doi.org
Practical integration of machine learning into ab initio calculations and workflows: Accelerating the SCF cycle via density matrix predictions
September 2025 • P. V. Stishenko, Qian Chen, Julia Westermayr, Reinhard J. Maurer, Andrew J. Logsdail
Data-driven approaches offer great potential for accelerating ab initio electronic structure calculations of molecules and materials but their transferability is often limited due to the vast amount of data needed for training, including when addressing the need to fine-tune universal models for each specific system to be studied. Here, we demonstrate how contributions from system-specific electronic structure machine learning (ESML) models may be combined (“stitched”) to deliver density matrices of entire systems…