arXiv subjects

Haidi Wang

Publications and source records attributed to Haidi Wang.

14 recordsLinked to original sources

arXiv2026

UniMatSim: A High-Throughput Materials Simulation Automation Framework Based on Universal Machine Learning Potentials

Universal machine learning interatomic potentials (UMLIPs) offer accuracy close to first-principles calculations at a fraction of the cost, showing significant potential for large-scale material simulations. However, the fragmented UMLIPs ecosystem lacks unified interface standards and integration frameworks, hindering their automated deployment in high-throughput workflows. To address this, we present UniMatSim, a modular Python framework. It systematically integrates various UMLIPs (e.g., CHGNet, M3GNet, MACE) and automates workflows from structural optimization to stability verification. The framework enables seamless model switching via abstracted interfaces, incorporates task orchestration, and provides standardized modules for key properties (elasticity, phonons, molecular dynamics), including automated handling for low-dimensional materials. As a test case, using the 2D Lieb lattice system, we constructed a multi-stage high-throughput screening workflow covering structural optimization, elastic stability, and phonon spectrum calculations. Starting from 1,176 candidate compositions, a four-model consensus pipeline yields 393 stable structures. These are refined by magnetic-state screening and DFT band-structure calculations to 59 Lieb-lattice candidates with staggered-magnetic-band characteristics. Results show UniMatSim significantly improves computational efficiency and reproducibility, providing a reliable infrastructure for data-driven materials discovery and design.

cond-mat.mtrl-sci↗

arXiv2025

Benchmarking Universal Machine Learning Interatomic Potentials for Elastic Property Prediction

Universal machine learning interatomic potentials have emerged as efficient tools for materials simulation, yet their reliability for elastic property prediction remains unclear. Here, we present a systematic benchmark of four uMLIPs -- MatterSim, MACE, SevenNet, and CHGNet -- against first-principles data for nearly 11\,000 elastically stable materials from the Materials Project database. The results show that SevenNet achieves the highest accuracy, MACE and MatterSim balance accuracy with efficiency, while CHGNet performs less effectively overall. To further improve predictive quality, we perform targeted fine-tuning on all four uMLIPs using strained configurations derived from 185 high-error materials. After fine-tuning, CHGNet shows the most substantial improvement in overall accuracy, with MatterSim and SevenNet also benefiting from the fine-tuning, whereas MACE shows limited robustness to this procedure. This work provides quantitative guidance for model selection and data refinement, advancing uMLIPs toward reliable applications in mechanical property prediction.

cond-mat.mtrl-sci↗

arXiv2025

Uni2D: A Universal Machine Learning Interatomic Potential for Two-Dimensional Materials

Accurate interatomic potentials (IAPs) are essential for modeling the potential energy surfaces (PES) that govern atomic interactions in materials. However, most existing IAPs are developed for bulk materials and often struggle to accurately and efficiently capture the diverse chemical environments of two-dimensional (2D) materials, which limits large-scale simulation and design of emerging 2D systems. To address this challenge, we develop Uni2D, an interatomic potential tailored for 2D materials. The Uni2D model is trained on a dataset comprising approximately 327,000 structure-energy-force-stress mappings derived from about 20,000 distinct 2D materials, covering 89 chemical elements. The model demonstrates reliable predictive performance for energies, forces, and stresses, and demonstrates quantitatively robust accuracy in tasks such as structural relaxation, equation-of-state calculations, and molecular dynamics simulations, making the model suitable for high-throughput screening of 2D materials. For derived properties, including elastic properties, lattice dynamics, and other screening-related metrics, the model provides qualitative to semi-quantitative predictions that remain useful for trend analysis and preliminary evaluation. To enhance usability, we further introduce an intelligent agent powered by a large language model (LLM), enabling automated workflows and natural language interaction for 2D materials simulations. Our work provides an efficient and accessible framework for high-throughput screening and computational exploration of 2D materials.

cond-mat.mtrl-sci↗

arXiv2025

High-throughput calculations of two-dimensional auxetic $M_4X_8$ with magnetism, electrocatalysis, and alkali metal battery applications

Two-dimensional (2D) materials with multifunctional properties, such as negative Poisson's ratio (NPR), magnetism, catalysis, and energy storage capabilities, are of significant interest for advanced applications in flexible electronics, spintronics, catalysis, and lithium-ion batteries. However, the discovery of such materials, particularly in low-dimensional forms, remains a challenge. In this study, we perform high-throughput density-functional theory (DFT) calculations to explore a new class of 2D V-shaped monolayers with remarkable physicochemical properties. Among 18 stable $M_4X_8$ (M = transition metal; X = halogen) compounds, we identify 9 auxetic monolayers, with \ce{Pd4I8} standing out for its exceptionally high NPR of -0.798. Notably, 4 of these materials exhibit half semiconductor properties, while 5 others are bipolar magnetic semiconductors, offering a unique combination of electronic and magnetic behavior. Additionally, these materials demonstrate promising catalytic activity for hydrogen and oxygen evolution reactions (HER/OER) and show potential as anodes for rechargeable metal-ion batteries, particularly in alkali-ion systems. This work not only expands the family of 2D NPR materials but also introduces new candidates with multifunctional capabilities for a wide range of applications in nanoelectronics, catalysis, and energy storage.

cond-mat.mes-hall↗

arXiv2024

High-throughput Screening of Ferrimagnetic Semiconductors With Ultrahigh N$\acute{e}$el Temperature

Ferrimagnetic semiconductors, integrated with net magnetization, antiferromagnetic coupling and semi-conductivity, have constructed an ideal platform for spintronics. For practical applications, achieving high N$\acute{e}$el temperatures ($T_{\mathrm{N}}$) is very desirable, but remains a significant challenge. Here, via high-throughput density-functional-theory calculations, we identify 19 intrinsic ferrimagnetic semiconductor candidates from nearly 44,000 structures in the Materials Project database, including 10 ferrimagnetic bipolar magnetic semiconductors (BMS) and 9 ferrimagnetic half semiconductors (HSC). Notably, the BMS \ce{NaFe5O8} possesses a high $T_{\mathrm{N}}$ of 768 K. By element substitutions, we obtain an HSC \ce{NaFe5S8} with a $T_{\mathrm{N}}$ of 957 K and a BMS \ce{LiFe5O8} with a $T_{\mathrm{N}}$ reaching 1059 K. Our results pave a promising avenue toward the development of ferrimagnetic spintronics at ambient temperature.

cond-mat.mtrl-sci↗

arXiv2021

High-throughput computational screening for bipolar magnetic semiconductors

Searching ferromagnetic semiconductor materials with electrically controllable spin polarization is a long-term challenge for spintronics. Bipolar magnetic semiconductors (BMS), with valence and conduction band edges fully spin-polarized in different spin directions, show great promise in this aspect because the carrier's spin polarization direction can be easily tuned by voltage gate. Here, we propose a standard high-throughput computational screening scheme for searching BMS materials. The application of this scheme to the Materials Project database gives 11 intrinsic BMS materials (1 experimental and 10 theoretical) from nearly 40000 structures. Among them, a room temperature BMS Li2V3TeO8 (mp-771246) is discovered with a Curie temperature of 478K. Moreover, the BMS feature can be maintained well when cutting the bulk Li2V3TeO8 into (001) nanofilms for realistic applications. This work provides a feasible solution for discovering novel intrinsic BMS materials from various crystal structure databases, paving the way for realizing electric-field controlled spintronic devices.

cond-mat.mtrl-sci↗

arXiv2021

Zero-sample surface defect detection and classification based on semantic feedback neural network

Defect detection and classification technology has changed from traditional artificial visual inspection to current intelligent automated inspection, but most of the current defect detection methods are training related detection models based on a data-driven approach, taking into account the difficulty of collecting some sample data in the industrial field. We apply zero-shot learning technology to the industrial field. Aiming at the problem of the existing "Latent Feature Guide Attribute Attention" (LFGAA) zero-shot image classification network, the output latent attributes and artificially defined attributes are different in the semantic space, which leads to the problem of model performance degradation, proposed an LGFAA network based on semantic feedback, and improved model performance by constructing semantic embedded modules and feedback mechanisms. At the same time, for the common domain shift problem in zero-shot learning, based on the idea of co-training algorithm using the difference information between different views of data to learn from each other, we propose an Ensemble Co-training algorithm, which adaptively reduces the prediction error in image tag embedding from multiple angles. Various experiments conducted on the zero-shot dataset and the cylinder liner dataset in the industrial field provide competitive results.

cs.CV↗

arXiv2021

Super-Resolution Image Reconstruction Based on Self-Calibrated Convolutional GAN

With the effective application of deep learning in computer vision, breakthroughs have been made in the research of super-resolution images reconstruction. However, many researches have pointed out that the insufficiency of the neural network extraction on image features may bring the deteriorating of newly reconstructed image. On the other hand, the generated pictures are sometimes too artificial because of over-smoothing. In order to solve the above problems, we propose a novel self-calibrated convolutional generative adversarial networks. The generator consists of feature extraction and image reconstruction. Feature extraction uses self-calibrated convolutions, which contains four portions, and each portion has specific functions. It can not only expand the range of receptive fields, but also obtain long-range spatial and inter-channel dependencies. Then image reconstruction is performed, and finally a super-resolution image is reconstructed. We have conducted thorough experiments on different datasets including set5, set14 and BSD100 under the SSIM evaluation method. The experimental results prove the effectiveness of the proposed network.

eess.IV↗

arXiv2021

A self-adapting super-resolution structures framework for automatic design of GAN

With the development of deep learning, the single super-resolution image reconstruction network models are becoming more and more complex. Small changes in hyperparameters of the models have a greater impact on model performance. In the existing works, experts have gradually explored a set of optimal model parameters based on empirical values or performing brute-force search. In this paper, we introduce a new super-resolution image reconstruction generative adversarial network framework, and a Bayesian optimization method used to optimizing the hyperparameters of the generator and discriminator. The generator is made by self-calibrated convolution, and discriminator is made by convolution lays. We have defined the hyperparameters such as the number of network layers and the number of neurons. Our method adopts Bayesian optimization as a optimization policy of GAN in our model. Not only can find the optimal hyperparameter solution automatically, but also can construct a super-resolution image reconstruction network, reducing the manual workload. Experiments show that Bayesian optimization can search the optimal solution earlier than the other two optimization algorithms.

cs.CV↗

arXiv2019

DP-GEN: A concurrent learning platform for the generation of reliable deep learning based potential energy models

In recent years, promising deep learning based interatomic potential energy surface (PES) models have been proposed that can potentially allow us to perform molecular dynamics simulations for large scale systems with quantum accuracy. However, making these models truly reliable and practically useful is still a very non-trivial task. A key component in this task is the generation of datasets used in model training. In this paper, we introduce the Deep Potential GENerator (DP-GEN), an open-source software platform that implements the recently proposed "on-the-fly" learning procedure [Phys. Rev. Materials 3, 023804] and is capable of generating uniformly accurate deep learning based PES models in a way that minimizes human intervention and the computational cost for data generation and model training. DP-GEN automatically and iteratively performs three steps: exploration, labeling, and training. It supports various popular packages for these three steps: LAMMPS for exploration, Quantum Espresso, VASP, CP2K, etc. for labeling, and DeePMD-kit for training. It also allows automatic job submission and result collection on different types of machines, such as high performance clusters and cloud machines, and is adaptive to different job management tools, including Slurm, PBS, and LSF. As a concrete example, we illustrate the details of the process for generating a general-purpose PES model for Cu using DP-GEN.

physics.comp-ph↗

arXiv2018

Two-dimensional Penta-Pt2N4: an ideal material for nanoelectronics

Since the discovery of graphene, two-dimensional (2D) materials have paved a new routine for designing high-performance nanoelectronic devices. To facilitate the device applications, there are three key requirements for a material: sizeable band gap, high carrier mobility and robust environmental stability. However, for the hottest 2D materials studied in recent years, graphene is gapless, transition metal dichalcogenides have low carrier mobility, and black phosphorene is environmentally sensitive. So far, these three characteristics can seldom be satisfied in one single material. Therefore, it becomes a great challenge for finding an ideal 2D material to overcome such a limitation. In this work, we theoretically predict a novel planar 2D material: Penta-Pt2N4, which are designed by the fantastic Cario pentagonal tiling as well as the rare nitrogen double bond. Most significantly, the 2D Penta-Pt2N4 exhibits excellent intrinsic properties, including large direct band gap up to 1.51 eV, high carrier mobility up to 105 cm2V-1s-1, giant Young's module up to 0.70 TPa, and robust dynamic, thermal and chemical stability. Moreover, Penta-Pt2N4 is a global minimal with PtN2 stoichiometry in 2D, so we also propose a CVD/MBE scheme to enable its experimental synthesis. We envision that the 2D Penta-Pt2N4 may find a wide application for future nanoelectronics.

cond-mat.mtrl-sci↗

arXiv2017

C3N: a Two Dimensional Semiconductor Material with High stiffness,Superior Stability and Bending Poisson's Effect

Recently, a new type of two-dimensional layered material, i.e. C3N, has been fabricated by polymerization of 2,3-diaminophenazine and used to fabricate a field-effect transistor device with an on/off current ratio reaching 5.5E10 (Adv. Mater. 2017, 1605625). Here we have performed a comprehensive first-principles study mechanical and electronic properties of C3N and related derivatives. Ab inito molecular dynamics simulation shows that C3N monolayer can withstand high temperature up to 2000K. Besides high stability, C3N is predicted to be a superior stiff material with high Young's modulus (1090.0 GPa), which is comparable or even higher than that of graphene (1057.7 GPa). By roll-up C3N nanosheet into the corresponding nanotube, an out-of-plane bending deformation is also investigated. The calculation indicates C3N nanosheet possesses a fascinating bending Poisson's effect, namely, bending induced lateral contraction. Further investigation shows that most of the corresponding nanotubes also present high Young's modulus and semiconducting properties. In addition, the electronic properties of few-layer C3N nanosheet is also investigated. It is predicated that C3N monolayer is an indirect semiconductor (1.09 eV) with strongly polar covalent bonds, while the multi-layered C3N possesses metallic properties with AD-stacking. Due to high stability, suitable band gap and superior mechanical strength, the C3N nanosheet will be an ideal candidate in high-strength nano-electronic device applications.

cond-mat.mtrl-sci↗

arXiv2017

BP_5 Monolayer with Multiferroicity and Negative Poisson's Ratio: A Prediction by Global Optimization Method

Based on variable components global optimization algorithm, we predict a stable two-dimensional (2D) phase of boron phosphide with 1:5 stoichiometry, i.e. boron pentaphosphide (BP_5) monolayer, which has a lower formation energy than that of the commonly believed graphitic phase (g-BP). BP_5 monolayer is a multiferroic material with coupled ferroelasticity and ferroelectricity. The predicted reversible strain is up to 41.41%, which is the largest among all reported ferroelastic materials. Due to the non-centrosymmetric structure and electronegativity differences between boron and phosphorus atoms, an in-plane spontaneous polarization of 326.0 pC/m occurs in BP_5. Moreover, the recently hunted negative Poisson's ratio property, is also observed in BP_5. As an indirect semiconductor with a band gap of 1.34 eV, BP_5 displays outstanding optical and electronic properties, for instance strongly anisotropic visible-light absorption and high carrier mobility. The rich and extraordinary properties of BP_5 make it a potential nanomaterial for designing electromechanical or optoelectronic devices, such as nonvolatile memory with conveniently readable/writeable capability. Finally, we demonstrate that AlN (010) surface could be a suitable substrate for epitaxy growth of BP_5 monolayer.

cond-mat.mtrl-sci↗

arXiv2016

δ-phosphorene: a two dimensional material with high negative Poisson's ratio

As a basic mechanical parameter, Poisson's ratio (ν) measures the mechanical responses of solids against external loads. In rare cases, materials have a negative Poisson's ratio (NPR), and present an interesting auxetic effect. That is, when a material is stretched in one direction, it will expand in the perpendicular direction. To design modern nanoscale electromechanical devices with special functions, two dimensional (2D) auxetic materials are highly desirable. In this work, based on first principles calculations, we rediscover the previously proposed δ-phosphorene (δ-P) nanosheets [Jie Guan et al., Phys. Rev. Lett. 2014, 113, 046804] are good auxetic materials with a high NPR. The results show that the Young's modulus and Poisson's ratio of δ-P are all anisotropic. The NPR value along the grooved direction is up to -0.267, which is much higher than the recently reported 2D auxetic materials. The auxetic effect of δ-P originated from its puckered structure is robust and insensitive to the number of layers due to weak interlayer interactions. Moreover, δ-P possesses good flexibility because of its relatively small Young's modulus and high critical crack strain. If δ-P can be synthesized, these extraordinary properties would endow it great potential in designing low dimensional electromechanical devices.

cond-mat.mtrl-sci↗