Machine-learning molecular dynamics and DFT analysis of CoFe ₂ O ₄ spinel stability and hydrogen recombination energetics for high-temperature thermochemical hydrogen production

This study examines the structural stability of CoFe2O4 and the energetics of Langmuir–Hinshelwood recombinative desorption of two pre-adsorbed hydrogen atoms on the CoFe2O4 (111) surface, relevant to high-temperature thermochemical hydrogen production. A pretrained universal M3GNet graph neural-network potential is used for machine-learning molecular dynamics (MLMD), combined with surface DFT calculations at the PBE level. Two-phase MLMD simulations identify an equilibrium melting temperature of approximately 1350 K, while single-phase heating of a defect-free crystal yields an apparent transition at 1700K, interpreted as a superheating-limited upper bound. Within this solid-phase temperature window, DFT calculations show that atomic H is strongly chemisorbed on Co (Eads = −2.04 eV) and O (Eads = −4.29 eV) sites, with O-H bond lengths consistent with experiment, while molecular H₂ is only weakly physisorbed (Eads = 0.001 eV). The recombinative desorption of two co-adsorbed H atoms on adjacent Co/O sites proceeds with an activation barrier of 0.46 eV and an estimated rate of 1.6 × 1010 s−1 at 1300 K, confirming that H-H recombination is fast and is not the rate-limiting step under hydrogen-rich conditions. All DFT values are reported without an explicit Hubbard U correction and represent best feasible estimates within the present computational constraints.