Document Type
Article
Publication Date
11-2025
Publisher
Royal Society of Chemistry
Source Publication
Physical Chemistry Chemical Physics
Source ISSN
1463-9076
Abstract
Water (H2O) is one of the most abundant molecules in the universe and is found in a wide variety of astrophysical environments. Rotational transitions in H2O + H2O collisions are important for modeling environments rich in water molecules but they are computationally intractable using quantum mechanical methods. Here, we present a machine learning (ML) tool using an ensemble of neural networks (NNs) to predict cross sections to construct a database of rate coefficients for rotationally inelastic transitions in collisions of complex molecules such as water. The proposed methodology utilizes data computed with a mixed quantum-classical theory (MQCT). We illustrate that efficient ML models using NNs can be built to accurately interpolate in the space of 12 quantum numbers for rotational transitions in two asymmetric top molecules, spanning both initial and final states. We examine various architectures of data corresponding to each collision energy, symmetry of water molecules, and excitation/de-excitation rotational transitions, and optimize the training/validation data sets. Using only about 10% of the computed data for training, the NNs predict cross sections of state-to-state rotational transitions in H2O + H2O collisions with an average relative root mean squared error of 0.409. Thermally averaged cross sections, computed using the predicted state-to-state cross sections (∼90%) and the data used for training and validation (∼10%), were compared against those obtained entirely from MQCT calculations. The agreement is found to be excellent with an average percent deviation of about ∼13.5%. The methodology is robust, and thus applicable to other complex molecular systems.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Recommended Citation
Mandal, Bikramaditya; Babikov, Dmitri; Stancil, Phillip C.; Forrey, Robert C.; Krems, Roman V.; and balakrishnan, Naduvalath, "Neural Network Ensemble for Computing Cross Sections of Rotational Transitions in H2O + H2O Collisions" (2025). Chemistry Faculty Research and Publications. 1115.
https://epublications.marquette.edu/chem_fac/1115
Comments
Published version. Physical Chemistry Chemical Physics, Vol. 27, No. 23000 (November 2025). DOI. This article is © The Owner Societies. Used with permission.
This article is licensed under a Creative Commons Attribution-Non Commercial 4.0 Unported Licence. You can use material from this article in other publications without requesting further permissions from the RSC, provided that the correct acknowledgement is given and it is not used for commercial purposes.