Machine learning-guided materials and system co-design for high-pressure hydrogen compression

Cost effective and reliable hydrogen compression remains a challenging barrier in the wide-spread adoption of hydrogen as an energy carrier. The prevailing technology of mechanical compression suffers from several drawbacks, some of which can be addressed by non-mechanical compression strategies (e.g., electrochemical or metal hydride-based thermal compression). Thermally driven metal hydride compression strategies typically rely on multi-stage metal hydride-based compressors; however, discovering or optimizing low-stability metal hydrides that can pressurize hydrogen upwards of 1000 bar is difficult, both with respect to computational predictions and experimental validation. Here we (1) demonstrate that simple machine learning-derived design rules can inform rational design of alloying strategies yielding low-stability hydrides, (2) validate their experimental pressure-composition-temperature (PCT) isotherms up to 875 bar, and (3) utilize a dynamic systems-level model of a metal hydride compressor design to evaluate their performance under realistic operating conditions. Importantly, this analysis yields predicted operational efficiencies of both 2-stage (90-875 bar) and 3-stage (20-875 bar) metal hydride compressors to enable further evaluation of this technology and its techno-economic outlook.