Fingerprinting diverse nanoporous materials for optimal hydrogen storage conditions using meta-learning

  • Yangzesheng Sun (Creator)
  • Robert F DeJaco (Creator)
  • Zhao Li (Creator)
  • Dai Tang (Creator)
  • Stephan Glante (Creator)
  • David S. Sholl (Creator)
  • Coray M. Colina (Creator)
  • Randall Q. Snurr (Creator)
  • Matthias Thommes (Creator)
  • Martin Hartmann (Creator)
  • Ilja Siepmann (Creator)



Adsorption using nanoporous materials is one of the emerging technologies for hydrogen storage in fuel cell vehicles, and efficiently identifying the optimal storage temperature requires modeling hydrogen loading as a continuous function of pressure and temperature. Using data obtained from high-throughput Monte Carlo simulations for zeolites, metal–organic frameworks, and hyper-cross-linked polymers, we develop a meta-learning model which jointly predicts the adsorption loading for multiple materials over wide ranges of pressure and temperature. Meta-learning gives higher accuracy and improved generalization compared to fitting a model separately to each material. Here, we apply the meta-learning model to identify the optimal hydrogen storage temperature with the highest working capacity for a given pressure difference. Materials with high optimal temperatures are found closer in the fingerprint space and exhibit high isosteric heats of adsorption. Our method and results provide new guidelines toward the design of hydrogen storage materials and a new route to incorporate machine learning into high-throughput materials discovery.

SorbMetaML software code, simulation and experimental data, and IPython notebooks to reproduce the results in the manuscript "Fingerprinting diverse nanoporous materials for optimal hydrogen storage conditions using meta-learning".

Funding information
Sponsorship: This research was primarily supported by the U.S. Department of Energy (DOE), Office of Basic Energy Sciences, Division of Chemical Sciences, Geosciences and Biosciences under Award DE-FG02-17ER16362. This research used resources of the Argonne Leadership Computing Facility, which is a DOE Office of Science User Facility supported under Contract DE-AC02-06CH11357. Additional computer resources were provided by the Minnesota Supercomputing Institute at the University of Minnesota, by the Partnership for an Advanced Computing Environment (PACE) at the Georgia Institute of Technology, and by the Quest high-performance computing facility at Northwestern University, which is jointly supported by the Office of the Provost, the Office for Research, and Northwestern University Information Technology. The experimental work was funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) – Project-ID 416229255 – SFB 1411. The authors thank Collin Bunner for the development of the three-site model for hydrogen and Tao Yang for help with the equation of state calculations.
Date made availableMay 19 2021
PublisherData Repository for the University of Minnesota
Date of data productionMay 17 2021

Cite this