Uncertainty-biased molecular dynamics for learning uniformly accurate
interatomic potentials
- URL: http://arxiv.org/abs/2312.01416v1
- Date: Sun, 3 Dec 2023 14:39:14 GMT
- Title: Uncertainty-biased molecular dynamics for learning uniformly accurate
interatomic potentials
- Authors: Viktor Zaverkin, David Holzm\"uller, Henrik Christiansen, Federico
Errica, Francesco Alesiani, Makoto Takamoto, Mathias Niepert, and Johannes
K\"astner
- Abstract summary: Active learning (AL) uses either biased or unbiased molecular dynamics (MD) simulations to generate candidate pools.
We use the proposed uncertainty-driven AL approach to develop machine-learned interatomic potentials (MLIPs) for two benchmark systems.
MLIPs trained with the proposed data-generation method more accurately represent the relevant configurational space for both atomic systems.
- Score: 20.574068788623798
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Efficiently creating a concise but comprehensive data set for training
machine-learned interatomic potentials (MLIPs) is an under-explored problem.
Active learning (AL), which uses either biased or unbiased molecular dynamics
(MD) simulations to generate candidate pools, aims to address this objective.
Existing biased and unbiased MD simulations, however, are prone to miss either
rare events or extrapolative regions -- areas of the configurational space
where unreliable predictions are made. Simultaneously exploring both regions is
necessary for developing uniformly accurate MLIPs. In this work, we demonstrate
that MD simulations, when biased by the MLIP's energy uncertainty, effectively
capture extrapolative regions and rare events without the need to know
\textit{a priori} the system's transition temperatures and pressures.
Exploiting automatic differentiation, we enhance bias-forces-driven MD
simulations by introducing the concept of bias stress. We also employ
calibrated ensemble-free uncertainties derived from sketched gradient features
to yield MLIPs with similar or better accuracy than ensemble-based uncertainty
methods at a lower computational cost. We use the proposed uncertainty-driven
AL approach to develop MLIPs for two benchmark systems: alanine dipeptide and
MIL-53(Al). Compared to MLIPs trained with conventional MD simulations, MLIPs
trained with the proposed data-generation method more accurately represent the
relevant configurational space for both atomic systems.
Related papers
- Iterative Sizing Field Prediction for Adaptive Mesh Generation From Expert Demonstrations [49.173541207550485]
Adaptive Meshing By Expert Reconstruction (AMBER) is an imitation learning problem.
AMBER combines a graph neural network with an online data acquisition scheme to predict the projected sizing field of an expert mesh.
We experimentally validate AMBER on 2D meshes and 3D meshes provided by a human expert, closely matching the provided demonstrations and outperforming a single-step CNN baseline.
arXiv Detail & Related papers (2024-06-20T10:01:22Z) - A Multi-Grained Symmetric Differential Equation Model for Learning
Protein-Ligand Binding Dynamics [74.93549765488103]
In drug discovery, molecular dynamics simulation provides a powerful tool for predicting binding affinities, estimating transport properties, and exploring pocket sites.
We propose NeuralMD, the first machine learning surrogate that can facilitate numerical MD and provide accurate simulations in protein-ligand binding.
We show the efficiency and effectiveness of NeuralMD, with a 2000$times$ speedup over standard numerical MD simulation and outperforming all other ML approaches by up to 80% under the stability metric.
arXiv Detail & Related papers (2024-01-26T09:35:17Z) - Ensemble models outperform single model uncertainties and predictions
for operator-learning of hypersonic flows [43.148818844265236]
Training scientific machine learning (SciML) models on limited high-fidelity data offers one approach to rapidly predict behaviors for situations that have not been seen before.
High-fidelity data is itself in limited quantity to validate all outputs of the SciML model in unexplored input space.
We extend a DeepONet using three different uncertainty mechanisms: mean-variance estimation, evidential uncertainty, and ensembling.
arXiv Detail & Related papers (2023-10-31T18:07:29Z) - Forces are not Enough: Benchmark and Critical Evaluation for Machine
Learning Force Fields with Molecular Simulations [5.138982355658199]
Molecular dynamics (MD) simulation techniques are widely used for various natural science applications.
We benchmark a collection of state-of-the-art (SOTA) ML FF models and illustrate, in particular, how the commonly benchmarked force accuracy is not well aligned with relevant simulation metrics.
arXiv Detail & Related papers (2022-10-13T17:59:03Z) - Physics-informed machine learning with differentiable programming for
heterogeneous underground reservoir pressure management [64.17887333976593]
Avoiding over-pressurization in subsurface reservoirs is critical for applications like CO2 sequestration and wastewater injection.
Managing the pressures by controlling injection/extraction are challenging because of complex heterogeneity in the subsurface.
We use differentiable programming with a full-physics model and machine learning to determine the fluid extraction rates that prevent over-pressurization.
arXiv Detail & Related papers (2022-06-21T20:38:13Z) - Multi-fidelity Hierarchical Neural Processes [79.0284780825048]
Multi-fidelity surrogate modeling reduces the computational cost by fusing different simulation outputs.
We propose Multi-fidelity Hierarchical Neural Processes (MF-HNP), a unified neural latent variable model for multi-fidelity surrogate modeling.
We evaluate MF-HNP on epidemiology and climate modeling tasks, achieving competitive performance in terms of accuracy and uncertainty estimation.
arXiv Detail & Related papers (2022-06-10T04:54:13Z) - Accurate Machine Learned Quantum-Mechanical Force Fields for
Biomolecular Simulations [51.68332623405432]
Molecular dynamics (MD) simulations allow atomistic insights into chemical and biological processes.
Recently, machine learned force fields (MLFFs) emerged as an alternative means to execute MD simulations.
This work proposes a general approach to constructing accurate MLFFs for large-scale molecular simulations.
arXiv Detail & Related papers (2022-05-17T13:08:28Z) - A data-driven peridynamic continuum model for upscaling molecular
dynamics [3.1196544696082613]
We propose a learning framework to extract, from molecular dynamics data, an optimal Linear Peridynamic Solid model.
We provide sufficient well-posedness conditions for discretized LPS models with sign-changing influence functions.
This framework guarantees that the resulting model is mathematically well-posed, physically consistent, and that it generalizes well to settings that are different from the ones used during training.
arXiv Detail & Related papers (2021-08-04T07:07:47Z) - Statistical control for spatio-temporal MEG/EEG source imaging with
desparsified multi-task Lasso [102.84915019938413]
Non-invasive techniques like magnetoencephalography (MEG) or electroencephalography (EEG) offer promise of non-invasive techniques.
The problem of source localization, or source imaging, poses however a high-dimensional statistical inference challenge.
We propose an ensemble of desparsified multi-task Lasso (ecd-MTLasso) to deal with this problem.
arXiv Detail & Related papers (2020-09-29T21:17:16Z) - Automated discovery of a robust interatomic potential for aluminum [4.6028828826414925]
Machine learning (ML) based potentials aim for faithful emulation of quantum mechanics (QM) calculations at drastically reduced computational cost.
We present a highly automated approach to dataset construction using the principles of active learning (AL)
We demonstrate this approach by building an ML potential for aluminum (ANI-Al)
To demonstrate transferability, we perform a 1.3M atom shock simulation, and show that ANI-Al predictions agree very well with DFT calculations on local atomic environments sampled from the nonequilibrium dynamics.
arXiv Detail & Related papers (2020-03-10T19:06:32Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.