Machine learning (ML) has been widely applied to chemical property prediction, most prominently for the energies and forces in molecules and materials. The strong interest in predicting energies in particular has led to a ‘local energy’-based paradigm for modern atomistic ML models, which ensures size-extensivity and a linear scaling of computational cost with system size. However, many electronic properties (such as excitation energies or ionization energies) do not necessarily scale linearly with system size and may even be spatially localized. Using size-extensive models in these cases can lead to large errors. In this work, we explore different strategies for learning intensive and localized properties, using HOMO energies in organic molecules as a representative test case. In particular, we analyze the pooling functions that atomistic neural networks use to predict molecular properties, and suggest an orbital weighted average (OWA) approach that enables the accurate prediction of orbital energies and locations.
KC acknowledges funding from the China Scholarship Council. KC is grateful for the TUM graduate school finance support to visit Bingqing Cheng's group in IST for two months. We also thankfully acknowledge computational resources provided by the MPCDF Supercomputing Centre.
Chen K, Kunkel C, Cheng B, Reuter K, Margraf JT. Physics-inspired machine learning of localized intensive properties. Chemical Science. 2023. doi:10.1039/d3sc00841j
Chen, K., Kunkel, C., Cheng, B., Reuter, K., & Margraf, J. T. (2023). Physics-inspired machine learning of localized intensive properties. Chemical Science. Royal Society of Chemistry. https://doi.org/10.1039/d3sc00841j
Chen, Ke, Christian Kunkel, Bingqing Cheng, Karsten Reuter, and Johannes T. Margraf. “Physics-Inspired Machine Learning of Localized Intensive Properties.” Chemical Science. Royal Society of Chemistry, 2023. https://doi.org/10.1039/d3sc00841j.
K. Chen, C. Kunkel, B. Cheng, K. Reuter, and J. T. Margraf, “Physics-inspired machine learning of localized intensive properties,” Chemical Science. Royal Society of Chemistry, 2023.
Chen K, Kunkel C, Cheng B, Reuter K, Margraf JT. 2023. Physics-inspired machine learning of localized intensive properties. Chemical Science.
Chen, Ke, et al. “Physics-Inspired Machine Learning of Localized Intensive Properties.” Chemical Science, Royal Society of Chemistry, 2023, doi:10.1039/d3sc00841j.
All files available under the following license(s):
Creative Commons Attribution 3.0 Unported (CC BY 3.0):
2023_ChemialScience_Chen.pdf 1.52 MB