Journal article
ALF: Open-Source Active Learning Framework for Atomistic Modeling
Journal of chemical theory and computation
08/11/2026
DOI: 10.1021/acs.jctc.6c01122
Abstract
Machine learning interatomic potentials (MLIPs) have surged in popularity over the last two decades, with many model architectures now openly available. As data-driven models, MLIPs critically depend on high-fidelity (i.e., physically accurate) training data produced by electronic structure calculations. However, assembling large and chemically diverse datasets can be a complex and time-consuming endeavor, often requiring the manual selection of representative atomic configurations and the execution of hundreds to millions of electronic structure simulations. To address this challenge, we introduce the Active Learning Framework (ALF), an open-source Python package designed to streamline the design and deployment of MLIP training datasets on High Performance Computing resources. ALF automatically selects new configurations from undersampled regions of the potential energy surface where the MLIP exhibits high uncertainty, schedules electronic structure calculations across available computational resources, and retrains MLIPs on the fly, thereby reducing manual intervention and limiting human bias. As a demonstration, we applied ALF to generate an actively learned dataset for molten salt mixtures consisting of F, Li, Na, Be, and K atoms. An MLIP trained on this data was then employed to predict melting point, viscosity, density, radial distribution function, and specific heat, which are computationally resource-intensive to evaluate via first-principles molecular dynamics. These results were subsequently validated against experimental data. Collectively, these findings illustrate ALF’s effectiveness in compiling datasets that capture essential chemical and structural regimes, thereby virtually eliminating manual curation.
Details
- Title: Subtitle
- ALF: Open-Source Active Learning Framework for Atomistic Modeling
- Creators
- Vitor F. Grizzi - University of Illinois Urbana-ChampaignPatrick J. Lohr - Los Alamos National LaboratoryNikita Fedik - Los Alamos National LaboratorySteven Anaya - Los Alamos National LaboratoryJared Averitt - Los Alamos National LaboratoryJoseph Gomes - University of IowaYing Wai LiKipton Barros - Los Alamos National LaboratoryNicholas Lubbers - Los Alamos National LaboratoryRichard A. Messerly - Los Alamos National LaboratoryJan JanssenMaksim Kulichenko - Los Alamos National LaboratoryJustin Smith - Nvidia (United Kingdom)Sergei Tretiak - Los Alamos National LaboratoryBenjamin T. Nebgen - Los Alamos National Laboratory
- Resource Type
- Journal article
- Publication Details
- Journal of chemical theory and computation
- DOI
- 10.1021/acs.jctc.6c01122
- ISSN
- 1549-9618
- eISSN
- 1549-9626
- Publisher
- American Chemical Society
- Grant note
- Laboratory Directed Research and Development: 20240006DR Los Alamos National Laboratory: FWP LANLE8AN
This work at Los Alamos National Laboratory (LANL) is supported by the U.S. Department of Energy, Office of Basic Energy Sciences (FWP LANLE8AN) and by the Laboratory-Directed Research and Development Program (20240006DR). The work was performed in part at the Center for Nonlinear Studies (CNLS) and the Center for Integrated Nanotechnologies (CINT), a US DOE Office of Science user facility at LANL. This research used resources provided by the Los Alamos National Laboratory Institutional Computing Program, which is supported by the U.S. Department of Energy National Nuclear Security Administration under Contract No. 89233218CNA000001. We also acknowledge the CCS-7 Darwin cluster at LANL for additional computing resources. LANL is managed by Triad National Security, LLC, for the US DOE's NNSA, under Contract No. 89233218CNA000001. R.A.M. acknowledges the Oak Ridge Leadership Computing Facility at the Oak Ridge National Laboratory, which is supported by the Office of Science of the U.S. Department of Energy under Contract No. DE-AC05-00OR22725.
- Language
- English
- Electronic publication date
- 08/11/2026
- Academic Unit
- Chemical and Biochemical Engineering
- Record Identifier
- 9985218636202771
Metrics
1 Record Views