arXiv subjects

Tong-Yi Zhang

Publications and source records attributed to Tong-Yi Zhang.

16 recordsLinked to original sources

arXiv2026

Bgolearn: a Unified Bayesian Optimization Framework for Accelerating Materials Discovery

Efficient exploration of vast compositional and processing spaces remains a major challenge in accelerated materials discovery. Bayesian optimization (BO) provides a principled approach to identify optimal materials with minimal experimentation, but its adoption has been limited by implementation complexity and a lack of domain-specific tools. Here, we present Bgolearn, a versatile Python framework that brings BO to materials research through intuitive interfaces, robust algorithms, and materials-focused workflows. Bgolearn supports single- and multi-objective optimization, multiple acquisition strategies, diverse surrogate models, and uncertainty quantification, enabling effective navigation of complex design spaces. Benchmark studies show that Bgolearn reduces experimental effort by 40-60\% compared with random search, grid search, and genetic algorithms, while achieving comparable or superior solution quality. Its effectiveness is demonstrated across case studies, including the discovery of maximum-elastic-modulus triply periodic minimal surface structures, ultra-high-hardness high-entropy alloys, and high-strength, high-ductility medium-Mn steels, and is further supported by numerous publications. With a modular architecture that integrates seamlessly into existing materials workflows and a graphical interface (BgoFace) that removes programming barriers, Bgolearn establishes a practical, reliable platform for Bayesian optimization in materials science. The software is openly available at https://github.com/Bin-Cao/Bgolearn.

cond-mat.mtrl-sci↗

arXiv2026

Pretrained battery transformer (PBT): A foundation model for battery life prediction

Early prediction of battery cycle life is essential for improving battery design, manufacturing and deployment. However, despite encouraging progress with machine learning, battery life prediction remains constrained by scarce data and pronounced heterogeneity across battery chemistries, specifications, formation protocols and operating conditions. Although transfer learning has been widely explored to alleviate these challenges, its effectiveness is limited by the absence of a foundation model that can integrate heterogeneous battery life data and provide broadly useful knowledge for target-scenario specialization. Here we introduce the pretrained battery transformer (PBT), a foundation model for battery life prediction that incorporates battery-knowledge-encoded mixture-of-experts layers to learn from scarce and heterogeneous lifetime data. PBT is first pretrained on 13 lithium-ion battery datasets to yield a general PBT that encodes comprehensive battery lifetime knowledge, and is then adapted through transfer learning into specialized PBT models for target scenarios. Across 15 datasets covering 977 batteries and 528 sets of aging conditions from lithium-ion, sodium-ion and zinc-ion batteries, PBT achieves state-of-the-art performance, surpassing the strongest competing method by 21.9% on average, with gains of up to 86.9%. This study establishes, to our knowledge, the first foundation model for battery life prediction and provides a step towards shifting battery lifetime prediction from isolated, scenario-specific modelling tasks to a reusable knowledge foundation that can be specialized to target scenarios with limited data, with implications for other prediction problems characterized by scarce and heterogeneous data in sustainable energy.

cs.LG↗

arXiv2026

BatteryMFormer: Multi-level Learning for Battery Degradation Trajectory Forecasting

Early battery degradation trajectory forecasting (BDTF), which predicts the full-life state-of-health trajectory from early operational data, is critical for battery optimization, manufacturing, and deployment. Battery degradation data exhibit two key characteristics. First, degradation data present a multi-level structure, including regularities shared within aging conditions and trajectory patterns shared across batteries. Second, degradation-related variations in voltage-current profiles are often localized to specific state of charge (SOC) intervals. Existing approaches often fail to explicitly model these characteristics. To bridge this gap, we propose BatteryMFormer, a multi-level Transformer for early BDTF. BatteryMFormer integrates (1) an aging-condition-aware decoder that injects aging-condition priors via aging-condition-informed queries and aging-condition-aware attention, (2) a meta degradation pattern memory that learns and retrieves trajectory prototypes to guide long-horizon forecasting, and (3) a dual-view encoder that jointly captures temporal dynamics and SOC-localized variations from voltage and current time series. Extensive experiments on four battery domains show that BatteryMFormer consistently outperforms state-of-the-art baselines, marking a significant step toward reliable BDTF. Our code is available at https://github.com/Ruifeng-Tan/BatteryMFormer.

cs.AI↗

arXiv2026

XDecomposer: Learning Prior-Free Set Decomposition for Multiphase X-ray Diffraction

Multiphase powder X-ray diffraction (PXRD) analysis remains a fundamental bottleneck in structure identification, as real-world synthesis often produces complex mixtures whose constituent phases (components) cannot be reliably disentangled. While recent advances in representation-based crystal retrieval and generation suggest the possibility of inferring structures directly from PXRD, existing approaches largely assume single-phase inputs and break down in multiphase settings. Here, we present XDecomposer, a prior-free framework for joint decomposition and identification of multiphase XRD patterns without requiring candidate phase lists, structural templates, or prior knowledge of phase number. We formulate multiphase diffraction analysis as a set prediction problem, where the model infers an unordered set of phase-resolved components, their mixture proportions, and corresponding structural representations within a unified architecture. A phase-query-driven decomposition mechanism, together with diffraction-consistent physical reconstruction, enables accurate source separation while preserving crystallographic fidelity. Extensive experiments on both simulated and experimental datasets show that XDecomposer substantially improves reconstruction accuracy and phase identification across diverse chemical systems, while maintaining strong generalization to unseen mixtures. These results provide a practical route toward data-driven, source-resolved multiphase XRD analysis and reduce long-standing dependence on prior-guided iteratively phase matching. The code is openly available at https://github.com/Licht0812/XDecomposer

cs.AI↗

arXiv2026

DeePAW: A universal machine learning model for orbital-free ab initio calculations

Developing universal machine learning models for ab initio calculations is the frontier of materials cutting edge research in the new era of artificial intelligence. Here, we present the Deep Augment Way model (DeePAW) that is a universal machine learning (ML) model for orbital-free (OF) ab initio calculations, based on the density functional theory (DFT). DeePAW is currently the best OFDFT ML model according to the three criterions, 1) covering the largest number of elements, 2) having the widest application capability to diverse crystal structures, and 3) achieving the highest prediction accuracy without further fine-tuning. These scientific merits and innovations of DeePAW are stemmed from the novel SE(3)-equivariant double massage passing neuron networks. Besides predicting electron density distributions, DeePAW predicts formation energies of crystals as well and therefore paves an efficient avenue for multiscale materials modeling beyond conventional electronic structure calculation methods.

cond-mat.mtrl-sci↗

arXiv2026

AI-Driven Structure Refinement of X-ray Diffraction

Artificial intelligence can rapidly propose candidate phases and structures from X-ray diffraction (XRD), but these hypotheses often fail in downstream refinement because peak intensities cannot be stably assigned under severe overlap and diffraction consistency is enforced only weakly. Here we introduce the whole-pattern expectation--maximization (WPEM) algorithm, a physics-constrained whole-pattern decomposition and refinement workflow that turns Bragg's law into an explicit constraint within a batch expectation--maximization framework. WPEM models the full profile as a probabilistic mixture density and iteratively infers component-resolved intensities while keeping peak centres Bragg-consistent, producing a continuous, physically admissible intensity representation that remains stable in heavily overlapped regions and in the presence of mixed radiation or multiple phases. We benchmark WPEM on standard reference patterns (PbSO$_4$ and Tb$_2$BaCoO$_5$), where it yields lower $R_p/R_{wp}$ than widely used packages (FullProf and TOPAS) under matched refinement conditions. We further demonstrate generality across realistic experimental scenarios, including phase-resolved decomposition in multiphase materials, quantitative recovery of mixture compositions, separation of crystalline peaks from amorphous backgrounds in semicrystalline systems, high-throughput operando lattice tracking, automated refinement of compositionally disordered solid solutions, and quantitative phase-resolved analysis of complex archaeological samples from synchrotron powder XRD. By providing Bragg-consistent, uncertainty-aware intensity partitioning as a refinement-ready interface, WPEM closes the gap between AI-generated hypotheses and diffraction-admissible structure refinement on challenging XRD data.

cond-mat.mtrl-sci↗

arXiv2026

Beyond Structure: Invariant Crystal Property Prediction with Pseudo-Particle Ray Diffraction

Crystal property prediction, governed by quantum mechanical principles, is computationally prohibitive to solve exactly for large many-body systems using traditional density functional theory. While machine learning models have emerged as efficient approximations for large-scale applications, their performance is strongly influenced by the choice of atomic representation. Although modern graph-based approaches have progressively incorporated more structural information, they often fail to capture long-range atomic interactions due to finite receptive fields and local encoding schemes. This limitation leads to distinct crystals being mapped to identical representations, hindering accurate property prediction. To address this, we introduce PRDNet that leverages unique reciprocal-space diffraction besides graph representations. To enhance sensitivity to elemental and environmental variations, we employ a data-driven pseudo-particle to generate a synthetic diffraction pattern. PRDNet ensures full invariance to crystallographic symmetries. Extensive experiments are conducted on Materials Project, JARVIS-DFT, and MatBench, demonstrating that the proposed model achieves state-of-the-art performance. The code is openly available at https://github.com/Bin-Cao/PRDNet.

cond-mat.mtrl-sci↗

arXiv2025

BatteryLife: A Comprehensive Dataset and Benchmark for Battery Life Prediction

Battery Life Prediction (BLP), which relies on time series data produced by battery degradation tests, is crucial for battery utilization, optimization, and production. Despite impressive advancements, this research area faces three key challenges. Firstly, the limited size of existing datasets impedes insights into modern battery life data. Secondly, most datasets are restricted to small-capacity lithium-ion batteries tested under a narrow range of diversity in labs, raising concerns about the generalizability of findings. Thirdly, inconsistent and limited benchmarks across studies obscure the effectiveness of baselines and leave it unclear if models popular in other time series fields are effective for BLP. To address these challenges, we propose BatteryLife, a comprehensive dataset and benchmark for BLP. BatteryLife integrates 16 datasets, offering a 2.5 times sample size compared to the previous largest dataset, and provides the most diverse battery life resource with batteries from 8 formats, 59 chemical systems, 9 operating temperatures, and 421 charge/discharge protocols, including both laboratory and industrial tests. Notably, BatteryLife is the first to release battery life datasets of zinc-ion batteries, sodium-ion batteries, and industry-tested large-capacity lithium-ion batteries. With the comprehensive dataset, we revisit the effectiveness of baselines popular in this and other time series fields. Furthermore, we propose CyclePatch, a plug-in technique that can be employed in various neural networks. Extensive benchmarking of 18 methods reveals that models popular in other time series fields can be unsuitable for BLP, and CyclePatch consistently improves model performance establishing state-of-the-art benchmarks. Moreover, BatteryLife evaluates model performance across aging conditions and domains. BatteryLife is available at https://github.com/Ruifeng-Tan/BatteryLife.

cs.LG↗

arXiv2025

KAN-Enhanced Contrastive Learning Accelerating Crystal Structure Identification from XRD Patterns

Accurate determination of crystal structures is central to materials science, underpinning the understanding of composition-structure-property relationships and the discovery of new materials. Powder X-ray diffraction is a key technique in this pursuit due to its versatility and reliability. However, current analysis pipelines still rely heavily on expert knowledge and slow iterative fitting, limiting their scalability in high-throughput and autonomous settings. Here, we introduce a physics-guided contrastive learning framework termed as XCCP. It aligns powder diffraction patterns with candidate crystal structures in a shared embedding space to enable efficient structure retrieval and symmetry recognition. The XRD encoder employs a dual-expert design with a Kolmogorov-Arnold Network projection head, one branch emphasizes low angle reflections reflecting long-range order, while the other captures dense high angle peaks shaped by symmetry. Coupled with a crystal graph encoder, contrastive pretraining yields physically grounded representations. XCCP demonstrates strong performance across tasks, with structure retrieval reaching 0.89 and space group identification attains 0.93 accuracy. The framework further generalizes to compositionally similar multi principal element alloys and demonstrates zero-shot transfer to experimental patterns. These results establish XCCP as a robust, interpretable, and scalable approach that offers a new paradigm for X-ray diffraction analysis. XCCP facilitates high-throughput screening, rapid structural validation and integration into autonomous laboratories.

cond-mat.mtrl-sci↗

arXiv2023

Unraveling the Complexity of Metal Ion Dissolution: Insights from Hybrid First-Principles/Continuum Calculations

The study of ion dissolution from metal surfaces has a long-standing history, wherein the gradual dissolution of solute atoms with increasing electrode potential, leading to their existence as ions in the electrolyte with integer charges, is well-known. However, our present work reveals a more intricate and nuanced physical perspective based on comprehensive first-principles/continuum calculations. We investigate the dissolution and deposition processes of 22 metal elements across a range of applied electrode potentials, unveiling diverse dissolution models. By analyzing the energy profiles and valence states of solute atoms as a function of the distance between the solute atom and metal surface, we identify three distinct dissolution models for different metals. Firstly, solute atoms exhibit an integer valence state following an integer-valence jump, aligning with classical understandings. Secondly, solute atoms attain an eventual integer valence, yet their valence state increases in a non-integer manner during dissolution. Lastly, we observe solute atoms exhibiting a non-integer valence state, challenging classical understandings. Furthermore, we propose a theoretical criterion for determining the selection of ion valence during electrode dissolution under applied potential. These findings not only contribute to a deeper understanding of the dissolution process but also offer valuable insights into the complex dynamics governing metal ion dissolution at the atomic level. Such knowledge has the potential to advance the design of more efficient electrochemical systems and open new avenues for controlling dissolution processes in various applications.

cond-mat.mtrl-sci↗

arXiv2021

Accelerated design of linear-superelastic Ti-Nb nanocomposite alloys with ultralow modulus via high-throughput phase-field simulations and machine learning

The controlled design of martensitic transformation (MT) to achieve specific properties is crucial for the innovative application of shape memory alloys (SMAs) in advanced technologies. Herein, we explore and design the MT behaviors and the mechanical properties of Ti-Nb nanocomposites by combining high-throughput phase-field simulations and machine learning (ML) approaches. Based on the systematic phase-field simulations, we obtain data sets of the mechanical properties for various nanocomposites constructed by four macroscopic degrees of freedom, which can be employed to design and optimize the microstructures for different applications. To accelerate the phase-field screening of the desired metallic biomaterials, a ML assisted strategy is adopted to perform multi-objective optimization of the mechanical properties, through which promising nanocomposite configurations are pre-screened for the next set of phase-field simulations. With the ML guided simulations, an optimized candidate composed of Nb-rich matrix and Nb-lean nanofillers that exhibits a combination of unprecedented mechanical properties, including ultra-low modulus, linear super-elasticity, and near-hysteresis-free is designed. The exceptional mechanical properties in the nanocomposite originate from optimized continuous MT rather than a sharp first-order transition, which is common in typical SMAs. This work provides a new computational approach and design concept for developing novel functional materials with extraordinary properties.

cond-mat.mtrl-sci↗

arXiv2021

Phase field simulation of grain size effects in nanograined Ti-Nb shape memory alloys

Titanium-based shape memory alloys, such as Ti2448, have attracted enormous attention owing to their unique thermomechanical properties and potential biomedical applications. In this study, we develop a polycrystalline phase field to investigate the grain size dependence of the martensitic transformation and associated mechanical properties of nanograined Ti-Nb alloys. It is shown that a reduction of the average grain size strengthens the suppression of the martensitic transformation (MT), leading to an increase of the transformation stress, shrinkage of the stress hysteresis, and elimination of residual strain. The time-temperature-transformation curves of nano-grained Ti-Nb alloys with different average grain sizes are obtained and the validity of Hall-Petch relation is also confirmed in all studied grain sizes. Furthermore, when the average grain size becomes ultrasmall, both the temperature- and stress-induced MTs show the continuous second-order phase transition behavior. These superior transformation characteristics are attributed to the high density of grain boundaries and the related dominant role of the gradient energy at the nanoscale. Our results have profound implications for the design and control of the properties in nano-grained shape memory alloys.

cond-mat.mtrl-sci↗

arXiv2020

Analysis of Phase Formations and Mechanical Properties in Complex Concentrated Alloys by Machine Learning Approach

The mechanical properties of complex concentrated alloys (CCAs) depend on their forming phases and corresponding structures, the prediction of the phase formation for a given CCA is essential to its discovery and applications. 541 sample were collected from previous studies, comprising 61 amorphous, 164 single-phase crystalline, and 361 multi-phases crystalline CCAs. We proposed three classification models to category and understand the phase selection of CCAS. Also, a two-objective regression model was constructed to predict the hardness and compressive yield stress of CCAs. All three classification models have accuracies higher than 85%, and correlation coefficient of random forest regression model is greater than 0.9 for both of two objectives. In addition, we proposed four descriptors via multi-task SISSO method to predict the mechanical properties of CCAs, the average correlation coefficient of SISSO models is higher than 0.85. The present work demonstrates the great potential of machine learning approach in the prediction of target properties in CCAs.

physics.app-ph↗

arXiv2020

Machine Learning of Mechanical Properties of Steels

The mechanical properties are essential for structural materials. The analyzed 360 data on four mechanical properties of steels, viz. fatigue strength, tensile strength, fracture strength, and hardness, are selected from the NIMS database, including carbon steels, and low-alloy steels. Five machine learning algorithms were applied on the 360 data to predict the mechanical properties and random forest regression illustrates the best performance. The feature selection was conducted by random forest and symbolic regressions, leading to the four most important features of tempering temperature, and alloying elements of carbon, chromium, and molybdenum to the mechanical properties of steels. Besides, mathematic expressions were generated via symbolic regression, and the expressions explicitly predict how each of the four mechanical properties varies quantitatively with the four most important features. The present work demonstrates the great potential of symbolic regression in the discovery of novel advanced materials.

physics.app-ph↗

arXiv2020

Two-dimensional metallic ferroelectricity in PbTe monolayer by electrostatic doping

Polar metals characterized by the simultaneous coexistence of ferroelectric distortions and metallicity have attracted tremendous attention. Developing such materials at low dimensions remains challenging since both conducting electrons and reduced dimensions are supposed to quench ferroelectricity. Here, based on first-principles calculations, we report the discovery of ferroelectric behavior in two-dimensional (2D) metallic materials with electrostatic doping, even though ferroelectricity is unconventional at the atomic scale. We reveal that PbTe monolayer is intrinsic ferroelectrics with pronounced out-of-plane electric polarization originated from its non-centrosymmetric buckled structure. The ferroelectric distortions can be preserved with carriers doping in the ferroelectric monolayer, which thus enables the doped PbTe monolayer to act as a 2D polar metal. With an effective Hamiltonian extracted from the parametrized energy space, we found that the elastic-polar mode interaction is of great importance for the existence of robust polar instability in the doped system. The application of this doping strategy is not specific to the present crystal, but is rather general to other 2D ferroelectrics to bring about the fascinating metallic ferroelectric properties. Our findings thus change conventional acknowledge in 2D materials and will facilitate the development of multifunctional material in low dimensions.

cond-mat.mtrl-sci↗

arXiv2015

Two-photon assisted clock comparison to picosecond precision

We have experimentally demonstrated a clock comparison scheme utilizing time-correlated photon pairs generated from the spontaneous parametric down conversion process of a laser pumped beta-barium borate crystal. The coincidence of two-photon events are analyzed by the cross correlation of the two time stamp sequences. Combining the coarse and fine part of the time differences at different resolutions, a 64 ps precision for clock synchronization has been realized. We also investigate the effects of hardware devices used in the system on the precision of clock comparison. The results indicate that the detector's time jitter and the background noise will degrade the system performance. With this method, comparison and synchronization of two remote clocks could be implemented with a precision at the level of a few tens of picoseconds.

physics.optics↗