Long-range electrostatics for machine learning interatomic potentials is easier than we thought
This addresses a key problem for researchers in materials science, chemistry, and biomolecular simulations by enabling reliable applications to interfaces, charge-transfer reactions, and polar materials, though it is incremental as it builds on existing MLIPs.
The paper tackles the limitation of long-range electrostatics in machine learning interatomic potentials by proposing the Latent Ewald Summation framework, which captures long-range interactions using Coulomb functional forms and avoids explicit training on ambiguous DFT partial charges, suggesting it is simpler and more broadly applicable than assumed.
The lack of long-range electrostatics is a key limitation of modern machine learning interatomic potentials (MLIPs), hindering reliable applications to interfaces, charge-transfer reactions, polar and ionic materials, and biomolecules. In this Perspective, we distill two design principles behind the Latent Ewald Summation (LES) framework, which can capture long-range interactions, charges, and electrical response just by learning from standard energy and force training data: (i) use a Coulomb functional form with environment-dependent charges to capture electrostatic interactions, and (ii) avoid explicit training on ambiguous density functional theory (DFT) partial charges. When both principles are satisfied, substantial flexibility remains: essentially any short-range MLIP can be augmented; charge equilibration schemes can be added when desired; dipoles and Born effective charges can be inferred or finetuned; and charge/spin-state embeddings or tensorial targets can be further incorporated. We also discuss current limitations and open challenges. Together, these minimal, physics-guided design rules suggest that incorporating long-range electrostatics into MLIPs is simpler and perhaps more broadly applicable than is commonly assumed.