Short-Range Δ-Machine Learning: A Cost-Efficient Strategy to Transfer Chemical Accuracy to Condensed Phase Systems

BB Mészáros and A Szabó and J Daru, JOURNAL OF CHEMICAL THEORY AND COMPUTATION, 21, 5372-5381 (2025).

DOI: 10.1021/acs.jctc.5c00367

DFT-based machine-learning potentials (MLPs) are now routinely trained for condensed-phase systems, but surpassing DFT accuracy remains challenging due to the cost or unavailability of periodic reference calculations. Our previous work () demonstrated that high-accuracy periodic MLPs can be trained within the CCMD framework using extended yet finite reference calculations. Here, we introduce short-range Delta- Machine Learning (sr Delta ML), a method that starts from a baseline MLP trained on low-level periodic data and adds a Delta-MLP correction based on high-level cluster calculations at the CC level. Applied to liquid water, sr Delta ML reduces the required cluster size from (H2O)64 to (H2O)15 and significantly lowers the number of clusters needed, resulting in a 50-200x reduction in computational cost. The resulting potential closely reproduces the target CC potential and accurately captures both two- and three-body structural descriptors.

Return to Publications page