Extrapolation Techniques in Database Construction for Machine-Learning Potentials: Achieving Subchemical Accuracy in Sampling Conformal Funnels in Catalytic Processes.

The generated MLIPs not only predict very accurately reaction energy barriers via nudged elastic band transition state searches but also prove to be able to uncover alternative reaction paths and changes in the reaction mechanism with reduced energy barriers, reaching mechanistic transferability en par with the best physics-based models.