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

Abstract

Adsorptive hydrogen storage is a desirable technology for 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 that 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 and allows us to identify the optimal hydrogen storage temperature with the highest working capacity for a given pressure difference. Materials with high optimal temperatures are found in close proximity 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.

Recent Progress Using Solid-State Materials for Hydrogen Storage: A Short Review

“…Compared to liquid storage at cryogenic temperatures, physisorption reduces hydrogen boil-off loss during storage and consumes relatively low amounts of energy during charging and discharging [23,46]. Porous materials such as zeolites, metal-organic frameworks (MOFs), covalent organic frameworks (COFs), and carbon materials (fullerenes, nanotubes, and graphene) are the most extensively examined materials [47].…”

“…The maximum hydrogen capacity was up to 2.07 wt% for the zeolite Na-LEV (Figure 3a). In a recent study, an ideal zeolite structure for hydrogen adsorption was estimated from the meta-learning of a zeolites database with Monte Carlo simulations [47]. It reports that the RWY-type zeolite represents a hydrogen uptake of 35 g L −1 (around 7 wt%) at 100 bar and 77 K. The AWO-type zeolite had a hydrogen uptake of 10 g L −1 (around 7 wt%) at 100 bar and 77 K and 35 g L −1 (around 2 wt%) at 100 bar (Figure 4).…”

“…10, 304 4 of 19organic frameworks (COFs), and carbon materials (fullerenes, nanotubes, and graphene) are the most extensively examined materials[47].…”

“…Figure 4. (a) Hydrogen adsorption behaviors of various types of zeolites, (b,c) 3D illustrations for hydrogen adsorbed in AWO-type zeolite, and (d) hydrogen adsorption isotherms of AWO-zeolite.Reproduced from ref [47]…”

Recommendation System to Predict Missing Adsorption Properties of Nanoporous Materials

“…Loosely related, meta-learning has been used to predict an adsorption property of materials at different conditions by learning an intermediate representation of the material based only on available adsorption data. 78 N.b., recommendation systems have been built for use in chemical sciences to impute missing gas permeabilities in polymers, 79 antiviral activities of molecules, 80 and stabilities of inorganic materials. 81,82…”