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 …
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 …
particularly through machine-learning interatomic potentials (MLIPs). Unlike traditional …
Data efficient machine learning potentials for modeling catalytic reactivity via active learning and enhanced sampling
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 …
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 …
interatomic potentials (MLIPs) for atomistic simulations. In this work, we propose for sparse …
Prediction rigidities for data-driven chemistry
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 …
very important to understand how the ML models learn to correlate chemical structures with …
Orb: A Fast, Scalable Neural Network Potential
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 …
materials. Orb models are 3-6 times faster than existing universal potentials, stable under …
Neural network potential for dislocation plasticity in ceramics
Dislocations in ceramics are increasingly recognized for their promising potential in
applications such as toughening intrinsically brittle ceramics and tailoring functional …
applications such as toughening intrinsically brittle ceramics and tailoring functional …
Random sampling versus active learning algorithms for machine learning potentials of quantum liquid water
Training accurate machine learning potentials requires electronic structure data
comprehensively covering the configurational space of the system of interest. As the …
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 …
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 …
as an efficient, urgently needed complement to ab initio molecular dynamics (aiMD). By …