Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
129 tokens/sec
GPT-4o
28 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

On the importance of catalyst-adsorbate 3D interactions for relaxed energy predictions (2310.06682v1)

Published 10 Oct 2023 in cs.LG

Abstract: The use of machine learning for material property prediction and discovery has traditionally centered on graph neural networks that incorporate the geometric configuration of all atoms. However, in practice not all this information may be readily available, e.g.~when evaluating the potentially unknown binding of adsorbates to catalyst. In this paper, we investigate whether it is possible to predict a system's relaxed energy in the OC20 dataset while ignoring the relative position of the adsorbate with respect to the electro-catalyst. We consider SchNet, DimeNet++ and FAENet as base architectures and measure the impact of four modifications on model performance: removing edges in the input graph, pooling independent representations, not sharing the backbone weights and using an attention mechanism to propagate non-geometric relative information. We find that while removing binding site information impairs accuracy as expected, modified models are able to predict relaxed energies with remarkably decent MAE. Our work suggests future research directions in accelerated materials discovery where information on reactant configurations can be reduced or altogether omitted.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (30)
  1. Solid state physics. Cengage Learning, 2022.
  2. Graph theory approach to high-throughput surface adsorption structure generation. The Journal of Physical Chemistry A, 123(11):2281–2285, 2019.
  3. Machine learning for molecular and materials science. Nature, 559(7715):547–555, 2018.
  4. Open catalyst 2020 (oc20) dataset and community challenges. ACS Catalysis, 11(10):6059–6072, 2021.
  5. Graph theory approach to determine configurations of multidentate and high coverage adsorbates for heterogeneous catalysis. npj Computational Materials, 6(1):79, 2020.
  6. Phast: Physics-aware, scalable, and task-specific gnns for accelerated catalyst design. arXiv preprint arXiv:2211.12020, 2022.
  7. Faenet: Frame averaging equivariant gnn for materials modeling. International Conference on Machine Learning, 2023. doi: 10.48550/arXiv.2305.05577.
  8. Gemnet-oc: developing graph neural networks for large and diverse molecular simulation datasets. arXiv preprint arXiv:2204.02782, 2022.
  9. Neural message passing for quantum chemistry. International Conference On Machine Learning, 2017.
  10. The materials project: A materials genome approach to accelerating materials innovation, apl mater. 2013.
  11. Fast and uncertainty-aware directional message passing for non-equilibrium molecules. Preprint arXiv:2011.14115, 2020.
  12. Density functional theory of electronic structure. The Journal of Physical Chemistry, 100(31):12974–12980, 1996.
  13. Ab initio molecular-dynamics simulation of the liquid-metal–amorphous-semiconductor transition in germanium. Physical Review B, 49(20):14251, 1994.
  14. Adsorbml: Accelerating adsorption energy calculations with machine learning. arXiv preprint arXiv: Arxiv-2211.16486, 2022.
  15. Matsciml: A broad, multi-task benchmark for solid-state materials modeling, 2023.
  16. The open MatSci ML toolkit: A flexible framework for machine learning in materials science. Preprint arXiv:2210.17484, 2022.
  17. Learning local equivariant representations for large-scale atomistic dynamics. Preprint arXiv:2204.05249, 2022.
  18. Structure prediction drives materials discovery. Nature Reviews Materials, 4(5):331–348, 2019.
  19. Python materials genomics (pymatgen): A robust, open-source python library for materials analysis. Computational Materials Science, 68:314–319, 2013.
  20. Reducing so (3) convolutions to so (2) for efficient equivariant gnns. arXiv preprint arXiv:2302.03655, 2023.
  21. Accelerating materials discovery using artificial intelligence, high performance computing and robotics. npj Computational Materials, 8(1):84, 2022.
  22. Schnet: A continuous-filter convolutional neural network for modeling quantum interactions. Advances in neural information processing systems, 30, 2017.
  23. MatSci-NLP: Evaluating scientific language models on materials science language tasks using text-to-schema modeling. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3621–3639, Toronto, Canada, July 2023. Association for Computational Linguistics. doi: 10.18653/v1/2023.acl-long.201. URL https://aclanthology.org/2023.acl-long.201.
  24. Active learning across intermetallics to guide discovery of electrocatalysts for co2 reduction and h2 evolution. Nature Catalysis, 1(9):696–703, 2018.
  25. Graph attention networks. arXiv preprint arXiv:1710.10903, 2017.
  26. Machine learning in materials science. InfoMat, 1(3):338–358, 2019.
  27. A compact review of molecular property prediction with graph neural networks. Drug Discovery Today: Technologies, 37:1–12, 2020.
  28. A survey on graph diffusion models: Generative ai in science for molecule, protein and material. arXiv preprint arXiv:2304.01565, 2023.
  29. Machine learning: a new paradigm in computational electrocatalysis. The Journal of Physical Chemistry Letters, 13(34):7920–7930, 2022.
  30. An introduction to electrocatalyst design using machine learning for renewable energy storage. Preprint arXiv:2010.09435, 2020.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now