2026
AI-Driven Structure Refinement of X-ray Diffraction
Cao Bin, Zhang Qian, Feng Zhenjie, Zhang Taolue, Huang Jiaqiang, Weng Lu-Tao, Zhang Tongyi# (# corresponding author)
arXiv 2026
AI can quickly propose candidate phases from X-ray diffraction (XRD), but refinement often fails due to unstable intensities under peak overlap and weak diffraction constraints. We introduce WPEM, a physics-constrained whole-pattern decomposition workflow that embeds Bragg's law in a batch expectation–maximization framework. WPEM models the full profile as a probabilistic mixture, iteratively inferring component intensities while keeping peak centers Bragg-consistent, producing a stable, physically valid representation. On \ce{PbSO4} and \ce{Tb2BaCoO5}, WPEM outperforms FullProf and TOPAS. It generalizes to multiphase Ti–15Nb films, \ce{NaCl}–\ce{Li2CO3} mixtures, semicrystalline polymers, operando cathodes, disordered Ru–Mn oxides (CCDC 2530452), and ancient Egyptian make-up, bridging AI-generated hypotheses and diffraction-ready structure refinement.
AI-Driven Structure Refinement of X-ray Diffraction
Cao Bin, Zhang Qian, Feng Zhenjie, Zhang Taolue, Huang Jiaqiang, Weng Lu-Tao, Zhang Tongyi# (# corresponding author)
arXiv 2026
AI can quickly propose candidate phases from X-ray diffraction (XRD), but refinement often fails due to unstable intensities under peak overlap and weak diffraction constraints. We introduce WPEM, a physics-constrained whole-pattern decomposition workflow that embeds Bragg's law in a batch expectation–maximization framework. WPEM models the full profile as a probabilistic mixture, iteratively inferring component intensities while keeping peak centers Bragg-consistent, producing a stable, physically valid representation. On \ce{PbSO4} and \ce{Tb2BaCoO5}, WPEM outperforms FullProf and TOPAS. It generalizes to multiphase Ti–15Nb films, \ce{NaCl}–\ce{Li2CO3} mixtures, semicrystalline polymers, operando cathodes, disordered Ru–Mn oxides (CCDC 2530452), and ancient Egyptian make-up, bridging AI-generated hypotheses and diffraction-ready structure refinement.
Bgolearn: a Unified Bayesian Optimization Framework for Accelerating Materials Discovery
Cao Bin, Xiong Jie#, Ma Jiaxuan, Tian Yuan, Hu Yirui, He Mengwei, Zhang Longhan, Wang Jiayu, Hui Jian#, Liu Li, Xue Dezhen, Turab Lookman#, Zhang Tongyi# (# corresponding author)
arXiv 2026
Efficient exploration of vast compositional and processing spaces is essential for accelerated materials discovery. Bayesian optimization (BO) provides a principled strategy for identifying optimal materials with minimal experiments, yet its adoption in materials science is hindered by implementation complexity and limited domain-specific tools. Here, we present Bgolearn, a comprehensive Python framework that makes BO accessible and practical for materials research through an intuitive interface, robust algorithms, and materials-oriented workflows.
Bgolearn: a Unified Bayesian Optimization Framework for Accelerating Materials Discovery
Cao Bin, Xiong Jie#, Ma Jiaxuan, Tian Yuan, Hu Yirui, He Mengwei, Zhang Longhan, Wang Jiayu, Hui Jian#, Liu Li, Xue Dezhen, Turab Lookman#, Zhang Tongyi# (# corresponding author)
arXiv 2026
Efficient exploration of vast compositional and processing spaces is essential for accelerated materials discovery. Bayesian optimization (BO) provides a principled strategy for identifying optimal materials with minimal experiments, yet its adoption in materials science is hindered by implementation complexity and limited domain-specific tools. Here, we present Bgolearn, a comprehensive Python framework that makes BO accessible and practical for materials research through an intuitive interface, robust algorithms, and materials-oriented workflows.
Beyond Structure: Invariant Crystal Property Prediction with Pseudo-Particle Ray Diffraction
Cao Bin, Liu Yang#, Zhang Longhan, Wu Yifan, Luo Yuyu, Cheng Hong, Ren Yang#, Zhang Tongyi# (# corresponding author)
International Conference on Learning Representations (ICLR) 2026 Top tier AI conference
We propose PRDNet, a novel architecture that integrates graph embeddings with a learned pseudoparticle diffraction module. It generates synthetic diffraction patterns that are invariant to crystallographic symmetries. We extensively evaluate PRDNet on multiple large-scale benchmarks, including Materials Project, JARVIS-DFT, and MatBench. Our model achieves state-of-the-art performance across a wide range of crystal property prediction tasks, demonstrating its effectiveness.
Beyond Structure: Invariant Crystal Property Prediction with Pseudo-Particle Ray Diffraction
Cao Bin, Liu Yang#, Zhang Longhan, Wu Yifan, Luo Yuyu, Cheng Hong, Ren Yang#, Zhang Tongyi# (# corresponding author)
International Conference on Learning Representations (ICLR) 2026 Top tier AI conference
We propose PRDNet, a novel architecture that integrates graph embeddings with a learned pseudoparticle diffraction module. It generates synthetic diffraction patterns that are invariant to crystallographic symmetries. We extensively evaluate PRDNet on multiple large-scale benchmarks, including Materials Project, JARVIS-DFT, and MatBench. Our model achieves state-of-the-art performance across a wide range of crystal property prediction tasks, demonstrating its effectiveness.
Spatial-adaptive active learning identifies ultra-durable and highly active catalysts for acidic oxygen evolution reaction
Cao Bin*, Qin Yin#, Luo Yan*, Ying Zhehan, Yan Zilin, Weng Tu-Tao, Li Kaikai#, Zhang Tongyi# (* equal contribution, # corresponding author)
Science Bulletin 2026
Here, we present a spatially adaptive active-learning framework with closed-loop experimentation for targeted catalyst optimization. Bayesian optimization and a conditional variational autoencoder first identify a low-overpotential stability subspace, followed by active learning to pinpoint the most stable candidate. This strategy leads to the discovery of a Cu–RuO₂ catalyst with outstanding durability (625 h) and a low overpotential of 177 mV at 10 mA cm⁻². Our results highlight an efficient AI-driven pathway for accelerating the design of stable acidic OER catalysts.
Spatial-adaptive active learning identifies ultra-durable and highly active catalysts for acidic oxygen evolution reaction
Cao Bin*, Qin Yin#, Luo Yan*, Ying Zhehan, Yan Zilin, Weng Tu-Tao, Li Kaikai#, Zhang Tongyi# (* equal contribution, # corresponding author)
Science Bulletin 2026
Here, we present a spatially adaptive active-learning framework with closed-loop experimentation for targeted catalyst optimization. Bayesian optimization and a conditional variational autoencoder first identify a low-overpotential stability subspace, followed by active learning to pinpoint the most stable candidate. This strategy leads to the discovery of a Cu–RuO₂ catalyst with outstanding durability (625 h) and a low overpotential of 177 mV at 10 mA cm⁻². Our results highlight an efficient AI-driven pathway for accelerating the design of stable acidic OER catalysts.
2025
Ferromagnetic Surface Segregation via Stress-Concentration Coupling Boosts the Oxygen Evolution Reaction in RuO2
Qin Yin*, Deng Sihao*, Zhou Xiaoye#, Cao Bin, Ying Zhehan, Yan Zilin, Zhong Zheng, He Lunhua#, Li Kaikai#, Zhang Tongyi# (* equal contribution, # corresponding author)
ACS Nano 2025
In this study, we successfully induced weak ferromagnetism in commercial RuO2, transitioning it from an AFM state using an electrochemical sodiation method. This process resulted in high activity, achieving an overpotential of 145 mV to reach 10 mA cm–2 and extending the service hours by more than 13 times compared to pristine RuO2 in 0.5 M H2SO4.
Ferromagnetic Surface Segregation via Stress-Concentration Coupling Boosts the Oxygen Evolution Reaction in RuO2
Qin Yin*, Deng Sihao*, Zhou Xiaoye#, Cao Bin, Ying Zhehan, Yan Zilin, Zhong Zheng, He Lunhua#, Li Kaikai#, Zhang Tongyi# (* equal contribution, # corresponding author)
ACS Nano 2025
In this study, we successfully induced weak ferromagnetism in commercial RuO2, transitioning it from an AFM state using an electrochemical sodiation method. This process resulted in high activity, achieving an overpotential of 145 mV to reach 10 mA cm–2 and extending the service hours by more than 13 times compared to pristine RuO2 in 0.5 M H2SO4.
Dissecting the chemical strain in inactive components of sodium-ion battery cathodes
Shi Xiuling*, Zhu Jiaqi*, Chen Bingxu, Cao Bin, Lv Bingfeng, Wang Zihan, Sun Sheng, Li Kaikai#, Zhang Tongyi# (* equal contribution, # corresponding author)
Scripta Materialia 2025
This work takes NaNi1/3Fe1/3Mn1/3O2 (NFM) as a model cathode and dissects the chemical strain in inactive components by combining operando XRD and digital image correlation techniques to simultaneously measure the chemically induced phase transformation strain and overall strain. Results reveal considerable negative strain during initial charge and positive strain after discharge, and the positive residual strain accumulates over cycles.
Dissecting the chemical strain in inactive components of sodium-ion battery cathodes
Shi Xiuling*, Zhu Jiaqi*, Chen Bingxu, Cao Bin, Lv Bingfeng, Wang Zihan, Sun Sheng, Li Kaikai#, Zhang Tongyi# (* equal contribution, # corresponding author)
Scripta Materialia 2025
This work takes NaNi1/3Fe1/3Mn1/3O2 (NFM) as a model cathode and dissects the chemical strain in inactive components by combining operando XRD and digital image correlation techniques to simultaneously measure the chemically induced phase transformation strain and overall strain. Results reveal considerable negative strain during initial charge and positive strain after discharge, and the positive residual strain accumulates over cycles.
First-Order Phase Transformation in Highly Concentrated Electrolyte for High-Rate and Long-Cycle Aqueous Zn-Ion Battery
Shi Xiuling#, Sun Yuchuan, Cao Bin, Zhou Xiaoye, Lei Tongxing, Li Jiahui, Ding Zhiyu, Fang Kai, Wu Junwei, Huang Yan#, Li Kaikai#, Zhang Tongyi# (# corresponding author)
Angewandte Chemie 2025
As a result, capacity doubles and cycle life increase sixty-fold compared to regular dilute electrolyte. The first-order phase transformation is attributed to reduced de-solvation energy and charge transfer energy barrier due to different Zn2+ solvation structure in the concentrated electrolyte. Our findings offer groundbreaking insights into the microstructure evolution of electrode in concentrated electrolyte and pave the way to further develop batteries with excellent performance.
First-Order Phase Transformation in Highly Concentrated Electrolyte for High-Rate and Long-Cycle Aqueous Zn-Ion Battery
Shi Xiuling#, Sun Yuchuan, Cao Bin, Zhou Xiaoye, Lei Tongxing, Li Jiahui, Ding Zhiyu, Fang Kai, Wu Junwei, Huang Yan#, Li Kaikai#, Zhang Tongyi# (# corresponding author)
Angewandte Chemie 2025
As a result, capacity doubles and cycle life increase sixty-fold compared to regular dilute electrolyte. The first-order phase transformation is attributed to reduced de-solvation energy and charge transfer energy barrier due to different Zn2+ solvation structure in the concentrated electrolyte. Our findings offer groundbreaking insights into the microstructure evolution of electrode in concentrated electrolyte and pave the way to further develop batteries with excellent performance.
XQueryer: an intelligent crystal structure identifier for powder X-ray diffraction
Cao Bin, Zheng Zinan, Liu Yang, Zhang Longhan, Wong W-Y Lawrence, Weng Tu-Tao, Li Jia#, Li Haoxiang#, Zhang Tongyi# (# corresponding author)
National Science Review 2025
We developed XQueryer, an intelligent agent for simulating, recognizing, and analyzing powder X-ray diffraction (PXRD) patterns. Trained on over two million high-fidelity simulated spectra, XQueryer achieves significantly higher accuracy—28.9% better than existing AI models and traditional methods. Integrated with a powder diffractometer, it enables real-time structural analysis of crystal samples.
XQueryer: an intelligent crystal structure identifier for powder X-ray diffraction
Cao Bin, Zheng Zinan, Liu Yang, Zhang Longhan, Wong W-Y Lawrence, Weng Tu-Tao, Li Jia#, Li Haoxiang#, Zhang Tongyi# (# corresponding author)
National Science Review 2025
We developed XQueryer, an intelligent agent for simulating, recognizing, and analyzing powder X-ray diffraction (PXRD) patterns. Trained on over two million high-fidelity simulated spectra, XQueryer achieves significantly higher accuracy—28.9% better than existing AI models and traditional methods. Integrated with a powder diffractometer, it enables real-time structural analysis of crystal samples.
Metal–Insulator Transition Driven by the Interplay of Vacancies and Charge Orders in Square-Net Materials GdSbxTe2-x-δ
Wang Qun, ..., Cao Bin, ..., Yue Chengming#, Lei Shiming#, Li Haoxiang# (# corresponding author)
Advanced Materials 2025
Here, a doping-dependent metal-insulator transition (MIT) with tunable bandgaps is reported in square-net materials GdSbxTe2-x-δ and a cooperative interaction between CDWs and vacancies that drives the MIT is discovered.
Metal–Insulator Transition Driven by the Interplay of Vacancies and Charge Orders in Square-Net Materials GdSbxTe2-x-δ
Wang Qun, ..., Cao Bin, ..., Yue Chengming#, Lei Shiming#, Li Haoxiang# (# corresponding author)
Advanced Materials 2025
Here, a doping-dependent metal-insulator transition (MIT) with tunable bandgaps is reported in square-net materials GdSbxTe2-x-δ and a cooperative interaction between CDWs and vacancies that drives the MIT is discovered.
Optimize the quantum yield of G‐quartet‐based circularly polarized luminescence materials via active learning strategy‐BgoFace
Li Tianliang*, Chen Lifei*, Cao Bin*, Liu Siyuan, Lin Lixing, Li Zeyu, Chen Yingying, Li Zhenzhen, Zhang Tongyi#, Feng Linyan# (* equal contribution, # corresponding author)
MGE advances 2025
This work developed an integrated AL software, BgoFace, which satisfies most material property optimization re-quirements. The application of BgoFace (with default setting) successfully accel-erated the discovery of G4-based CPL materials, achievingresults within six iterations and synthesizing 24 experimentalgroups. The final QY nearly doubled the initial best QY inthe training dataset.
Optimize the quantum yield of G‐quartet‐based circularly polarized luminescence materials via active learning strategy‐BgoFace
Li Tianliang*, Chen Lifei*, Cao Bin*, Liu Siyuan, Lin Lixing, Li Zeyu, Chen Yingying, Li Zhenzhen, Zhang Tongyi#, Feng Linyan# (* equal contribution, # corresponding author)
MGE advances 2025
This work developed an integrated AL software, BgoFace, which satisfies most material property optimization re-quirements. The application of BgoFace (with default setting) successfully accel-erated the discovery of G4-based CPL materials, achievingresults within six iterations and synthesizing 24 experimentalgroups. The final QY nearly doubled the initial best QY inthe training dataset.
Materials Generation in the Era of Artificial Intelligence: A Comprehensive Survey
Li Zhixun*, Cao Bin*, Jiao Rui*, Wang Liang*, Wang Ding, Liu Yang, Chen Dingshuo, Li Jia, Liu Yu, Wang Liang, Zhang Tongyi, Yu Xu Jeffrey (* equal contribution)
arXiv 2025
We first organize various types of materials and illustrate multiple representations of crystalline materials. We then provide a detailed summary and taxonomy of current AI-driven materials generation approaches. Furthermore, we discuss the common evaluation metrics and summarize open-source codes and benchmark datasets. Finally, we conclude with potential future directions and challenges in this fast-growing field.
Materials Generation in the Era of Artificial Intelligence: A Comprehensive Survey
Li Zhixun*, Cao Bin*, Jiao Rui*, Wang Liang*, Wang Ding, Liu Yang, Chen Dingshuo, Li Jia, Liu Yu, Wang Liang, Zhang Tongyi, Yu Xu Jeffrey (* equal contribution)
arXiv 2025
We first organize various types of materials and illustrate multiple representations of crystalline materials. We then provide a detailed summary and taxonomy of current AI-driven materials generation approaches. Furthermore, we discuss the common evaluation metrics and summarize open-source codes and benchmark datasets. Finally, we conclude with potential future directions and challenges in this fast-growing field.
Interpretable Active Learning Identifies Iron-Doped Carbon Dots With High Photothermal Conversion Efficiency for Antitumor Synergistic Therapy
Li Tianliang*, Cao Bin*, Wang Yitong, Lin Lixing, Chen Lifei, Su Tianhao, Song Haicheng, Ren Yuze, Zhang Longhan, Chen Yingying, Li Zhenzhen, Feng Linyan#, Zhang Tongyi# (* equal contribution, # corresponding author)
Aggregate 2025
We apply an interpretable AL strategy to efficiently optimize the photothermal conversion efficiency (PCE) of carbon dots (CDs) in photothermal therapy (PTT). Using this approach, we successfully synthesized irondoped CDs (Fe-CDs) with PCE exceeding 78.7% after only 16 experimental trials over four iterations.
Interpretable Active Learning Identifies Iron-Doped Carbon Dots With High Photothermal Conversion Efficiency for Antitumor Synergistic Therapy
Li Tianliang*, Cao Bin*, Wang Yitong, Lin Lixing, Chen Lifei, Su Tianhao, Song Haicheng, Ren Yuze, Zhang Longhan, Chen Yingying, Li Zhenzhen, Feng Linyan#, Zhang Tongyi# (* equal contribution, # corresponding author)
Aggregate 2025
We apply an interpretable AL strategy to efficiently optimize the photothermal conversion efficiency (PCE) of carbon dots (CDs) in photothermal therapy (PTT). Using this approach, we successfully synthesized irondoped CDs (Fe-CDs) with PCE exceeding 78.7% after only 16 experimental trials over four iterations.
opXRD: Open Experimental Powder X-Ray DiffractionDatabase
Daniel Hollarek, Henrik Schopmans, Jona Östreicher, Jonas Teufel, Cao Bin, ..., Zhang Tongyi, Pascal Friederich# (# corresponding author)
Advanced Intelligent Discovery 2025
With the Open Experimental Powder X-ray Diffraction Database (opXRD), we providean openly available and easily accessible dataset of labeled and unlabeled experimental powder diffractograms. Labeled opXRDdata can be used to evaluate the performance of models on experimental data and unlabeled opXRD data can help improve theperformance of models on experimental data, for example, through transfer learning methods. We collected 92,552 diffractograms,2179 of them labeled, from a wide spectrum of material classes. We hope this ongoing effort can guide machine learning researchtoward fully automated analysis of pXRD data and thus enable future self-driving materials labs.
opXRD: Open Experimental Powder X-Ray DiffractionDatabase
Daniel Hollarek, Henrik Schopmans, Jona Östreicher, Jonas Teufel, Cao Bin, ..., Zhang Tongyi, Pascal Friederich# (# corresponding author)
Advanced Intelligent Discovery 2025
With the Open Experimental Powder X-ray Diffraction Database (opXRD), we providean openly available and easily accessible dataset of labeled and unlabeled experimental powder diffractograms. Labeled opXRDdata can be used to evaluate the performance of models on experimental data and unlabeled opXRD data can help improve theperformance of models on experimental data, for example, through transfer learning methods. We collected 92,552 diffractograms,2179 of them labeled, from a wide spectrum of material classes. We hope this ongoing effort can guide machine learning researchtoward fully automated analysis of pXRD data and thus enable future self-driving materials labs.
SimXRD-4M: Big Simulated X-ray Diffraction Data and Crystal Symmetry Classification Benchmark
Cao Bin*, Liu Yang*, Zheng Zinan*, Tan Ruifeng, Li Jia#, Zhang Tongyi# (* equal contribution, # corresponding author)
International Conference on Learning Representations (ICLR) 2025 Top tier AI conference
We developed a novel XRD simulation method that incorporates comprehensive physical interactions, resulting in a high-fidelity database. SimXRD comprises 4,065,346 simulated powder XRD patterns, representing 119,569 unique crystal structures under 33 simulated conditions that reflect real-world variations. We benchmark 21 sequence models in both in-library and out-of-library scenarios and analyze the impact of class imbalance in longtailed crystal label distributions. Remarkably, we find that: (1) current neural networks struggle with classifying low-frequency crystals, particularly in out-oflibrary situations; (2) models trained on SimXRD can generalize to real experimental data.
SimXRD-4M: Big Simulated X-ray Diffraction Data and Crystal Symmetry Classification Benchmark
Cao Bin*, Liu Yang*, Zheng Zinan*, Tan Ruifeng, Li Jia#, Zhang Tongyi# (* equal contribution, # corresponding author)
International Conference on Learning Representations (ICLR) 2025 Top tier AI conference
We developed a novel XRD simulation method that incorporates comprehensive physical interactions, resulting in a high-fidelity database. SimXRD comprises 4,065,346 simulated powder XRD patterns, representing 119,569 unique crystal structures under 33 simulated conditions that reflect real-world variations. We benchmark 21 sequence models in both in-library and out-of-library scenarios and analyze the impact of class imbalance in longtailed crystal label distributions. Remarkably, we find that: (1) current neural networks struggle with classifying low-frequency crystals, particularly in out-oflibrary situations; (2) models trained on SimXRD can generalize to real experimental data.
Enhancing the performance of Li-rich oxide cathodes through multifunctional surface engineering
Lei Tongxing, Cao Guolin, Shi Xiuling, Cao Bin, Ding Zhiyu, Bai Yu, Wu Junwei#, Li Kaikai#, Zhang Tongyi# (# corresponding author)
Journal of Power Sources 2025
Herein, a multifunctional surface engineering is successfully applied to improve Li1.2Mn0.54Co0.13Ni0.13O2 materials by a facile method of solution pretreatment followed by high-temperature thermal treatment. Gradient fluorine doping on the near-surface region is demonstrated to induce the higher ratio of Mn3+/Mn4+, the increasing amounts of oxygen vacancies and the decreasing Li+ diffusion energy barrier.
Enhancing the performance of Li-rich oxide cathodes through multifunctional surface engineering
Lei Tongxing, Cao Guolin, Shi Xiuling, Cao Bin, Ding Zhiyu, Bai Yu, Wu Junwei#, Li Kaikai#, Zhang Tongyi# (# corresponding author)
Journal of Power Sources 2025
Herein, a multifunctional surface engineering is successfully applied to improve Li1.2Mn0.54Co0.13Ni0.13O2 materials by a facile method of solution pretreatment followed by high-temperature thermal treatment. Gradient fluorine doping on the near-surface region is demonstrated to induce the higher ratio of Mn3+/Mn4+, the increasing amounts of oxygen vacancies and the decreasing Li+ diffusion energy barrier.
2024
Machine Learning-Engineered Nanozyme System for Synergistic Anti-Tumor Ferroptosis/Apoptosis Therapy
Li Tianliang*, Cao Bin*, Su Tianhao*, Lin Lixing, Wang Dong, Liu Xinting, Wan haoyu, Ji Haiwei, He Zixuan, Chen Yingying, Feng Lingyan#, Zhang Tongyi (* equal contribution, # corresponding author)
Small 2024
A novel ML model, termed the sequential backward Tree-Classifier for Gaussian Process Regression (TCGPR), is proposed to improve data pattern recognition following the divide-and-conquer principle.
Machine Learning-Engineered Nanozyme System for Synergistic Anti-Tumor Ferroptosis/Apoptosis Therapy
Li Tianliang*, Cao Bin*, Su Tianhao*, Lin Lixing, Wang Dong, Liu Xinting, Wan haoyu, Ji Haiwei, He Zixuan, Chen Yingying, Feng Lingyan#, Zhang Tongyi (* equal contribution, # corresponding author)
Small 2024
A novel ML model, termed the sequential backward Tree-Classifier for Gaussian Process Regression (TCGPR), is proposed to improve data pattern recognition following the divide-and-conquer principle.
A universal strategy towards high-rate and ultralong-life of Li‐rich Mn‐based cathode materials
Fu Wenbo, Lei Tongxing, Cao Bin, Shi Xiuling, Zhang Qi, Ding Zhiyu, Chen Lina#, Wu Junwei# (# corresponding author)
Journal of Power Sources 2024
we employed a simple citric acid treatment (CA-treatment) method to fabricate the Li-rich spinel coating layer on LRMs. This in situ formed spinel Li4Mn5O12 layer successfully suppresses the oxygen release, provides three-dimensional (3D) lithium-ion diffusion channels and enriches Li embedding sites, resulting in a substantial improvement in the rate capability and high-rate cycling performance.
A universal strategy towards high-rate and ultralong-life of Li‐rich Mn‐based cathode materials
Fu Wenbo, Lei Tongxing, Cao Bin, Shi Xiuling, Zhang Qi, Ding Zhiyu, Chen Lina#, Wu Junwei# (# corresponding author)
Journal of Power Sources 2024
we employed a simple citric acid treatment (CA-treatment) method to fabricate the Li-rich spinel coating layer on LRMs. This in situ formed spinel Li4Mn5O12 layer successfully suppresses the oxygen release, provides three-dimensional (3D) lithium-ion diffusion channels and enriches Li embedding sites, resulting in a substantial improvement in the rate capability and high-rate cycling performance.
CGWGAN: crystal generative framework based on Wyckoff generative adversarial network
Su Tianhao*, Cao Bin*, Hu Shunbo, Li Musen, Zhang Tongyi# (* equal contribution, # corresponding author)
journal of material informatics 2024
In this work, we present a crystal generative framework based on Wyckoff generative adversarial network (CGWGAN) to efficiently discover novel crystals.
CGWGAN: crystal generative framework based on Wyckoff generative adversarial network
Su Tianhao*, Cao Bin*, Hu Shunbo, Li Musen, Zhang Tongyi# (* equal contribution, # corresponding author)
journal of material informatics 2024
In this work, we present a crystal generative framework based on Wyckoff generative adversarial network (CGWGAN) to efficiently discover novel crystals.
A Li-rich layered oxide cathode with remarkable capacity and prolonged cycle life
Lei Tongxing, Cao Bin, Fu Wenbo, Shi Xiuling, Ding Zhiyu, Zhang Qi, Wu Junwei#, Li Kaikai#, Zhang Tongyi# (# corresponding author)
Chemical Engineering Journal 2024
Introducing a facile ion-exchange method coupled with low-temperature thermal treatment, we have developed a strategy to enhance the cycling performance of Lithium-rich manganese-based layered oxides (LLOs).
A Li-rich layered oxide cathode with remarkable capacity and prolonged cycle life
Lei Tongxing, Cao Bin, Fu Wenbo, Shi Xiuling, Ding Zhiyu, Zhang Qi, Wu Junwei#, Li Kaikai#, Zhang Tongyi# (# corresponding author)
Chemical Engineering Journal 2024
Introducing a facile ion-exchange method coupled with low-temperature thermal treatment, we have developed a strategy to enhance the cycling performance of Lithium-rich manganese-based layered oxides (LLOs).
Crystallographic Phase Identifier of a Convolutional Self-Attention Neural Network (CPICANN) on Powder Diffraction Patterns
Zhang Shouyang*, Cao Bin*, Su Tianhao, Wu Yue, Feng Zhenjie, Xiong Jie#, Zhang Tongyi# (* equal contribution, # corresponding author)
IUCrJ 2024
In this work, we developed a machine learning phase identifier that achieved excellent performance for structure identification from powder diffraction patterns.
Crystallographic Phase Identifier of a Convolutional Self-Attention Neural Network (CPICANN) on Powder Diffraction Patterns
Zhang Shouyang*, Cao Bin*, Su Tianhao, Wu Yue, Feng Zhenjie, Xiong Jie#, Zhang Tongyi# (* equal contribution, # corresponding author)
IUCrJ 2024
In this work, we developed a machine learning phase identifier that achieved excellent performance for structure identification from powder diffraction patterns.
Active Learning Accelerates the Discovery of High Strength and High Ductility Lead-Free Solder Alloys
Cao Bin, Su Tianhao, Yv Shuting, Li Tianyuan, Zhang Taolue, Dong Ziqiang#, Zhang Tongyi# (# corresponding author)
Materials & Design 2024
To facilitate materials informatics development, all active learning algorithms were made open-source in our designed framework, Bgolearn
Active Learning Accelerates the Discovery of High Strength and High Ductility Lead-Free Solder Alloys
Cao Bin, Su Tianhao, Yv Shuting, Li Tianyuan, Zhang Taolue, Dong Ziqiang#, Zhang Tongyi# (# corresponding author)
Materials & Design 2024
To facilitate materials informatics development, all active learning algorithms were made open-source in our designed framework, Bgolearn
MLMD: a programming-free AI platform to predict and design materials
Ma Jiaxuan*, Cao Bin*, Dong Shuya, Tian Yuan, Wang Menghuan, Xiong Jie#, Sun Sheng# (* equal contribution, # corresponding author)
npj Computational Materials 2024
We developed MLMD, an AI platform for materials design. It is capable of effectively discovering novel materials with high-potential advanced properties end-to-end, utilizing model inference, surrogate optimization, and even working in situations of data scarcity based on active learning.
MLMD: a programming-free AI platform to predict and design materials
Ma Jiaxuan*, Cao Bin*, Dong Shuya, Tian Yuan, Wang Menghuan, Xiong Jie#, Sun Sheng# (* equal contribution, # corresponding author)
npj Computational Materials 2024
We developed MLMD, an AI platform for materials design. It is capable of effectively discovering novel materials with high-potential advanced properties end-to-end, utilizing model inference, surrogate optimization, and even working in situations of data scarcity based on active learning.
Machine learning-assisted composition design of W-free Co-based superalloys with high γ′-solvus temperature and low density
Sun Linlin, Cao Bin, Ma Qingshuang, Gao Qiuzhi#, Luo Jiahao, Gong Minglong, Bai Jing# (# corresponding author)
Journal of Materials Research and Technology 2024
This article validates a straightforward strategy to guide rapid discovery and fabrication of multi-component materials with desired dual-performance characteristics.
Machine learning-assisted composition design of W-free Co-based superalloys with high γ′-solvus temperature and low density
Sun Linlin, Cao Bin, Ma Qingshuang, Gao Qiuzhi#, Luo Jiahao, Gong Minglong, Bai Jing# (# corresponding author)
Journal of Materials Research and Technology 2024
This article validates a straightforward strategy to guide rapid discovery and fabrication of multi-component materials with desired dual-performance characteristics.
2023
Divide and conquer: Machine learning accelerated design of lead-free solder alloys with high strength and high ductility
Wei Qinghua*, Cao Bin*, Yuan Hao*, Chen Youyang, You Kangdong, Yv Shuting, Yang Tixin, Dong Ziqiang#, Zhang Tongyi# (* equal contribution, # corresponding author)
npj Computational Materials 2023
In general, small in size and big in noise, while the design space is huge, by a newly developed data preprocessing algorithm, named the Tree-Classifier for Gaussian Process Regression (TCGPR)….
Divide and conquer: Machine learning accelerated design of lead-free solder alloys with high strength and high ductility
Wei Qinghua*, Cao Bin*, Yuan Hao*, Chen Youyang, You Kangdong, Yv Shuting, Yang Tixin, Dong Ziqiang#, Zhang Tongyi# (* equal contribution, # corresponding author)
npj Computational Materials 2023
In general, small in size and big in noise, while the design space is huge, by a newly developed data preprocessing algorithm, named the Tree-Classifier for Gaussian Process Regression (TCGPR)….
Orthorhombic (Ru, Mn)2O3: A superior electrocatalyst for acidic oxygen evolution reaction
Qin Yin, Cao Bin, Zhou Xiaoye#, Xiao Zhuorui, Zhou Hanxiang, Zhao Zhenyi, Weng Yibo, Lv Jianshuai, Liu Yang, He Yan-Bing, Kang Feiyu, Li Kaikai#, Zhang Tongyi# (# corresponding author)
Nano Energy 2023
The present work, for the first time, successfully synthesizes orthorhombic (Ru, Mn)2O3 electrocatalyst through cation exchange. The orthorhombic (Ru, Mn)2O3 particles exhibit the outstanding electrocatalysis performance as OER electrocatalyst, showing an ultralow overpotential of 168 mV at 10 mA cm−2 in acidic water and good stability in 40 h of OER.
Orthorhombic (Ru, Mn)2O3: A superior electrocatalyst for acidic oxygen evolution reaction
Qin Yin, Cao Bin, Zhou Xiaoye#, Xiao Zhuorui, Zhou Hanxiang, Zhao Zhenyi, Weng Yibo, Lv Jianshuai, Liu Yang, He Yan-Bing, Kang Feiyu, Li Kaikai#, Zhang Tongyi# (# corresponding author)
Nano Energy 2023
The present work, for the first time, successfully synthesizes orthorhombic (Ru, Mn)2O3 electrocatalyst through cation exchange. The orthorhombic (Ru, Mn)2O3 particles exhibit the outstanding electrocatalysis performance as OER electrocatalyst, showing an ultralow overpotential of 168 mV at 10 mA cm−2 in acidic water and good stability in 40 h of OER.
Discovering a formula for the high temperature oxidation behavior of FeCrAlCoNi based high entropy alloys by domain knowledge-guided machine learning Author links open overlay panel
Wei Qinghua, Cao Bin, Deng Lucheng, Sun Ankang, Dong Ziqiang#, Zhang Tongyi# (# corresponding author)
Journal of Materials Science & Technology 2023
The Tree-Classifier for Linear Regression (TCLR) algorithm utilizes the two experimental features of exposure time (t) and temperature (T) to extract the spectrums of activation energy (Q) and time exponent (m) from the complex and high dimensional feature space, which automatically gives the spectrum of pre-factor. The three spectrums are assembled by using the element features, which leads to a general and interpretive formula with high prediction accuracy of the determination coefficient =0.971.
Discovering a formula for the high temperature oxidation behavior of FeCrAlCoNi based high entropy alloys by domain knowledge-guided machine learning Author links open overlay panel
Wei Qinghua, Cao Bin, Deng Lucheng, Sun Ankang, Dong Ziqiang#, Zhang Tongyi# (# corresponding author)
Journal of Materials Science & Technology 2023
The Tree-Classifier for Linear Regression (TCLR) algorithm utilizes the two experimental features of exposure time (t) and temperature (T) to extract the spectrums of activation energy (Q) and time exponent (m) from the complex and high dimensional feature space, which automatically gives the spectrum of pre-factor. The three spectrums are assembled by using the element features, which leads to a general and interpretive formula with high prediction accuracy of the determination coefficient =0.971.
2022
Domain knowledge-guided interpretive machine learning: formula discovery for the oxidation behavior of ferritic-martensitic steels in supercritical water
Cao Bin, Yang Shuang, Sun Ankang, Dong Ziqing#, Zhang Tongyi# (# corresponding author)
journal of material informatics 2022 Cover Paper & 2024 Best Paper Award
In this study, we propose a domain knowledge-guided interpretive machine learning strategy and demonstrate it by studying the oxidation behavior of ferritic-martensitic steels in supercritical water…
Domain knowledge-guided interpretive machine learning: formula discovery for the oxidation behavior of ferritic-martensitic steels in supercritical water
Cao Bin, Yang Shuang, Sun Ankang, Dong Ziqing#, Zhang Tongyi# (# corresponding author)
journal of material informatics 2022 Cover Paper & 2024 Best Paper Award
In this study, we propose a domain knowledge-guided interpretive machine learning strategy and demonstrate it by studying the oxidation behavior of ferritic-martensitic steels in supercritical water…