Fast, propagatable uncertainty estimates for machine learning interatomic potentials.
I work actively on uncertainty quantification (UQ) schemes for machine learning interatomic potentials (MLIPs).
I have developed the shallow ensembles scheme for neural networks: a fast, last-layer ensemble-based UQ scheme for neural-network MLIPs that yields fast yet high-quality uncertainty estimates. Because the ensemble lives only in the last layer, its uncertainties can easily be propagated through arbitrarily complex simulation workflows with very little computational overhead (Kellner & Ceriotti, 2024). A follow-up work discusses how to train such ensembles well (Schäfer et al., 2026).
More recently, we developed the PET-UAFD / PET-EXP scheme, the first universal machine learning potentials of their kind, whose predictions are calibrated against experiment and which yield uncertainty estimates not with respect to DFT but with respect to experiment (Kellner et al., 2026).
UQ schemes will make physical simulations with ML surrogate models more trustworthy. They also enable a better trade-off between more accurate and faster simulations, balancing the various error sources in atomistic simulations.
The supplementary code and data for the shallow ensemble paper are available on GitHub.
References
2026
JCTC
How to Train a Shallow Ensemble
Moritz Schäfer, Matthias Kellner, Johannes Kästner, and 1 more author
@article{schafer2026train,title={How to Train a Shallow Ensemble},author={Sch{\"a}fer, Moritz and Kellner, Matthias and K{\"a}stner, Johannes and Ceriotti, Michele},journal={Journal of Chemical Theory and Computation},volume={22},number={10},pages={4939--4950},year={2026},publisher={American Chemical Society},doi={10.1021/acs.jctc.6c00310},}
arXiv
Errors that matter: Uncertainty-aware universal machine-learning potentials calibrated on experiments
Matthias Kellner, Teitur Hansen, Thomas Bligaard, and 2 more authors
@article{kellner2026errors,title={Errors that matter: Uncertainty-aware universal machine-learning potentials calibrated on experiments},author={Kellner, Matthias and Hansen, Teitur and Bligaard, Thomas and Jacobsen, Karsten Wedel and Ceriotti, Michele},journal={arXiv preprint},year={2026},}
2024
MLST
Uncertainty quantification by direct propagation of shallow ensembles
@article{kellner2024uncertainty,title={Uncertainty quantification by direct propagation of shallow ensembles},author={Kellner, Matthias and Ceriotti, Michele},journal={Machine Learning: Science and Technology},volume={5},number={3},pages={035006},year={2024},publisher={IOP Publishing},doi={10.1088/2632-2153/ad594a},}