arXiv subjects

Xiao-Ming Cao

Publications and source records attributed to Xiao-Ming Cao.

3 recordsLinked to original sources

arXiv2026

Scalable Prediction of Complex Surface Reconstructions under Operating Conditions via Harmony-Search-Based Global Optimization

The dynamic structural evolution of catalyst surfaces under operating conditions dictates catalytic performance, yet capturing these reconstructions atomically remains challenging. Global optimization based on machine learning interatomic potentials (MLIPs) is promising, but scaling to large-scale, low-symmetry operando systems is hindered by expansive search spaces and potential energy surface (PES) inaccuracies. Herein, we present Harmony-search-based Atomic Structural Global Optimization (HASGO), a framework integrating universal MLIPs with a harmony search algorithm. HASGO overcomes the problem of PES softening by incorporating a multi-head replay fine-tuning protocol. Moreover, the stochastic structural perturbation step in its algorithm offers a fault-tolerant strategy to enhance the robustness of global convergence. These enable HASGO to identify intricate surface oxide overlayers that align with atomic-resolution microscopy, thereby resolving the square-pyramidal subsurface O5 motif on Ag(100) during ethylene epoxidation. This scalable framework provides a robust approach for uncovering operando structures, accelerating the rational design of industrial catalysts.

cond-mat.mtrl-sci↗

arXiv2026

Orbital-interaction-aware deep learning model for efficient surface chemistry simulations

Deep learning has advanced efficient chemical process simulations on the surfaces, accelerating high-throughput materials screening and rational design in heterogeneous catalysis, energy storage and conversion, and gas separation. However, the accuracy of the deep learning model generally depends on the quality of the training data. Unfortunately, precise experimental data in surface chemistry, such as adsorption energies, are scarce, while accurate quantum chemistry simulations remain computationally prohibitive for large-scale studies. Herein, we present a deep learning model of DOS Transformer for Adsorption (DOTA) for efficient surface chemistry simulations with chemical accuracy. It enables the alignment of experimental data and multi-fidelity quantum chemistry calculation data by capturing latent orbital interaction patterns based on the map between local density of states (LDOS) and adsorption energy. This minimizes the reliance on scarce high-precision training data in surface chemistry to accomplish efficient prediction of adsorption energies rivaling the high-precision experimental data, resolving the long-standing challenge of "CO puzzle". It provides a robust framework for efficient materials screening, effectively bridging the gap between computational and experimental data.

cond-mat.dis-nn↗

arXiv2025

Accelerating High-Throughput Catalyst Screening by Direct Generation of Equilibrium Adsorption Structures

The adsorption energy serves as a crucial descriptor for the large-scale screening of catalysts. Nevertheless, the limited distribution of training data for the extensively utilised machine learning interatomic potential (MLIP), predominantly sourced from near-equilibrium structures, results in unreliable adsorption structures and consequent adsorption energy predictions. In this context, we present DBCata, a deep generative model that integrates a periodic Brownian-bridge framework with an equivariant graph neural network to establish a low-dimensional transition manifold between unrelaxed and DFT-relaxed structures, without requiring explicit energy or force information. Upon training, DBCata effectively generates high-fidelity adsorption geometries, achieving an interatomic distance mean absolute error (DMAE) of 0.035 \textÅ on the Catalysis-Hub dataset, which is nearly three times superior to that of the current state-of-the-art machine learning potential models. Moreover, the corresponding DFT accuracy can be improved within 0.1 eV in 94\% of instances by identifying and refining anomalous predictions through a hybrid chemical-heuristic and self-supervised outlier detection approach. We demonstrate that the remarkable performance of DBCata facilitates accelerated high-throughput computational screening for efficient alloy catalysts in the oxygen reduction reaction, highlighting the potential of DBCata as a powerful tool for catalyst design and optimisation.

cs.LG↗