QZQionghua Zhou

Qionghua Zhou

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Qionghua Zhou has a total of 84 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Accelerating the Discovery of Synthesizable 2D Hybrid Double Perovskites through Human–LLM Collaborative Descriptor Engineering

    by Rong Guo, Chang-Feng Wang, Ming-Gang Ju, Yilei Wu, Peiguo Liu, Qionghua Zhou, Shuaihua Lu, Zhilong Song, Qianglong Fang, Qisheng Wu, et al.

    Two-dimensional hybrid perovskites offer exceptional structural diversity and multifunctional properties, yet their synthesis remains a major bottleneck due to low hit rates and strong reliance on empirical intuition. Here we introduce AL-SynAgent, a human-in-the-loop, ML-guided screening workflow that integrates literature-derived synthetic priors, expert-refined chemical descriptors, and active learning to assess the synthesis feasibility of two dimensional (2D) hybrid organic–inorganic rare-earth double perovskites (HORDPs). By converting LLM-assisted literature knowledge and expert chemical reasoning into system-specific computable descriptors, AL-SynAgent reduces dependence on large experimental data sets while retaining chemically interpretable decision rules. With experimental feedback from only 4.8% of candidate space, the model converged and achieved successful target-phase formation for 11 of the 14 candidates in the prospectively selected experimental set, corresponding to a hit rate of 78.6%. Screening of an enumerated virtual library of 280,000 candidates further prioritized 64,482 compositions with high predicted synthesis feasibility. Notably, three newly obtained compounds also exhibit both excellent ferroelectricity and photoluminescence, including (4-F-321)4RbEu(NO3)8, which displays an exceptionally high Curie temperature of 388 K and strong emission at 592 nm. This work establishes a practical, human-in-the-loop strategy for data-efficient prioritization of candidate compositions within chemically constrained 2D HORDP space under a standardized laboratory synthesis protocol.

  • Mechanism-Guided Catalyst Discovery for Methane C–H Activation via Structure-Aware Multisource Transfer Learning

    by Wangqiang Lin, Huiyang Zhang, Jinxin Sun, Chongyi Ling, Xiuyun Zhang, Qiang Li, Qionghua Zhou, Jinlan Wang

    In complex heterogeneous systems, data-driven catalyst discovery is severely hindered by the scarcity of kinetic data and the breakdown of traditional linear scaling relationships caused by the diverse local coordination environments. Herein, we formulate a mechanism-driven approach to alleviate data dependence and develop a multisource transfer learning (MS-TL) framework that leverages the knowledge embedded in abundant adsorption data sets while accurately capturing local structural dependence. Taking methane C–H activation as a representative case, this framework extracts key thermodynamic descriptors corresponding to the initial, transition, and final states as source domains, enabling a deep fusion of multidimensional thermodynamic knowledge while preserving local structural information. Using this framework, we achieved universal predictions of barriers across various facets and compositions in complex alloys. Subsequent data-driven analysis recovers the classical Sabatier principle beyond the limits of linear scaling, revealing a multidimensional volcano-shaped trend that delineates the optimal catalytic window. Furthermore, we propose a temperature-barrier composite kinetic descriptor that quantitatively bridges microscopic theoretical calculations with macroscopic experimental methane oxidation rates, establishing a new data-driven paradigm for rational catalyst design under realistic operating conditions.

  • Open Access

    Decoding plasticity in van der Waals crystals via causality-driven interpretable machine learning

    by Xinyu Chen, Qian Chen, Liang Ma, Qionghua Zhou, Jinlan Wang

    Plastic deformation in van der Waals (vdW) crystals is essential for flexible and wearable electronics. However, its evaluation typically requires destructive testing or costly first-principles calculations. To address this, we present a causality-driven, interpretable machine learning framework that extracts accurate plasticity descriptors from easily accessible material features, avoiding empirical assumptions and high computational costs. By leveraging causal discovery, we clarify the roles of interlayer and intralayer interactions in plasticity and identify key features that govern plastic behavior. A causality-constrained symbolic regression method then generates a compact, physically meaningful descriptor with 96% accuracy in distinguishing plastic from brittle vdW materials. This descriptor enables rapid screen of large material databases and identifies 29 previously unrecognized semiconductors with superior plasticity. This framework provides a generalizable approach to convert empirical data into actionable materials knowledge, accelerating functional materials design.


  • Boosting Crystalline Property Prediction through Dynamical Feature Updating and Wavelet-Denoised Features: A New Deep Learning Model

    by Zening Yang, Jin Yu, Zhengyu Sun, Chengchen Li, Qionghua Zhou, Weiwei Sun

    Graph neural networks (GNNs) inherently excel at representing atomistic material, therefore enabling predictions of properties with high accuracy with embedded descriptors. Approaching to accurate prediction of a variety of physical properties of diverse materials, particularly those with multicomponents, remains challenging due to the complexity of many-body atomic interactions and the reliance on handcrafted symmetry descriptors. Here, we introduce the Wavelet Atomic Neighborhood Network (WANN), a novel framework that implicitly captures many-body interactions through an iterative subembedding module for updating atomic features, thereby eliminating the integration of the predefined feature engineering. A wavelet-based regression component is built up through multiscale feature analysis. WANN demonstrates superior accuracy, achieving small mean absolute error (MAE) in predicting a variety of physical and chemical quantities, including thermodynamical, dielectric, piezoelectric, magnetic, and thermoelectric properties. For instance, it could significantly reduce MAE maximum by 61.64% in comparison to Matformer for shear moduli and by 90.84% in comparison to ALIGNN for the exfoliation energy. This scalable and preprocessing-light deep-learning framework provides an efficient toolkit for facilitating high-throughput screening of emergent materials, like high-entropy alloys and ceramics.

  • Open Access

    Continuous discovery of novel 2D materials via dual active learning-driven generative models

    by Xinyu Chen, Zhilong Song, Shuaihua Lu, Qian Chen, Yuanqiu Mo, Qionghua Zhou, Jinlan Wang

    Generative artificial intelligence is transforming materials discovery by creating unexplored candidates. However, such models are trapped in historical data bias, particularly for data-scarce systems like two-dimensional (2D) materials, leading to repetitive outputs rather than genuine discoveries. Here, we introduce DuALGen, a dual active learning framework that mitigates these limitations. DuALGen couples two complementary loops to enrich data diversity and correct data bias: a generative loop that uses dynamic, multi-criteria sampling to drive exploration of the design space, and a predictive loop that samples outliers to counter distribution shift, enabling reliable evaluation of novel, previously unknown candidates. Applied to 2D materials, DuALGen uncovers >10 000 stable, distinct compounds, including thousands of high-performance candidates for electronic applications. This self-updating workflow connects generative models to uncharted chemical spaces, and offers a practical route to continuous discovery of new materials.


  • Extending the Schottky–Mott Rule to Atomic Thickness: Descriptors for Two-Dimensional Semiconductor–Metal Contacts

    by Xing Yu, Xinyu Chen, Xuchen Yu, Qionghua Zhou, Liang Ma, Jinlan Wang

    Ultralow-resistance Ohmic contacts at two-dimensional (2D) semiconductor-metal interfaces are pivotal for advancing next-generation electronics, yet the classical Schottky-Mott rule fails in 2D systems due to quantum confinement and pronounced Fermi-level pinning. Here, we use domain knowledge with machine learning to derive compact, physically interpretable Schottky-barrier descriptors that quantitatively characterize interfacial carrier behavior and accurately predict barrier heights from intrinsic parameters (work function and electronegativity). Applying these descriptors to transition metal dichalcogenides and various metal substrates, we identify 12 promising Ohmic contact electrodes from 1392 heterojunctions. We further introduce a physically grounded Schottky-barrier factor (δ) and reformulate the Schottky-Mott rule by explicitly coupling the interfacial work function difference (ΔWF) with the electronegativity mismatches (Δχ). The co-modulation of ΔWF and Δχ governs the Schottky-barrier formation at semiconductor-metal interfaces. This work extends Schottky-Mott physics to the atomic limit and offers practical design rules for engineering low-resistance 2D contacts.


  • A Descriptor-Driven Thermodynamic Framework for Achieving Unidirectional Nucleation in 2D Material Epitaxy

    by Ruikang Dong, Yilei Wu, Chunjin Ren, Xiaoshu Gong, Qionghua Zhou, Jinlan Wang, Liang Ma

    Unidirectional nucleation is crucial for achieving wafer-sized single-crystal epitaxy of two-dimensional (2D) materials, yet it is fundamentally hindered by multidirectional nucleations resulting from symmetry mismatch-induced energy equivalence at the epilayer-substrate interfaces. Here, we propose a universal, hierarchical framework that integrates thermodynamic modeling, epitaxial descriptor construction, and substrate-step engineering to enable unidirectional nucleation and epitaxy across diverse 2D materials. Our thermodynamic model classifies 2D nucleation into edge-dominated and surface-dominated regimes, pinpointing that the latter can be controlled only when terrace steps are precisely aligned with the preferred epitaxial axis. A quantitative epitaxial descriptor based on lattice mismatch and interfacial atomic spacing is developed for screening optimal growth orientations for arbitrary 2D/substrate systems, eliminating the need for first-principles calculations. Applied to benchmark systems, this framework predicts that graphene and hexagonal boron nitride (h-BN) tolerate broad step directions, whereas molybdenum disulfide (MoS2) requires strict orientation engineering, in full agreement with experiments. This work establishes a general protocol for substrate-step engineering that promotes unidirectional nucleation and provides guidelines for wafer-scale single-crystal epitaxy of diverse 2D materials.


  • Active Learning for Accelerated Discovery of Two-Dimensional Magnetic Topological Materials

    by Zhipeng Cao, Shuaihua Lu, Shijun Yuan, Liang Ma, Qionghua Zhou, Jinlan Wang


  • Top Cited Papers
    Open Access

    Accurate prediction of synthesizability and precursors of 3D crystal structures via large language models

    by Zhilong Song, Shuaihua Lu, Minggang Ju, Qionghua Zhou, Jinlan Wang

    Accessing the synthesizability of crystal structures is crucial for transforming theoretical materials into real-world applications. Nevertheless, there is a significant gap between actual synthesizability and thermodynamic or kinetic stability commonly used to screen synthesizable structures. Herein, we develop the Crystal Synthesis Large Language Models (CSLLM) framework, which utilizes three specialized LLMs to predict the synthesizability of arbitrary 3D crystal structures, possible synthetic methods, and suitable precursors, respectively. We construct a comprehensive dataset including synthesizable/non-synthesizable crystal structures and develop an efficient text representation for crystal structures to fine-tune LLMs. Our Synthesizability LLM achieves state-of-the-art accuracy (98.6%), significantly outperforming traditional synthesizability screening based on thermodynamic and kinetic stability. Its outstanding generalization ability is further demonstrated in experimental structures with complexity considerably exceeding that of the training data. Furthermore, both the Method and Precursor LLMs exceed 90% accuracy in classifying possible synthetic methods and identifying solid-state synthetic precursors for common binary and ternary compounds, respectively. Leveraging CSLLM, tens of thousands of synthesizable theoretical structures are successfully identified, with their 23 key properties predicted using accurate graph neural network models.


  • Feature-Extended Descriptor Construction for Prediction of Consecutive Elementary Reaction Energies in Methane Oxidation

    by Wangqiang Lin, Fangting Liu, Zhilong Song, Yehui Zhang, Qionghua Zhou, Chongyi Ling, Qiang Li, Jinlan Wang