Machine Learning of Potential-Energy Surfaces Within a Bond-Order Sampling Scheme
| Autor: | Sergio Rampino, Vincenzo Barone, Daniele Licari |
|---|---|
| Přispěvatelé: | Sanjay Misra, Osvaldo Gervasi, Beniamino Murgante, Elena Stankova, Vladimir Korkhov, Carmelo Torre, Ana Maria A.C. Rocha, David Taniar, Bernady O. Apduhan, Eufemia Tarantino (Eds.), Licari, D., Rampino, S., Barone, V. |
| Rok vydání: | 2019 |
| Předmět: |
010304 chemical physics
Artificial neural network Computer science Sampling (statistics) Deep learning Potential energy surface Systems modeling 010402 general chemistry 01 natural sciences Potential energy Chemical reaction Bond order Neural network Domain (mathematical analysis) 0104 chemical sciences Space reduced bond order Set (abstract data type) Machine learning 0103 physical sciences Atom Atom diatom reaction Algorithm Interpolation |
| Zdroj: | Computational Science and Its Applications – ICCSA 2019 ISBN: 9783030243104 ICCSA (6) |
| DOI: | 10.1007/978-3-030-24311-1_28 |
| Popis: | Predicting the values of the potential energy surface (PES) for a given chemical system is essential to running the associated dynamics and modeling its evolution in time. To the purpose of modeling chemical reactions involving few atoms, this task is usually accomplished by fitting or interpolating a set of energies computed at different nuclear geometries through accurate, though computationally demanding, quantum-chemical calculations. Among the several approaches for choosing an appropriate set of geometries and energies, a new scheme has been recently proposed (Rampino S, J Phys Chem A 120:4683–4692, 2016) which is based on a regular sampling in a space-reduced bond-order (SRBO) domain rather than in the more conventional bond-length (BL) domain. In this work we address the performances of four machine-learning (ML) models, as opposed to pure mathematical fitting or interpolation schemes, in predicting the PES of a three-atom system modeling an atom-diatom exchange reaction when coupled to the SRBO sampling scheme. The models (two ensemble-learning, an automated ML, and a deep-learning one), trained on both SRBO and BL datasets, are shown to perform better than popular fitting or interpolation schemes and to give the best results if coupled to SRBO data. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|