bayesian neural networks and show that calibration, sharpness, and confidence curve diagnostics reveal differences in uncertainty quality that are not visible from point-prediction metrics alone. Second, we transfer this framework to the prediction of intrinsic magnetic properties in Nd2 Fe14 B-based magnets. Third, we extend the same uncertainty-aware perspective to coercivity prediction from microstructural information using a graph neural network. Together, these studies show that uncertainty quantification improves the trustworthiness of magnetic material property predictions and can be transferred from composition-based surrogate models to more complex structure-sensitive learning tasks.
Abstract:Machine learning is increasingly used to accelerate materials discovery across large compositional and structural design spaces, but limited and heterogeneous data make reliable uncertainty estimation essential. In this work, we investigate uncertainty quantification for permanent magnet modeling across three complementary studies. First, on a public Curie temperature surrogate dataset, we benchmark Gaussian process regression, random forest bagging, and dropout-based Bayesian neural networks and show that calibration, sharpness, and confidence curve diagnostics reveal differences in uncertainty quality that are not visible from point-prediction metrics alone. Second, we transfer this framework to the prediction of intrinsic magnetic properties in Nd2 Fe14 B-based magnets. Third, we extend the same uncertainty-aware perspective to coercivity prediction from microstructural information using a graph neural network. Together, these studies show that uncertainty quantification improves the trustworthiness of magnetic material property predictions and can be transferred from composition-based surrogate models to more complex structure-sensitive learning tasks.
Materials Science (cond-mat.mtrl-sci); Machine Learning (cs.LG)
arXiv:2606.11870 [cond-mat.mtrl-sci]
(or arXiv:2606.11870v2 [cond-mat.mtrl-sci] for this version)
https://doi.org/10.48550/arXiv.2606.11870 Focus to learn more arXiv-issued DOI via DataCite
https://doi.org/10.1016/j.commatsci.2026.115073 Focus to learn more DOI(s) linking to related resources
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 253 words
Related coverage
Synthesis Superintelligence: from Semiconductors to Superconductors — Periodic Labs’ Liam Fedus and Ekin Dogus Cubuk
Latent Space · Oct 8, 2026
Modelling magnetic material properties with uncertainty-aware neural networks
arXiv · Jun 12, 2026
News
Quantum Computing Report · Jul 25, 2026
Constitutive parameterized deep energy method for solid mechanics problems with random material parameters
arXiv · Oct 15, 2026