Machine-learning molecular dynamics and DFT analysis of CoFe2O4 spinel stability and hydrogen recombination energetics for high-temperature thermochemical hydrogen production

Machine Learning Potential-Driven Molecular Dynamics Simulations of Dehydrogenation in Pristine and Doped MgH$_2$

Machine learning potential-driven molecular dynamics simulations (ML-MD) were employed to provide atomistic insights into the dehydrogenation kinetics of pristine and doped MgH2. Through systematic investigation of distinct surface orientations, the MgH2 (100) surface was identified as the most active low-index surface for hydrogen release. For pristine MgH2, our simulations revealed a novel H2 formation mechanism characterized by H2 generation in the subsurface region followed by diffusion to the surface for desorption, highlighting the critical role of subsurface processes beyond conventional surface-driven pathways. Comprehensive screening of 22 doping elements identified Ni as the most effective dopant. Among several descriptors, machine learning analysis identified the time-coupled Miedema electron density as the critical descriptor, underscoring the role of electronic properties. Consequently, a volcano-shaped relationship was uncovered between the intrinsic Miedema electron density ( nws ) and total hydrogen release (optimal window: 4.0<nws<5.4x10-2 e/bohr3). Dopants within this range serve a dual function: acting as thermodynamic sinks for H attraction while maintaining a balanced interaction strength to facilitate H-H coupling and H2 release. This atomistic-level validation provides strong theoretical support for the experimentally observed"hydrogen pump"effect of catalytic phases. The present study demonstrates the strong capability of ML- MD in navigating through complex catalytic mechanisms and establishing quantitative property-activity relationships, providing a robust framework for rational design of high-performance catalysts for MgH2 and other hydrogen storage materials.

Machine learning-guided discovery of γ-Al2O3 as defect-rich structural ensemble governs single-atom Pt catalysis

Charge-Density-Wave Phase Transitions in Monolayer 1T-TaS2 from Universal Machine Learning Molecular Dynamics

Charge-density-wave (CDW) phases in 1T transition-metal dichalcogenides arise from strong electron-phonon coupling and accompanying lattice instabilities. Capturing their temperature-dependent structural evolution using conventional first-principles molecular dynamics (MD) remains challenging because of the large supercells and extensive finite-temperature sampling required. Here, we combine density functional theory (DFT), universal machine-learning interatomic potentials (MLIPs), MD, and temperature-dependent effective potential phonon calculations to investigate the structural and vibrational signatures of CDW transitions in monolayer 1T-TaS2. Benchmarking against DFT displacement energies identifies UMA-s-1p1 universal machine learning potentials with sufficient accuracy for subsequent finite-temperature simulations. Our results show that large-scale MD simulations reproduce the experimentally observed phase transition sequence from the low-temperature Star-of-David (SoD) distorted structure to the high-temperature primitive hexagonal structure, as quantified by the number of Ta atoms attributed to SoDs. Heating-cooling cycles exhibit thermal hysteresis, and upon cooling, the system freezes into a multi-domain state in which {\alpha} and \b{eta} CDW chiralities nucleate independently and persist to the lowest temperatures. These findings demonstrate that carefully benchmarked universal MLIPs can provide a scalable framework for finite-temperature studies of CDW materials.

Molecular Dynamics Study of Hydrogen Release from NaH Using Machine Learning Potential

Sodium hydride (NaH) is the main by-product generated during the operation of the cold traps in a sodium-cooled fast reactor. Its thermal decomposition releases hydrogen gas, posing a safety hazard. However, understanding the atomic-scale decomposition mechanism remains challenging because conventional simulation methods are limited in the accessible length and time scales. This study developed a deep neural network potential (DP) for the NaH system using the DP-GEN active learning framework. Benchmark tests show that the DP model accurately reproduces density functional theory (DFT) reference energies, forces, equations of state, elastic properties, and phonon spectra. In particular, the DP-predicted bulk modulus and lattice constant are in good agreement with DFT results and close to experimental values, significantly outperforming the empirical ReaxFF potential. Subsequently, we conducted large-scale Deep Potential Molecular Dynamics (DPMD) simulations to investigate the thermal decomposition behavior of NaH clusters and a slab model. The simulation results reveal model-dependent thermal responses of NaH. In the original Na48H48 cluster simulation heated from 100 to 1200 K, a structural transition and disordering were observed, but no H2 formation occurred within the simulation time. In contrast, the slab model heated from 300 to 1500 K exhibited surface disordering, Na-H bond cleavage, H-H bond formation, cluster detachment, and H2 formation and release at elevated temperatures. A supplementary higher-temperature Na48H48 cluster simulation further showed cluster dissociation in the 1000–1500 K range. These results provide atomistic insight into the model- and temperature-dependent decomposition behavior of NaH and suggest that the DP model is a useful tool for studying hydrogen-related processes in alkali metal hydrides.

The structural and dynamical stability of BeF2 at finite temperatures studied by machine learning molecular dynamics.

BeF2 is a key component of fluoride coolants in molten salt reactors. The structural phase transition between its α- and β-quartz phases at high temperatures directly affects the mechanical and thermal properties. In this work, by combining first-principles calculations and machine learning molecular dynamics simulations, we systematically investigate the structural stability, elastic properties, and anharmonic lattice dynamics of BeF2 at finite temperatures. A displacive second-order phase transition from the α to the β phase driven by anharmonic effects is revealed. At low temperatures, F atoms are confined in a multi-well potential landscape, and their off-center displacements induce a multi-peak distribution of Be atoms through the Be-F network coupling. As the temperature increases, enhanced anharmonic atomic motion and dynamic averaging gradually smear out the multi-well energy barriers, releasing F atoms from their local confinement and weakening the Be-F vibrational coupling, which ultimately stabilizes the high-symmetry β phase. The high temperature β phase exhibits higher bulk and Young's moduli, indicating enhanced resistance to compression. The imaginary phonon modes present in the harmonic phonon spectrum disappear at high temperatures due to anharmonic renormalization, confirming the dynamical stability of the β phase at elevated temperatures. The temperature evolution of the phonon density of states further shows that the Be-F vibrational coupling weakens with increasing temperature, and the Be-related modes in the high-frequency region undergo red shifts and broadening, consistent with the enhanced anharmonicity and increased local disorder. This study provides a systematic theoretical basis for understanding the microscopic mechanism of the quartz-type phase transition in BeF2 and offers guidance for optimizing the high-temperature service performance of fluoride materials in molten salt reactors.

Energetically Anchored Machine-Learning Interatomic Potential Embeddings for Reliable Hydrogen Evolution Electrocatalyst Prediction.

Reliable prediction of hydrogen adsorption free energy (ΔGH) is essential for accelerating electrocatalyst discovery for the alkaline hydrogen evolution reaction (HER), yet practical machine-learning workflows remain limited by inconsistent energetic definitions, heterogeneous density functional theory (DFT) protocols, and poor out-of-distribution (OOD) generalization. Here, we present an energetically anchored machine-learning framework that integrates machine-learning interatomic potential (MLIP)-derived energetic descriptors with pretrained Crystal Hamiltonian Graph Neural Network (CHGNet) latent embeddings to predict DFT-defined hydrogen adsorption energetics across chemically diverse catalyst surfaces. The framework employs protocol-consistent single-point MLIP energy evaluation on reference geometries to construct thermodynamically aligned energetic descriptors while combining them with structural representations through gradient-boosting regression. Using curated data sets from Catalysis Hub and AQCat25 containing single-, bi-, and trimetallic adsorption systems, the embedding-augmented energetic model achieved high predictive accuracy (R2 = 0.976, MAE = 0.054 eV, RMSE = 0.105 eV) under site-level data splitting, substantially outperforming embedding-only and physicochemical-descriptor-only models. Shapley additive explanations analysis revealed a hierarchical learning mechanism in which the protocol-consistent energetic descriptor serves as the dominant thermodynamic anchor, whereas structural descriptors provide secondary refinements that improve adsorption-energy discrimination, particularly near the thermoneutral regime relevant to catalyst screening. Explicit evaluation of MLIP-only geometry workflows further demonstrated that the framework retains meaningful adsorption-energy ranking capability despite degradation introduced by MLIP-relaxed geometries. Additional OOD and transfer-learning analyses showed that predictive robustness depends strongly on the balance between compositional diversity and reference-protocol consistency. These results establish energetically anchored MLIP embeddings as an effective strategy for scalable post-DFT adsorption-energy refinement and data-efficient electrocatalyst screening while clarifying the practical limitations of MLIP-driven workflows for heterogeneous catalysis.