Autonomous atomistic-continuum coupling through uncertainty-aware active learning
Abstract
We develop an uncertainty-aware surrogate modeling approach for coupling an atomistic kinetic Monte Carlo (KMC) surface-chemistry solver with a continuum multi-species fluid dynamics solver across disparate physical length and time scales. The surrogate model predicts boundary mass fluxes for six species and their uncertainties, which the continuum solver monitors to automatically trigger additional KMC simulations when new training data are needed. This enables efficient multiscale coupling and maintains a user-specified level of accuracy. We demonstrate the approach for reactive halide-perovskite vapor deposition, which involves a multi-species vapor jet impinging on a reactive substrate. The KMC solver uses a DFT-calibrated energetics model that we construct as part of this work and provides net deposition and desorption rates for six species. With a conservative uncertainty threshold, the surrogate-coupled approach reproduces cumulative mass fluxes of the directly coupled approach with errors typically within 10-20%, while capturing the non-monotonic dependence of net deposition on species partial pressure. Importantly, the results show that detailed crystal structure need not be explicitly represented to predict quantities exchanged between atomistic and continuum solvers; species-resolved mass fluxes provide a sufficiently low-dimensional representation of the atomistic response. For this accuracy target, the autonomous online-learning approach reduces the number of required atomistic simulations by two to three orders of magnitude relative to direct multiscale coupling.
Related
- Atomistic Insights into MOCVD Growth of GaAs using a Closed Loop Autonomous System Combining Directed Reinforcement Learning and Kinetic Monte Carlo Simulations
- Ferroelectric Switching in ZnO/Zn1-xMgxO Heterostructures: Atomistic Insights into Interfacial Coupling and Layer Architecture
- Polaritonic self-hybridized critical coupling by Brillouin zone folding induced quasi-bound states in the continuum in bulk WS2 metasurfaces
- Study of low-frequency core-edge coupling in a tokamak: III. Core-localized MHD continuum pulsations \& distant forced reconnection
- Long-range electrostatics in atomistic machine learning: a physical perspective
BibTeX
@misc{abdulah2026autonomous,
title = {{Autonomous atomistic-continuum coupling through uncertainty-aware active learning}},
author = {Daniel Abdulah and Hariswaran Sitaraman and Ross E. Larsen and Kevin Patrick Griffin and Grace Wei and Janelle Domantay and Ethan Young and Marc T. Henry de Frahan},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.33272},
eprint = {2610.33272},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.33272},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Autonomous atomistic-continuum coupling through uncertainty-aware active learning
AU - Daniel Abdulah
AU - Hariswaran Sitaraman
AU - Ross E. Larsen
AU - Kevin Patrick Griffin
AU - Grace Wei
AU - Janelle Domantay
AU - Ethan Young
AU - Marc T. Henry de Frahan
PY - 2026
DA - 2026/10/23
PB - arXiv
DO - 10.48550/arxiv.2610.33272
UR - https://arxiv.org/abs/2610.33272
AB - We develop an uncertainty-aware surrogate modeling approach for coupling an atomistic kinetic Monte Carlo (KMC) surface-chemistry solver with a continuum multi-species fluid dynamics solver across disparate physical length and time scales. The surrogate model predicts boundary mass fluxes for six species and their uncertainties, which the continuum solver monitors to automatically trigger additional KMC simulations when new training data are needed. This enables efficient multiscale coupling and maintains a user-specified level of accuracy. We demonstrate the approach for reactive halide-perovskite vapor deposition, which involves a multi-species vapor jet impinging on a reactive substrate. The KMC solver uses a DFT-calibrated energetics model that we construct as part of this work and provides net deposition and desorption rates for six species. With a conservative uncertainty threshold, the surrogate-coupled approach reproduces cumulative mass fluxes of the directly coupled approach with errors typically within 10-20%, while capturing the non-monotonic dependence of net deposition on species partial pressure. Importantly, the results show that detailed crystal structure need not be explicitly represented to predict quantities exchanged between atomistic and continuum solvers; species-resolved mass fluxes provide a sufficiently low-dimensional representation of the atomistic response. For this accuracy target, the autonomous online-learning approach reduces the number of required atomistic simulations by two to three orders of magnitude relative to direct multiscale coupling.
ER -