2017/06/27 by Pavlo O. Dral, A. Owens, Alec Owens +3
Chemistry · Computer Science · Materials Science · Mathematics · Physics and Astronomy · #Ab initio #Algorithm #Artificial intelligence #Computational Drug Discovery Methods #Computer science #Crystallography and molecular interactions #Discrete mathematics #Energy (signal processing) #Kernel (algebra) #Machine Learning in Materials Science #Machine learning #Mathematics #Molecule #Physics #Quantum mechanics #Rotational–vibrational spectroscopy #Sampling (signal processing) #Set (abstract data type) #Statistics #physics.chem-ph
paper · pdf · doi:10.1063/1.4989536
published as J. Chem. Phys. 146, 244108 (2017)
openalex publication_date 2017/06/27 · arxiv created 2018/08/17 · arxiv updated 2018/08/20 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
We present an efficient approach for generating highly accurate molecular potential energy surfaces (PESs) using self-correcting, kernel ridge regression (KRR) based machine learning (ML). We introduce structure-based sampling to automatically assign nuclear configurations from a pre-defined grid to the training and prediction sets, respectively. Accurate high-level ab initio energies are required only for the points in the training set, while the energies for the remaining points are provided by the ML model with negligible computational cost. The proposed sampling procedure is shown to be superior to random sampling and also eliminates the need for training several ML models. Self-correcting machine learning has been implemented such that each additional layer corrects errors from the previous layer. The performance of our approach is demonstrated in a case study on a published high-level ab initio PES of methyl chloride with 44 819 points. The ML model is trained on sets of different sizes and then used to predict the energies for tens of thousands of nuclear configurations within seconds. The resulting datasets are utilized in variational calculations of the vibrational energy levels of CH3Cl. By using both structure-based sampling and self-correction, the size of the training set can be kept small (e.g., 10% of the points) without any significant loss of accuracy. In ab initio rovibrational spectroscopy, it is thus possible to reduce the number of computationally costly electronic structure calculations through structure-based sampling and self-correcting KRR-based machine learning by up to 90%.