EUVIMEDEUVIMED entdecken
Crossref

Two-Dimensional Energy Histograms as Features for Machine Learning to Predict Adsorption in Diverse Nanoporous Materials

Kaihang Shi iD, Zhao Li iD, Dylan M Anstine, Dai Tang, Coray M Colina iD, David S Sholl iD, J Ilja Siepmann iD, Randall Q Snurr iD

Journal of Chemical Theory and Computation · 25.07.2023 · 19 (14) · 4568-4583

DOI: 10.1021/acs.jctc.2c00798 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Chemical Theory and Computation, online erschienen am 03.02.2023. Verfasst von Kaihang Shi und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Chemical and Biological Engineering, Northwestern University, Evanston, Illinois60208, United States. Die Arbeit wurde bisher 58-mal zitiert (Crossref) und nennt 92 Literaturangaben. Gefördert von: U.S. Department of Energy, National Energy Research Scientific Computing Center, National Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

A major obstacle for machine learning (ML) in chemical science is the lack of physically informed feature representations that provide both accurate prediction and easy interpretability of the ML model. In this work, we describe adsorption systems using novel two-dimensional energy histogram (2D-EH) features, which are obtained from the probe-adsorbent energies and energy gradients at grid points located throughout the adsorbent. The 2D-EH features encode both energetic and structural information of the material and lead to highly accurate ML models (coefficient of determination R2 ∼ 0.94-0.99) for predicting single-component adsorption capacity in metal-organic frameworks (MOFs). We consider the adsorption of spherical molecules (Kr and Xe), linear alkanes with a wide range of aspect ratios (ethane, propane, n-butane, and n-hexane), and a branched alkane (2,2-dimethylbutane) over a wide range of temperatures and pressures. The interpretable 2D-EH features enable the ML model to learn the basic physics of adsorption in pores from the training data. We show that these MOF-data-trained ML models are transferrable to different families of amorphous nanoporous materials. We also identify several adsorption systems where capillary condensation occurs, and ML predictions are more challenging. Nevertheless, our 2D-EH features still outperform structural features including those derived from persistent homology. The novel 2D-EH features may help accelerate the discovery and design of advanced nanoporous materials using ML for gas storage and separation in the future.

Autor:innen und Institutionen

  • Department of Chemical and Biological Engineering, Northwestern University, Evanston, Illinois60208, United States.
  • Department of Materials Science and Engineering, University of Florida, Gainesville, Florida32611, United States.
  • George and Josephine Butler Polymer Research Laboratory, University of Florida, Gainesville, Florida32611, United States.
  • School of Chemical and Biomolecular Engineering, Georgia Institute of Technology, Atlanta, Georgia30332, United States.
  • Department of Chemistry, University of Florida, Gainesville, Florida32611, United States.
  • Transformational Decarbonization Initiative, Oak Ridge National Laboratory, Oak Ridge, Tennessee37830, United States.

ORCID-Profile: Kaihang Shi, Zhao Li, Coray M Colina, David S Sholl, J Ilja Siepmann, Randall Q Snurr

Förderung

  • U.S. Department of Energy
  • National Energy Research Scientific Computing Center
  • National Science Foundation

Zitieren

APA

Shi, K., Li, Z., Anstine, D. M., Tang, D., Colina, C. M., Sholl, D. S., Siepmann, J. I., & Snurr, R. Q. (2023). Two-Dimensional Energy Histograms as Features for Machine Learning to Predict Adsorption in Diverse Nanoporous Materials. Journal of Chemical Theory and Computation, 19(14), 4568-4583. https://doi.org/10.1021/acs.jctc.2c00798

Vancouver

Shi K, Li Z, Anstine DM, Tang D, Colina CM, Sholl DS, et al. Two-Dimensional Energy Histograms as Features for Machine Learning to Predict Adsorption in Diverse Nanoporous Materials. Journal of Chemical Theory and Computation. 2023;19(14):4568-4583. doi:10.1021/acs.jctc.2c00798

BibTeX
@article{Shi2023,
  author = {Shi, Kaihang and Li, Zhao and Anstine, Dylan M and Tang, Dai and Colina, Coray M and Sholl, David S and Siepmann, J Ilja and Snurr, Randall Q},
  title = {Two-Dimensional Energy Histograms as Features for Machine Learning to Predict Adsorption in Diverse Nanoporous Materials},
  journal = {Journal of Chemical Theory and Computation},
  year = {2023},
  volume = {19},
  number = {14},
  pages = {4568--4583},
  doi = {10.1021/acs.jctc.2c00798}
}
Kostenlos starten →