Title: Accurate and Fast Geometry Optimization with Time Estimation and Method Switching

Abstract: Geometry optimization is an important task in quantum chemical calculations to analyze the characteristics of molecules. A top concern on it is a long execution time because time-consuming energy and gradient calculations are repeated across several to tens of steps. In this work, we present a scheme to estimate the execution times of geometry optimization of a target molecule at different accuracy levels (i.e., the combinations of ab initio methods and basis sets). It enables to identify the accuracy levels where geometry optimization will finish in an acceptable time. In addition, we propose a gradient-based method switching (GMS) technique that reduces the execution time by dynamically switching multiple methods during geometry optimization. Our evaluation using 46 molecules in total shows that the geometry optimization times at 20 accuracy levels are estimated with a mean error of 29.5%, and GMS reduces the execution time by up to 42.7% without affecting the accuracy of geometry optimization.