Uncertainty quantification and propagation in atomistic machine learning

J Dai, S Adhikari, M Wen - Reviews in Chemical Engineering, 2024 - degruyter.com
Abstract Machine learning (ML) offers promising new approaches to tackle complex
problems and has been increasingly adopted in chemical and materials sciences. In …

ArcaNN: automated enhanced sampling generation of training sets for chemically reactive machine learning interatomic potentials

R David, M de la Puente, A Gomez, O Anton… - Digital …, 2025 - pubs.rsc.org
The emergence of artificial intelligence is profoundly impacting computational chemistry,
particularly through machine-learning interatomic potentials (MLIPs). Unlike traditional …

Data efficient machine learning potentials for modeling catalytic reactivity via active learning and enhanced sampling

S Perego, L Bonati - npj Computational Materials, 2024 - nature.com
Simulating catalytic reactivity under operative conditions poses a significant challenge due
to the dynamic nature of the catalysts and the high computational cost of electronic structure …

Efficient ensemble uncertainty estimation in Gaussian processes regression

MPV Christiansen, N Rønne… - … Learning: Science and …, 2024 - iopscience.iop.org
Reliable uncertainty measures are required when using data-based machine learning
interatomic potentials (MLIPs) for atomistic simulations. In this work, we propose for sparse …

Prediction rigidities for data-driven chemistry

S Chong, F Bigi, F Grasselli, P Loche, M Kellner… - Faraday …, 2025 - pubs.rsc.org
The widespread application of machine learning (ML) to the chemical sciences is making it
very important to understand how the ML models learn to correlate chemical structures with …

Orb: A Fast, Scalable Neural Network Potential

M Neumann, J Gin, B Rhodes, S Bennett, Z Li… - arXiv preprint arXiv …, 2024 - arxiv.org
We introduce Orb, a family of universal interatomic potentials for atomistic modelling of
materials. Orb models are 3-6 times faster than existing universal potentials, stable under …

Neural network potential for dislocation plasticity in ceramics

S Zhang, Y Li, S Suzuki, A Nakamura… - npj Computational …, 2024 - nature.com
Dislocations in ceramics are increasingly recognized for their promising potential in
applications such as toughening intrinsically brittle ceramics and tailoring functional …

Random sampling versus active learning algorithms for machine learning potentials of quantum liquid water

N Stolte, J Daru, H Forbert, D Marx, J Behler - arXiv preprint arXiv …, 2024 - arxiv.org
Training accurate machine learning potentials requires electronic structure data
comprehensively covering the configurational space of the system of interest. As the …

Enhanced sampling of robust molecular datasets with uncertainty-based collective variables

AR Tan, JCB Dietschreit… - arXiv preprint arXiv …, 2024 - arxiv.org
Generating a data set that is representative of the accessible configuration space of a
molecular system is crucial for the robustness of machine learned interatomic potentials …

Accelerating the Training and Improving the Reliability of Machine-Learned Interatomic Potentials for Strongly Anharmonic Materials through Active Learning

K Kang, TAR Purcell, C Carbogno… - arXiv preprint arXiv …, 2024 - arxiv.org
Molecular dynamics (MD) employing machine-learned interatomic potentials (MLIPs) serve
as an efficient, urgently needed complement to ab initio molecular dynamics (aiMD). By …