DeepModeling

Recently, the group of Professor Xiumin Chen at the National Engineering Research Center of Vacuum Metallurgy, Kunming University of Science and Technology, in collaboration with DP Technology, applied a new AI-driven scientific research approach (AI for Science) to implement neural-network potential molecular dynamics simulations for nanoscale simulation of complex industrial processes. They completed a three-level multi-scale simulation and validation route spanning first-principles molecular dynamics (FPMD) + Deep Potential Molecular Dynamics (DPMD) + industrial experimental verification, establishing the connection from atomic-scale dynamic behavior to experimental microstructural characterization. This reveals the intrinsic micro-mechanisms of materials at different process stages and verifies them experimentally, providing reliable support for theoretical research to guide the optimization of complex processes. Using Deep Potential Molecular Dynamics (DPMD), this work carried out atomic simulations of the entire cast-rolling and processing chain of 1xxx aluminum alloys and validated the multi-scale simulation results with industrial experiments, revealing the atomic diffusion, segregation behavior, and dislocation evolution mechanisms of 1XXX-series commercial pure aluminum across the entire cast-rolling and heat-treatment chain. The intrinsic mechanisms by which combined Ti and B additions regulate microstructure and suppress brittle intermetallic phases were clarified, providing important guidance for practical process optimization and composition design of aluminum alloy sheets.

Under reverse bias, bipolar membranes must continuously dissociate water into H⁺ and OH⁻ at the interface. Hydroxyl groups on the catalyst surface can accept or release protons, and terminal hydroxyls, bridging hydroxyls, and hydroxyls near different oxygen vacancies differ in their local structures and in how water molecules approach them. Identifying the specific sites that promote water dissociation is essential for linking surface-structure regulation to membrane voltage.

Core–shell nanostructured alloys, with their tunable electronic structures and catalytic performance, show broad application prospects in fields such as fuel cells and electrocatalysis. Among them, the Pd@Ag system, with a lattice mismatch of about 4%, serves as an ideal model for studying strain-driven structural transformations. However, traditional empirical potentials cannot accurately describe the complex atomic processes of dislocation nucleation, stacking fault evolution, and twin boundary formation in bimetallic systems, limiting an in-depth understanding of the octahedral-to-icosahedral structural transformation mechanism.

To address this challenge, Professor Chen Fuyi's group at Northwestern Polytechnical University published the study “Deep learning potential reveals surface dislocation nucleation in AgPd Nanoalloy during atomic rearrangement” in Computational Materials Science. They used a deep learning potential to perform systematic molecular dynamics simulations of the structural reconstruction of the Pd309@Ag1106 core–shell nanocluster at 500 K. The DP model was constructed via active learning using the DP-GEN workflow, with training data covering bulk, surface, and deformed configurations of pure Pd, pure Ag, and various Pd–Ag alloy phases (L10, L11, L12). The final model achieves a root-mean-square error of 4.11 meV/atom for energy and 17.8 meV/Å for forces on the validation set, in excellent agreement with DFT calculations (see Figure 1) and significantly better than traditional EAM potentials.

1. Introduction

In April 2026, a research team from the Materials Genome Institute and the School of Computer Engineering and Science at Shanghai University, together with researchers from the Department of Computer Science at the University of Tsukuba, Japan, published a research paper titled “Theoretical study of TiO₂ phase stability through DFT+U and machine learning” in the internationally renowned journal Computational Materials Science. Based on the open-source density functional theory software ABACUS, this work innovatively combines machine learning with DFT+U calculations and proposes a data-driven strategy to identify electron densities that can simultaneously match multiple experimental properties, providing a new approach to resolving the long-standing contradiction between theory and experiment in the phase stability of titanium dioxide (TiO₂).

I. Introduction

Recently, a research team from the Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, and the CAS Key Laboratory of Quantum Information, University of Science and Technology of China, published a research article titled "Enhanced shift current in GeTe/SnSe heterostructures for bulk photovoltaic effect" in the authoritative journal in the field of computational materials, npj Computational Materials.

1. Introduction

Recently, a collaborative team from Peking University, University of Science and Technology of China, Institute of Physics, and other institutions has implemented a unified heterogeneous computing framework for real-time time-dependent density functional theory (RT-TDDFT) based on numerical atomic orbitals (NAO) within the domestically developed open-source density functional theory software ABACUS. By introducing a hardware-agnostic abstraction layer into the ABACUS code, the team successfully achieved efficient cross-platform acceleration from single-node multi-core CPUs to large-scale multi-GPU architectures while keeping the physics algorithm code clean and maintainable.

Recently, the team of Likun Pan and Chenglong Wang from East China Normal University, together with the team of Jinliang Li from Jinan University, and researchers from Shanghai Maritime University and the National University of Singapore, published a research paper titled "A Quantitative Electrostatic Potential Descriptor Enables Deep Learning-Accelerated Discovery of High-Performance Lithium-Ion Battery Electrolytes" in Angewandte Chemie International Edition. The study proposes a quantitative electrostatic potential ratio descriptor, ESPratio, and combines it with a fine-tuned Uni-Mol self-supervised pre-trained model to conduct a three-tier screening of approximately 1 million PubChem molecules, yielding 353 candidate electrolyte molecules. Experimental validation further confirmed the application potential of molecules such as TBDN and PIV in high-voltage lithium-ion batteries, providing a new strategy for the rational design of high-performance electrolytes.

Accuracy Rivals Mainstream Models, Speed Surpasses Empirical Potentials: DPA4 OMat24 and OMol25 Pre-trained Models Unveiled

Whether a new material can withstand high temperatures, whether a battery will swell, or where an alloy part will crack—to answer these questions, the most thorough approach is to lay out the atoms in the material one by one, let them move according to physical laws, and play an "atomic-level movie" in a computer. This is cheaper and faster than actually smelting a batch, burning it, or breaking it.

Yet for decades, this movie has been stuck in the same place: you have to choose between fidelity and scale.

Molten salt reactors (MSRs), as important candidates for Generation IV advanced nuclear energy systems, feature fluoride molten salts (such as the LiF-NaF-KF ternary eutectic system FLiNaK) as core functional materials. Their high-temperature stability, excellent thermal conductivity, and ability to dissolve actinides make them ideal carriers for liquid nuclear fuel and coolants. However, the microstructural coordination environment and thermophysical property evolution of the key actinide ion Th⁴⁺ in thorium-based MSRs under different alkali metal cation ratios have lacked systematic study. How to efficiently and accurately screen fuel salt formulations that balance thermal storage, transport properties, and structural stability across a wide compositional space has become a critical bottleneck limiting MSR optimization.

In silicon-on-insulator (SOI) technology, the core challenge of the separation by implanted oxygen (SIMOX) process lies in precisely controlling the thickness and oxygen distribution of the buried oxide (BOX) layer and understanding cross-interface thermal transport behavior. Traditional methods often suffer from limited accuracy or efficiency in predicting oxygen diffusion dynamics, layer thickness evolution, and interfacial thermal resistance during post-implantation annealing. Recently, a team led by Prof. Guangping Zheng and Dr. Jiashu Chen from the Department of Mechanical Engineering at The Hong Kong Polytechnic University, in collaboration with Prof. Zhuo Tang’s group from the College of Information Science and Engineering, Hunan University, published a research achievement in Communications Materials (IF=9.6) titled “Deep learning modeling of oxygen redistribution and thermal transport in silicon on insulator and buried oxide layers”. They proposed a computational framework integrating deep neural network potential with molecular dynamics (DFT-MD + DP), systematically addressing the multiscale modeling challenges from oxygen implantation and diffusion to interfacial heat transport.