coupled cluster – Software for Data-Intensive Applications

Multifidelity methods predict energies of organic molecules with coupled cluster accuracy

Kshema Shaju News, News April 12, 2025April 12, 2025Atmos, coupled cluster, Isomers, multi-fidelity, organic molecules, quantum chemistry, single point energies 0 Comment

V. Vinod, D. Lyu, M. Ruth, U. Kleinekathöfer, P. R. Schreiner, and P. Zaspel. Predicting molecular energies of small organic molecules with multifidelity methods. J. Comput. Chem., 46: e70056, 2025. DOI: https://doi.org/10.1002/jcc.70056; also available as chemrxiv-2024-9zz16.

Multifidelity methods for quantum chemistry (QC) is an effective machine learning (ML) tool to reduce computational costs without compromising on model accuracy. In this work, V. Vinod et al. assess the efficiency of several multifidelity methods in predicting energies of small organic molecules with coupled cluster triples (CCSD(T)) accuracy. In addition to an analysis of time-cost and model accuracy, the trained multifidelity models are used to predict CCSD(T) energies for a collection of atmospherically relevant molecules and highly conjugated molecules with high accuracy. This work is associated with the SPP 2363 on “Utilization and Development of Machine Learning for Molecular Applications – Molecular Machine Learning funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) under its special priority program scheme.

Optimal Combination with Multifidelity Machine Learning Achieves Coupled Cluster Accuracy

Kshema Shaju News, News July 22, 2024September 12, 2024atomization energies, coupled cluster, electronic structure theory, excitation energies, kernel ridge regression, machine learning, multi-fidelity 0 Comment

Vinod, V., Kleinekathöfer, U., & Zaspel, P. (2024). Optimized multifidelity machine learning for quantum chemistry. Machine Learning: Science and Technology, 5(1), 015054 http://doi.org/10.1088/2632-2153/ad2cef.

Recent research in Multifidelity Machine Learning (MFML) has resulted in ML methods that reduce the cost of generating a training set without compromising on the accuracy of the predictions. This is achieved by the combination of cheaper and less accurate data with high accuracy (or fidelity) and high cost data. In this work, a novel methodological improvement of MFML is benchmarked for various quantum chemical (QC) properties. Optimized MFML (o-MFML) performs the combination of the different fidelities of data are using an Optimal Combination method. With this improvement, it is shown that high accuracy methods such as Coupled Cluster Singlets Double (Triplet) are now more accessible that ever to the ML-QC community. The work is available in the Machine Learning: Science and Technology journal from IOPScience and is authored by Vivin Vinod, Ulrich Kleinekathöfer, and Peter Zaspel.