Physics-informed active learning for accelerating quantum chemical simulations
This work addresses the challenge of accelerating quantum chemical simulations for researchers in computational chemistry, though it is incremental as it builds on existing active learning methods.
The authors tackled the problem of high effort and insufficient robustness in constructing machine learning potentials for quantum chemical simulations by introducing an end-to-end active learning protocol with physics-informed sampling, reducing simulation times from weeks to days.
Quantum chemical simulations can be greatly accelerated by constructing machine learning potentials, which is often done using active learning (AL). The usefulness of the constructed potentials is often limited by the high effort required and their insufficient robustness in the simulations. Here we introduce the end-to-end AL for constructing robust data-efficient potentials with affordable investment of time and resources and minimum human interference. Our AL protocol is based on the physics-informed sampling of training points, automatic selection of initial data, uncertainty quantification, and convergence monitoring. The versatility of this protocol is shown in our implementation of quasi-classical molecular dynamics for simulating vibrational spectra, conformer search of a key biochemical molecule, and time-resolved mechanism of the Diels-Alder reactions. These investigations took us days instead of weeks of pure quantum chemical calculations on a high-performance computing cluster. The code in MLatom and tutorials are available at https://github.com/dralgroup/mlatom.