Fundamental physics often confronts complex symbolic problems with few guiding exemplars or established principles.While artificial intelligence(AI)offers promise,its typical need for vast datasets to learn from hinde...Fundamental physics often confronts complex symbolic problems with few guiding exemplars or established principles.While artificial intelligence(AI)offers promise,its typical need for vast datasets to learn from hinders its use in these information-scarce frontiers.We introduce learning at criticality(LaC),a reinforcement learning scheme that tunes large language models(LLMs)to a sharp learning transition,addressing this information scarcity.At this transition,LLMs achieve peak generalization from minimal data,exemplified by 7-digit base-7 addition-a test of nontrivial arithmetic reasoning.To elucidate this peak,we analyze a minimal concept-network model designed to capture the essence of how LLMs might link tokens.Trained on a single exemplar,this model also undergoes a sharp learning transition.This transition exhibits hallmarks of a second-order phase transition,notably power-law distributed solution path lengths.At this critical point,the system maximizes a“critical thinking pattern”crucial for generalization,enabled by the underlying scale-free exploration.This suggests LLMs reach peak performance by operating at criticality,where such explorative dynamics enable the extraction of underlying operational rules.We demonstrate LaC in quantum field theory:an 8B-parameter LLM,tuned to its critical point by LaC using a few exemplars of symbolic Matsubara sums,solves unseen,higher-order problems,significantly outperforming far larger models.LaC thus leverages critical phenomena,a physical principle,to empower AI for complex,data-sparse challenges in fundamental physics.展开更多
Ultra-high temperature ceramics(UHTCs)exhibit a unique combination of excellent properties,including ultra-high melting point,excellent chemical stability,and good oxidation resistance,which make them promising candid...Ultra-high temperature ceramics(UHTCs)exhibit a unique combination of excellent properties,including ultra-high melting point,excellent chemical stability,and good oxidation resistance,which make them promising candidates for aerospace and nuclear applications.However,the degradation of hightemperature strength is one of the main limitations for their ultra-high temperature applications.Thus,searching for mechanisms that can help to develop high-performance UHTCs with good high-temperature mechanical properties is urgently needed.To achieve this goal,grain boundary segregation of a series of carbides,including conventional,medium entropy,and high entropy transition metal carbides,i.e.,Zr_(0.95)W_(0.05)C,TiZrHfC_(3),ZrHfNbTaC_(4),TiZrHfNbTaC_(5),were studied by atomistic simulations with a fitted Deep Potential(DP),and the effects of segregation on grain boundary strength were emphasized.For all the studied carbides,grain boundary segregations are realized,which are dominated by the atomic size effect.In addition,tensile simulations indicate that grain boundaries(GBs)will usually be strengthened due to segregation.Our simulation results reveal that grain boundary segregation may be a universal mechanism in enhancing the high-temperature strength of both conventional UHTCs and medium/high entropy UHTCs,since GBs play a key role in controlling the fracture of UHTCs at elevated temperatures.展开更多
Solid-state batteries have received increasing attention in scientific and industrial communities,which benefits from the intrinsically safe solid electrolytes(SEs).Although much effort has been devoted to designing S...Solid-state batteries have received increasing attention in scientific and industrial communities,which benefits from the intrinsically safe solid electrolytes(SEs).Although much effort has been devoted to designing SEs with high ionic conductivities,it is extremely difficult to fully understand the ionic diffusion mechanisms in SEs through conventional experimental and theoretical methods.Herein,the temperature-dependent concerted diffusion mechanism of ions in SEs is explored through machinelearning molecular dynamics,taking Li_(10)GeP_(2)S_(12) as a prototype.Weaker diffusion anisotropy,more disordered Li distributions,and shorter residence time are observed at a higher temperature.Arrhenius-type temperature dependence is maintained within a wide temperature range,which is attributed to the linear temperature dependence of jump frequencies of various concerted diffusion modes.These results provide a theoretical framework to understand the ionic diffusion mechanisms in SEs and deepen the understanding of the chemical origin of temperature-dependent concerted diffusions in SEs.展开更多
Multi-component alloys have demonstrated excellent performance in various applications,but the vast range of possible compositions and microstructures makes it challenging to identify optimized alloys for specific pur...Multi-component alloys have demonstrated excellent performance in various applications,but the vast range of possible compositions and microstructures makes it challenging to identify optimized alloys for specific purposes.To overcome this challenge,large-scale atomic simulation techniques have been widely used for the design and optimization of multi-component alloys.The capability and reliability of large-scale atomic simulations essentially rely on the quality of interatomic potentials that describe the interactions between atoms.This work provides a comprehensive summary of the latest advances in atomic simulation techniques for multi-component alloys.The focus is on interatomic potentials,including both conventional empirical potentials and newly developed machine learning potentials(MLPs).The fitting processes for different types of interatomic potentials applied to multi-component alloys are also discussed.Finally,the challenges and future perspectives in developing MLPs are thoroughly addressed.Overall,this review provides a valuable resource for researchers interested in developing optimized multicomponent alloys using atomic simulation techniques.展开更多
Molecular dynamics(MD)is an indispensable atomistic-scale computational tool widely-used in various disciplines.In the past decades,nearly all ab initio MD and machine-learning MD have been based on the general-purpos...Molecular dynamics(MD)is an indispensable atomistic-scale computational tool widely-used in various disciplines.In the past decades,nearly all ab initio MD and machine-learning MD have been based on the general-purpose central/graphics processing units(CPU/GPU),which are well-known to suffer from their intrinsic“memory wall”and“power wall”bottlenecks.Consequently,nowadays MD calculations with ab initio accuracy are extremely time-consuming and power-consuming,imposing serious restrictions on the MD simulation size and duration.To solve this problem,here we propose a special-purpose MD processing unit(MDPU),which could reduce MD time and power consumption by about 103 times(109 times)compared to state-of-the-art machine-learningMD(ab initio MD)based on CPU/GPU,while keeping ab initio accuracy.With significantly-enhanced performance,the proposed MDPU may pave a way for the accurate atomistic-scale analysis of large-size and/or longduration problems which were impossible/impractical to compute before.展开更多
The rapid advancements in artificial intelligence(AI)are catalyzing transformative changes in atomic modeling,simulation,and design.AI-driven potential energy models havedemonstrated the capability to conduct large-sc...The rapid advancements in artificial intelligence(AI)are catalyzing transformative changes in atomic modeling,simulation,and design.AI-driven potential energy models havedemonstrated the capability to conduct large-scale,long-duration simulations with the accuracy of ab initio electronic structure methods.However,the model generation process remains a bottleneck for large-scale applications.We propose a shift towards a model-centric ecosystem,wherein a large atomic model(LAM),pretrained across multiple disciplines,can be efficiently fine-tuned and distilled for various downstream tasks,thereby establishing a new framework for molecular modeling.In this study,we introduce the DPA-2 architecture as a prototype for LAMs.Pre-trained on a diverse array of chemical and materials systemsusing a multi-task approach,DPA-2demonstrates superior generalization capabilities across multiple downstream tasks compared to the traditional single-task pre-training and fine-tuning methodologies.Our approach sets the stage for the development and broad application of LAMs in molecular and materials simulation research.展开更多
Inspired by the single-atom catalysts(SACs)concept,we rationally design a series of Pt single atom catalysts embedded in different transition metal nanoclusters through first-principles calculations.In these so-called...Inspired by the single-atom catalysts(SACs)concept,we rationally design a series of Pt single atom catalysts embedded in different transition metal nanoclusters through first-principles calculations.In these so-called“crown-jewel”(CJ)structures,Pt atoms(jewels)occupy the vertex sites of the metal nanocluster(crown)surface.We investigated the thermal stability and oxygen reduction reaction(ORR)catalytic activity of these catalysts.The results reveal that CJ-structured PtCu nanoclusters are stable and possess a comparable or even better ORR activity compared to Pt catalyst,making it a promising candidate for low-cost ORR catalysts.The effect of cluster size on the adsorption strength of ORR intermediates and catalytic property has also been studied.Furthermore,the overall ORR catalytic activity trend of these SACs is explained based on analysis of their electronic properties.A descriptorΨwas established to provide further insight into the correlation between the electronic structure and catalytic activity,which provides a design strategy for new ORR catalysts.More importantly,we reveal that this electronic descriptor can be extended to predict other CJ-structured nanoclusters.展开更多
We report on an extensive study of the viscosity of liquid water at near-ambient conditions,performed within the Green-Kubo theory of linear response and equilibrium ab initio molecular dynamics(AIMD),based on density...We report on an extensive study of the viscosity of liquid water at near-ambient conditions,performed within the Green-Kubo theory of linear response and equilibrium ab initio molecular dynamics(AIMD),based on density-functional theory(DFT).In order to cope with the long simulation times necessary to achieve an acceptable statistical accuracy,our ab initio approach is enhanced with deep-neural-network potentials(NNP).This approach is first validated against AIMD results,obtained by using the Perdew–Burke–Ernzerhof(PBE)exchange-correlation functional and paying careful attention to crucial,yet often overlooked,aspects of the statistical data analysis.Then,we train a second NNP to a dataset generated from the Strongly Constrained and Appropriately Normed(SCAN)functional.Once the error resulting from the imperfect prediction of the melting line is offset by referring the simulated temperature to the theoretical melting one,our SCAN predictions of the shear viscosity of water are in very good agreement with experiments.展开更多
The interest in refractory materials is increasing rapidly in recent decades due to the development of hypersonic vehicles.However,the substance that has the highest melting point(Tm)keeps a secret,since precise measu...The interest in refractory materials is increasing rapidly in recent decades due to the development of hypersonic vehicles.However,the substance that has the highest melting point(Tm)keeps a secret,since precise measurements in extreme conditions are overwhelmingly difficult.In the present work,an accurate deep potential(DP)model of a Hf-Ta-C-N system was first trained,and then applied to search for the highest melting point material by molecular dynamics(MD)simulation and Bayesian global optimization(BGO).The predicted melting points agree well with the experiments and confirm that carbon site vacancies can enhance the melting point of rock-saltstructure carbides.The solid solution with N is verified as another new and more effective melting point enhancing approach for HfC,while a conventional routing of the solid solution with Ta(e.g.,HfTa_(4)C_(5))is not suggested to result in a maximum melting point.The highest melting point(~4236 K)is achieved with the composition of HfCo.638No.271,which is~80 K higher than the highest value in a Hf-C binary system.Dominating mechanism of the N addition is believed to be unstable C-N and N-N bonds in liquid phase,which reduces liquid phase entropy and renders the liquid phase less stable.The improved melting point and less gas generation during oxidation by the addition of N provide a new routing to modify thermal protection materials for the hypersonic vehicles.展开更多
Machine learning-assisted modeling of the inter-atomic potential energy surface(PES)is revolutionizing the field ofmolecular simulation.With the accumulation of high-quality electronic structure data,a model that can ...Machine learning-assisted modeling of the inter-atomic potential energy surface(PES)is revolutionizing the field ofmolecular simulation.With the accumulation of high-quality electronic structure data,a model that can be pretrained on all available data and finetuned on downstream tasks with a small additional effort would bring the field to a new stage.Here we propose DPA-1,a Deep Potentialmodel with a gated attentionmechanism,which is highly effective for representing the conformation and chemical spaces of atomic systems and learning the PES.We tested DPA-1 on a number of systems and observed superior performance compared with existing benchmarks.When pretrained on large-scale datasets containing 56 elements,DPA-1 can be successfully applied to various downstream tasks with a great improvement of sample efficiency.Surprisingly,for different elements,the learned type embedding parameters form a spiral in the latent space and have a natural correspondence with their positions on the periodic table,showing interesting interpretability of the pretrained DPA-1 model.展开更多
Accurate prediction of protein-ligand complex structures is a crucial step in structure-based drug design.Traditional molecular docking methods exhibit limitations in terms of accuracy and sampling space,while relying...Accurate prediction of protein-ligand complex structures is a crucial step in structure-based drug design.Traditional molecular docking methods exhibit limitations in terms of accuracy and sampling space,while relying on machine-learning approaches may lead to invalid conformations.In this study,we propose a novel strategy that combines molecular docking and machine learning methods.Firstly,the protein-ligand binding poses are predicted using a deep learning model.Subsequently,position-restricted docking on predicted binding poses is performed using Uni-Dock,generating physically constrained and valid binding poses.Finally,the binding poses are re-scored and ranked using machine learning scoring functions.This strategy harnesses the predictive power of machine learning and the physical constraints advantage of molecular docking.Evaluation experiments on multiple datasets demonstrate that,compared to using molecular docking or machine learning methods alone,our proposed strategy can significantly improve the success rate and accuracy of protein-ligand complex structure predictions.展开更多
To fill the gap between accurate(and expensive)ab initio calculations and efficient atomistic simulations based on empirical interatomic potentials,a new class of descriptions of atomic interactions has emerged and be...To fill the gap between accurate(and expensive)ab initio calculations and efficient atomistic simulations based on empirical interatomic potentials,a new class of descriptions of atomic interactions has emerged and been widely applied;i.e.machine learning potentials(MLPs).One recently developed type of MLP is the deep potential(DP)method.In this review,we provide an introduction to DP methods in computational materials science.The theory underlying the DP method is presented along with a step-by-step introduction to their development and use.We also review materials applications of DPs in a wide range of materials systems.The DP Library provides a platform for the development of DPs and a database of extant DPs.We discuss the accuracy and efficiency of DPs compared with ab initio methods and empirical potentials.展开更多
The C-glycosidic bond that connects the sugar moiety with aglycone is difficult to be broken or made due to its inert nature.The knowledge of C-glycoside breakdown and synthesis is very limited.Recently,the enzyme Dgp...The C-glycosidic bond that connects the sugar moiety with aglycone is difficult to be broken or made due to its inert nature.The knowledge of C-glycoside breakdown and synthesis is very limited.Recently,the enzyme Dgp A/B/C cascade from a human intestinal bacterium PUE was identified to specifically cleave the C-glycosidic bond of puerarin(daidzein-8-C-glucoside).Here we investigated how puerarin is recognized and oxidized by Dgp A based on crystal structures of Dgp A with or without substrate and biochemical characterization.More strikingly,we found that apart from being a C-glycoside cleaving enzyme,Dgp A/B/C is capable of efficiently converting O-to C-glycoside showing the activity as a structure isomerase.A possible mechanistic model was proposed dependently of the simulated complex structure of Dgp B/C with 3’’-oxo-daidzin and structure-based mutagenesis.Our findings not only shed light on understanding the enzyme-mediated C-glycosidic bond breakage and formation,but also may help to facilitate stereospecific C-glycoside synthesis in pharmaceutical industry.展开更多
The electrochemical reaction in silicon(Si)electrode,accompanying with tremendous volume expansion,causes rapid capacity fade of Li-ion batteries.The Li-ion concentration gradient and structural distribution uniformit...The electrochemical reaction in silicon(Si)electrode,accompanying with tremendous volume expansion,causes rapid capacity fade of Li-ion batteries.The Li-ion concentration gradient and structural distribution uniformity influence the inhomogeneous expansion,and the kinetic mechanism of lithiation and interfacial morphology evolvement remains debated.展开更多
Two-dimensional(2D)hybrid organic-inorganic perovskites(HOIPs)have strong potential for optoelectronic applications due to their polarized photon absorption and emission properties.These macroscopic behaviors are intr...Two-dimensional(2D)hybrid organic-inorganic perovskites(HOIPs)have strong potential for optoelectronic applications due to their polarized photon absorption and emission properties.These macroscopic behaviors are intrinsically linked to microscopic symmetry breaking,particularly the emergence of momentum-dependent,non–centrosymmetric spin splitting in frontier electronic bands.To efficiently identify such spin-related phenomena,we combine first-principles calculations and deep learning models to explore the correlation between in-plane bond distortions and spin-orbit splitting.Our model achieves 100%accuracy in qualitatively identifying systems with observable spin splitting,and over 80%quantitative accuracy in predicting its magnitude and location,confirming that in-plane structural distortions are key descriptors of spin splitting.The trained model can be readily extended to real 2D HOIP systems and is expected to benefit experimentalists by enabling rapid screening and discovery of functional materials,especially in caseswhere ab initio calculations are not feasible due to computational cost.展开更多
The escalating energy crisis has spurred extensive research into organic compounds for energyefficient applications,taking advantage of their environmental friendliness,cost-effective synthesis,and adaptable molecular...The escalating energy crisis has spurred extensive research into organic compounds for energyefficient applications,taking advantage of their environmental friendliness,cost-effective synthesis,and adaptable molecular structures.Traditional trial-and-error methods for discovering highly functional organic compounds are expensive and time-consuming.We employed a 3D transformerbased molecular representation learning algorithm to create the Org-Mol pre-trained model,using 60 million semi-empirically optimized small organic molecule structures.After fine-tuning with public experimental data,the model can accurately predict various physical properties of pure organics,with test set R2 values exceeding 0.92.These fine-tuned models are used in high-throughput screening among millions of ester molecules to identify novel immersion coolants,resulting in the experimental validation of two promising candidates.This work not only demonstrates the potential of Org-Mol in predicting bulk properties for pure organic compounds but also paves the way for the rational and efficient development of ideal candidates for energy-saving materials.展开更多
The ability to rapidly evaluate materials properties through atomistic simulation approaches is the foundation of many new artificial intelligence-based approaches to materials identification and design.This depends o...The ability to rapidly evaluate materials properties through atomistic simulation approaches is the foundation of many new artificial intelligence-based approaches to materials identification and design.This depends on the availability of accurate descriptions of atomic bonding and an efficient means for determining materials properties.We present an efficient,robust platform for calculating materials properties from a wide-range of atomic bonding descriptions,i.e.,APEX,the Alloy Property Explorer.APEX enables the rapid evolution of interatomic potential development and optimization,which is of particular importance in fine-tuning new classes of general AI-based foundation models for applications in materials science and engineering.APEX is an open-source,extendable,cloud-native platform for material property calculations using a range of atomistic simulation methodologies that effectively manages diverse computational resources and is built upon user-friendly features including automatic results visualization,a web-based platform and a NoSQL database client.It is designed for expert and non-specialist users,lowering the barrier to entry for interdisciplinary research within an“AI for Materials”framework.We describe the foundation and use of APEX,as well as provide two examples of its application to properties of titanium and 179 metals and alloys for a wide-range of bonding descriptions.展开更多
Solid electrolytes with fast ion transport are crucial for solid state lithium metal batteries.Chemical doping has been the most effective strategy for improving ion condictiviy,and atomistic simulation with machine-l...Solid electrolytes with fast ion transport are crucial for solid state lithium metal batteries.Chemical doping has been the most effective strategy for improving ion condictiviy,and atomistic simulation with machine-learning potentials helps optimize doping by predicting ion conductivity for various composition.Yet most existing machine-learning models are trained on narrow chemistry,requiring retraining for each new system,which wastes transferable knowledge and incurs significant cost.Here,we propose a pre-trained deep potential model purpose-built for sulfide solid electrolytes with attention mechanism,known as DPA-SSE.The training set includes 15 elements and consists of both equilibrium and extensive out-of-equilibrium configurations.DPA-SSE achieves a high energy resolution of less than 2 meV/atom for dynamical trajectories up to 1150 K,and reproduces experimental ion conductivity with remarkable accuracy.DPA-SSE generalizes well to complex electrolytes with mixes of cation and anion atoms,and enables highly efficient dynamical simulation via model distillation.DPA-SSE also serves as a platform for continuous learning and can be fine-tuned with minimal downstream data.These results demonstrate the possibility of a new pathway for the AIdriven development of solid electrolytes with exceptional performance.展开更多
Quantum transport simulations are essential for understanding and designing nanoelectronic devices,yet the long-standing trade-off between accuracy and computational efficiency has limited their practical applications...Quantum transport simulations are essential for understanding and designing nanoelectronic devices,yet the long-standing trade-off between accuracy and computational efficiency has limited their practical applications.We present DeePTB-NEGF,an integrated framework combining deep learning tight-binding Hamiltonian prediction with non-equilibrium Green’s function methodology to enable accurate quantum transport simulations in open boundary conditions with 2–3 orders of magnitude acceleration.We demonstrate DeePTB-NEGF through two challenging applications:comprehensive break junction simulations with over 104 snapshots,showing excellent agreement with experimental conductance histograms;and carbon nanotube field-effect transistors(CNT-FETs)at experimental dimensions,reproducing measured transfer characteristics for a 41 nm channel CNT-FET(~8000 atoms,3×10^(4)orbitals)and predicting zero-bias transmission spectra for a 180 nm CNT(~3×10^(4)atoms,10^(5)orbitals),showcasing the framework’s capability for large-scale device simulations.Our systematic studies across varying geometries confirm the necessity of simulating realistic experimental structures for precise predictions.DeePTB-NEGF bridges the longstanding gap between first-principles accuracy and computational efficiency,providing a scalable tool for highthroughput and large-scale quantum transport simulations that enable previously inaccessible nanoscale device investigations.展开更多
The rational design of organic functional devices relies on understanding structure-propertyperformance relationships through multi-scale characterization.However,traditional characterizations are costly and require m...The rational design of organic functional devices relies on understanding structure-propertyperformance relationships through multi-scale characterization.However,traditional characterizations are costly and require multidisciplinary expertise.Here we present OCNet,a domain-knowledge-enhanced representation learning framework that,for the first time,enables unified virtual characterization from molecules to devices.Pre-trained on over ten million selfgenerated conjugated molecules and dimers,OCNet learns generalizable microscopic representations comparable to expert-crafted features.As a result,it surpasses state-of-the-art models by over 20%in predicting key computed and experimental molecular optoelectronic properties.OCNet further provides the first transferable model for predicting transfer integrals in thin films,enabling accurate mesoscale carrier mobility estimation via multiscale simulations.By integrating tight-binding-level electronic descriptors,OCNet achieves near real-time,accurate prediction of device power conversion efficiency.Together,OCNet offers a unified and scalable foundation for virtual characterization of organic materials across multiple scales,with broad applicability in photovoltaics,displays,and sensing.展开更多
基金supported by the National Key Research and Development Program of China(Grant No.2024YFA1408604 for K.C.and X.C.)the National Natural Science Foundation of China(Grant Nos.12047503,12447103 for K.C.and X.C.,12325501 for P.Z.,and 12275263 for Y.D.and S.H.)+1 种基金the Innovation Program for Quantum Science and Technology(Grant No.2021ZD0301900 for Y.D.and S.H.)the Natural Science Foundation of Fujian Province of China(Grant No.2023J02032 for Y.D.and S.H.)。
文摘Fundamental physics often confronts complex symbolic problems with few guiding exemplars or established principles.While artificial intelligence(AI)offers promise,its typical need for vast datasets to learn from hinders its use in these information-scarce frontiers.We introduce learning at criticality(LaC),a reinforcement learning scheme that tunes large language models(LLMs)to a sharp learning transition,addressing this information scarcity.At this transition,LLMs achieve peak generalization from minimal data,exemplified by 7-digit base-7 addition-a test of nontrivial arithmetic reasoning.To elucidate this peak,we analyze a minimal concept-network model designed to capture the essence of how LLMs might link tokens.Trained on a single exemplar,this model also undergoes a sharp learning transition.This transition exhibits hallmarks of a second-order phase transition,notably power-law distributed solution path lengths.At this critical point,the system maximizes a“critical thinking pattern”crucial for generalization,enabled by the underlying scale-free exploration.This suggests LLMs reach peak performance by operating at criticality,where such explorative dynamics enable the extraction of underlying operational rules.We demonstrate LaC in quantum field theory:an 8B-parameter LLM,tuned to its critical point by LaC using a few exemplars of symbolic Matsubara sums,solves unseen,higher-order problems,significantly outperforming far larger models.LaC thus leverages critical phenomena,a physical principle,to empower AI for complex,data-sparse challenges in fundamental physics.
基金supported by the National Natural Science Foundation of China(No.51672064)。
文摘Ultra-high temperature ceramics(UHTCs)exhibit a unique combination of excellent properties,including ultra-high melting point,excellent chemical stability,and good oxidation resistance,which make them promising candidates for aerospace and nuclear applications.However,the degradation of hightemperature strength is one of the main limitations for their ultra-high temperature applications.Thus,searching for mechanisms that can help to develop high-performance UHTCs with good high-temperature mechanical properties is urgently needed.To achieve this goal,grain boundary segregation of a series of carbides,including conventional,medium entropy,and high entropy transition metal carbides,i.e.,Zr_(0.95)W_(0.05)C,TiZrHfC_(3),ZrHfNbTaC_(4),TiZrHfNbTaC_(5),were studied by atomistic simulations with a fitted Deep Potential(DP),and the effects of segregation on grain boundary strength were emphasized.For all the studied carbides,grain boundary segregations are realized,which are dominated by the atomic size effect.In addition,tensile simulations indicate that grain boundaries(GBs)will usually be strengthened due to segregation.Our simulation results reveal that grain boundary segregation may be a universal mechanism in enhancing the high-temperature strength of both conventional UHTCs and medium/high entropy UHTCs,since GBs play a key role in controlling the fracture of UHTCs at elevated temperatures.
基金supported by the National Key Research and Development Program(2021YFB2500210)the Beijing Municipal Natural Science Foundation(Z20J00043)+4 种基金the National Natural Science Foundation of China(22109086 and 21825501)the China Postdoctoral Science Foundation(2021TQ0161 and 2021 M691709)the Guoqiang Institute at Tsinghua University(2020GQG1006)the support from the Shuimu Tsinghua Scholar Program of Tsinghua Universitythe support from the Tsinghua National Laboratory for Information Science and Technology for theoretical simulations。
文摘Solid-state batteries have received increasing attention in scientific and industrial communities,which benefits from the intrinsically safe solid electrolytes(SEs).Although much effort has been devoted to designing SEs with high ionic conductivities,it is extremely difficult to fully understand the ionic diffusion mechanisms in SEs through conventional experimental and theoretical methods.Herein,the temperature-dependent concerted diffusion mechanism of ions in SEs is explored through machinelearning molecular dynamics,taking Li_(10)GeP_(2)S_(12) as a prototype.Weaker diffusion anisotropy,more disordered Li distributions,and shorter residence time are observed at a higher temperature.Arrhenius-type temperature dependence is maintained within a wide temperature range,which is attributed to the linear temperature dependence of jump frequencies of various concerted diffusion modes.These results provide a theoretical framework to understand the ionic diffusion mechanisms in SEs and deepen the understanding of the chemical origin of temperature-dependent concerted diffusions in SEs.
基金the National Key Research and Development Program of China(No.2022YFB3709000)the National Natural Science Foundation of China(Nos.52122408,52071023,52101019,and 51901013)the Fundamental Research Funds for the Central Universities(University of Science and Technology Beijing,Nos.06500135 and FRF-TP-2021-04C1).
文摘Multi-component alloys have demonstrated excellent performance in various applications,but the vast range of possible compositions and microstructures makes it challenging to identify optimized alloys for specific purposes.To overcome this challenge,large-scale atomic simulation techniques have been widely used for the design and optimization of multi-component alloys.The capability and reliability of large-scale atomic simulations essentially rely on the quality of interatomic potentials that describe the interactions between atoms.This work provides a comprehensive summary of the latest advances in atomic simulation techniques for multi-component alloys.The focus is on interatomic potentials,including both conventional empirical potentials and newly developed machine learning potentials(MLPs).The fitting processes for different types of interatomic potentials applied to multi-component alloys are also discussed.Finally,the challenges and future perspectives in developing MLPs are thoroughly addressed.Overall,this review provides a valuable resource for researchers interested in developing optimized multicomponent alloys using atomic simulation techniques.
基金supported by the National Natural Science Foundation of China(62474058 and 61804049)the Yuelushan Center for Industrial Innovation(2023YCII0104)+2 种基金the Huxiang High Level Talent Gathering Project(2019RS1023)the Technology Innovation and Entrepreneurship Funds of Hunan Province,P.R.China(2019GK5029)the Fund for Distinguished Young Scholars of Changsha(kq1905012).
文摘Molecular dynamics(MD)is an indispensable atomistic-scale computational tool widely-used in various disciplines.In the past decades,nearly all ab initio MD and machine-learning MD have been based on the general-purpose central/graphics processing units(CPU/GPU),which are well-known to suffer from their intrinsic“memory wall”and“power wall”bottlenecks.Consequently,nowadays MD calculations with ab initio accuracy are extremely time-consuming and power-consuming,imposing serious restrictions on the MD simulation size and duration.To solve this problem,here we propose a special-purpose MD processing unit(MDPU),which could reduce MD time and power consumption by about 103 times(109 times)compared to state-of-the-art machine-learningMD(ab initio MD)based on CPU/GPU,while keeping ab initio accuracy.With significantly-enhanced performance,the proposed MDPU may pave a way for the accurate atomistic-scale analysis of large-size and/or longduration problems which were impossible/impractical to compute before.
基金supported by the National Key R&D Program of China(grantno.2022YFA1004300)the National Natural Science Foundation of China(grant no.12122103)+11 种基金supported by the National Key Research and Development Project of China(grant no.2022YFA1004302)the National Natural Science Foundation of China(grants nos.92270001 and 12288101)supported by the National Institutes of Health(grant no.GM107485 to D.M.Y.)the National Science Foundation(grant no.2209718 to D.M.Y.)supported by the Natural Science Foundation of Zhejiang Province(grant no.2022XHSJJ006)supported by the National Natural Science Foundation of China(grants nos.22222303 and 22173032)supported by the National Key R&D Program of China(grants nos.2021YFA0718900 and 2022YFA1403000)supported by the National Natural Science Foundation of China(grants nos.12034009 and 91961204)supported by the National Science Fund for Distinguished Young Scholars(grant no.22225302)Laboratory of AI for Electrochemistry(AI4EC),and IKKEM(grants nos.RD2023100101 and RD2022070501)supported by the National Natural Science Foundation of China(grants nos.12122401,12074007,and 12135002)Lastly,the computational resource was supported by the Bohrium Cloud Platform at DP Technology and Tan Kah Kee Supercomputing Center(IKKEM).
文摘The rapid advancements in artificial intelligence(AI)are catalyzing transformative changes in atomic modeling,simulation,and design.AI-driven potential energy models havedemonstrated the capability to conduct large-scale,long-duration simulations with the accuracy of ab initio electronic structure methods.However,the model generation process remains a bottleneck for large-scale applications.We propose a shift towards a model-centric ecosystem,wherein a large atomic model(LAM),pretrained across multiple disciplines,can be efficiently fine-tuned and distilled for various downstream tasks,thereby establishing a new framework for molecular modeling.In this study,we introduce the DPA-2 architecture as a prototype for LAMs.Pre-trained on a diverse array of chemical and materials systemsusing a multi-task approach,DPA-2demonstrates superior generalization capabilities across multiple downstream tasks compared to the traditional single-task pre-training and fine-tuning methodologies.Our approach sets the stage for the development and broad application of LAMs in molecular and materials simulation research.
基金the National Key Research and Development Program of China(No.2018YFB0704300)the Ministry of Education,Singapore,under its MOE AcRF Tier 3 Award MOE2018-T3-1-002Q.L.thanks the China Scholarship Council(CSC)for financial support(No.202006460065)。
文摘Inspired by the single-atom catalysts(SACs)concept,we rationally design a series of Pt single atom catalysts embedded in different transition metal nanoclusters through first-principles calculations.In these so-called“crown-jewel”(CJ)structures,Pt atoms(jewels)occupy the vertex sites of the metal nanocluster(crown)surface.We investigated the thermal stability and oxygen reduction reaction(ORR)catalytic activity of these catalysts.The results reveal that CJ-structured PtCu nanoclusters are stable and possess a comparable or even better ORR activity compared to Pt catalyst,making it a promising candidate for low-cost ORR catalysts.The effect of cluster size on the adsorption strength of ORR intermediates and catalytic property has also been studied.Furthermore,the overall ORR catalytic activity trend of these SACs is explained based on analysis of their electronic properties.A descriptorΨwas established to provide further insight into the correlation between the electronic structure and catalytic activity,which provides a design strategy for new ORR catalysts.More importantly,we reveal that this electronic descriptor can be extended to predict other CJ-structured nanoclusters.
基金This work was partially funded by the EU through the MAX Centre of Excellence for supercomputing applications(Project No.824143)the Italian MUR,through the PRIN grant FERMATThe work at Princeton University was supported by the Computational Chemical Sciences Center“Chemistry in Solution and at Interfaces”funded by the US Department of Energy under Award No.DE-SC0019394.
文摘We report on an extensive study of the viscosity of liquid water at near-ambient conditions,performed within the Green-Kubo theory of linear response and equilibrium ab initio molecular dynamics(AIMD),based on density-functional theory(DFT).In order to cope with the long simulation times necessary to achieve an acceptable statistical accuracy,our ab initio approach is enhanced with deep-neural-network potentials(NNP).This approach is first validated against AIMD results,obtained by using the Perdew–Burke–Ernzerhof(PBE)exchange-correlation functional and paying careful attention to crucial,yet often overlooked,aspects of the statistical data analysis.Then,we train a second NNP to a dataset generated from the Strongly Constrained and Appropriately Normed(SCAN)functional.Once the error resulting from the imperfect prediction of the melting line is offset by referring the simulated temperature to the theoretical melting one,our SCAN predictions of the shear viscosity of water are in very good agreement with experiments.
基金supports by the National Natural Science Foundation of China(Nos.52032002,51972081,and U2130103)University Nursing Program for Young Scholars with Creative Talents in Heilongjiang Province(No.UNPYSCT-2020052)+1 种基金Heilongjiang Touyan Team Programsupported by Bohrium Cloud Platform of DP Technology.
文摘The interest in refractory materials is increasing rapidly in recent decades due to the development of hypersonic vehicles.However,the substance that has the highest melting point(Tm)keeps a secret,since precise measurements in extreme conditions are overwhelmingly difficult.In the present work,an accurate deep potential(DP)model of a Hf-Ta-C-N system was first trained,and then applied to search for the highest melting point material by molecular dynamics(MD)simulation and Bayesian global optimization(BGO).The predicted melting points agree well with the experiments and confirm that carbon site vacancies can enhance the melting point of rock-saltstructure carbides.The solid solution with N is verified as another new and more effective melting point enhancing approach for HfC,while a conventional routing of the solid solution with Ta(e.g.,HfTa_(4)C_(5))is not suggested to result in a maximum melting point.The highest melting point(~4236 K)is achieved with the composition of HfCo.638No.271,which is~80 K higher than the highest value in a Hf-C binary system.Dominating mechanism of the N addition is believed to be unstable C-N and N-N bonds in liquid phase,which reduces liquid phase entropy and renders the liquid phase less stable.The improved melting point and less gas generation during oxidation by the addition of N provide a new routing to modify thermal protection materials for the hypersonic vehicles.
基金supported by the National Key R&D Program of China under Grant No.2022YFA1004300the National Natural Science Foundation of China under Grant No.12122103supported by the Bohrium Cloud Platform at DP technology.
文摘Machine learning-assisted modeling of the inter-atomic potential energy surface(PES)is revolutionizing the field ofmolecular simulation.With the accumulation of high-quality electronic structure data,a model that can be pretrained on all available data and finetuned on downstream tasks with a small additional effort would bring the field to a new stage.Here we propose DPA-1,a Deep Potentialmodel with a gated attentionmechanism,which is highly effective for representing the conformation and chemical spaces of atomic systems and learning the PES.We tested DPA-1 on a number of systems and observed superior performance compared with existing benchmarks.When pretrained on large-scale datasets containing 56 elements,DPA-1 can be successfully applied to various downstream tasks with a great improvement of sample efficiency.Surprisingly,for different elements,the learned type embedding parameters form a spiral in the latent space and have a natural correspondence with their positions on the periodic table,showing interesting interpretability of the pretrained DPA-1 model.
基金supported by the National Key Research and Development Program of China(2022YFA1004302)
文摘Accurate prediction of protein-ligand complex structures is a crucial step in structure-based drug design.Traditional molecular docking methods exhibit limitations in terms of accuracy and sampling space,while relying on machine-learning approaches may lead to invalid conformations.In this study,we propose a novel strategy that combines molecular docking and machine learning methods.Firstly,the protein-ligand binding poses are predicted using a deep learning model.Subsequently,position-restricted docking on predicted binding poses is performed using Uni-Dock,generating physically constrained and valid binding poses.Finally,the binding poses are re-scored and ranked using machine learning scoring functions.This strategy harnesses the predictive power of machine learning and the physical constraints advantage of molecular docking.Evaluation experiments on multiple datasets demonstrate that,compared to using molecular docking or machine learning methods alone,our proposed strategy can significantly improve the success rate and accuracy of protein-ligand complex structure predictions.
基金T W and D J S gratefully acknowledge the support of the Research Grants Council,Hong Kong SAR,through the Collaborative Research Fund Project No.8730054The work of H W is supported by the National Science Foundation of China under Grant Nos.11871110 and 12122103The work of W E is supported in part by a gift from iFlytek to Princeton University。
文摘To fill the gap between accurate(and expensive)ab initio calculations and efficient atomistic simulations based on empirical interatomic potentials,a new class of descriptions of atomic interactions has emerged and been widely applied;i.e.machine learning potentials(MLPs).One recently developed type of MLP is the deep potential(DP)method.In this review,we provide an introduction to DP methods in computational materials science.The theory underlying the DP method is presented along with a step-by-step introduction to their development and use.We also review materials applications of DPs in a wide range of materials systems.The DP Library provides a platform for the development of DPs and a database of extant DPs.We discuss the accuracy and efficiency of DPs compared with ab initio methods and empirical potentials.
基金supported by grants from National Natural Science Foundation of China(No.81073018 and 81274044)to Rufeng WangStartup fund program at Beijing University of Chinese Medicine(90011451310011)key research fund for drug discovery in Chinese medicine at Beijing University of Chinese Medicine(1000061223476)to Wenfu Ma。
文摘The C-glycosidic bond that connects the sugar moiety with aglycone is difficult to be broken or made due to its inert nature.The knowledge of C-glycoside breakdown and synthesis is very limited.Recently,the enzyme Dgp A/B/C cascade from a human intestinal bacterium PUE was identified to specifically cleave the C-glycosidic bond of puerarin(daidzein-8-C-glucoside).Here we investigated how puerarin is recognized and oxidized by Dgp A based on crystal structures of Dgp A with or without substrate and biochemical characterization.More strikingly,we found that apart from being a C-glycoside cleaving enzyme,Dgp A/B/C is capable of efficiently converting O-to C-glycoside showing the activity as a structure isomerase.A possible mechanistic model was proposed dependently of the simulated complex structure of Dgp B/C with 3’’-oxo-daidzin and structure-based mutagenesis.Our findings not only shed light on understanding the enzyme-mediated C-glycosidic bond breakage and formation,but also may help to facilitate stereospecific C-glycoside synthesis in pharmaceutical industry.
基金funding support from the Ministry of Science and Technology of People’s Republic of China(Grant No.2021YFB3800303)DP Technology Corporation(Grant No.2021110016001141)the National Natural Science Foundation of China(Grants No.22008096).
文摘The electrochemical reaction in silicon(Si)electrode,accompanying with tremendous volume expansion,causes rapid capacity fade of Li-ion batteries.The Li-ion concentration gradient and structural distribution uniformity influence the inhomogeneous expansion,and the kinetic mechanism of lithiation and interfacial morphology evolvement remains debated.
基金supported by the National Key Research and Development Program of China(Grant No.2022YFB4200500)the National Natural Science Foundation of China(Grant Nos.12474057 and 52494934)+1 种基金the Fundamental Research Funds for the Central Universities for this workR.Z.also thanks DHC-AI Co.,Ltd.for providing financial support and computational resources.R.S.declares no external funding for this work.
文摘Two-dimensional(2D)hybrid organic-inorganic perovskites(HOIPs)have strong potential for optoelectronic applications due to their polarized photon absorption and emission properties.These macroscopic behaviors are intrinsically linked to microscopic symmetry breaking,particularly the emergence of momentum-dependent,non–centrosymmetric spin splitting in frontier electronic bands.To efficiently identify such spin-related phenomena,we combine first-principles calculations and deep learning models to explore the correlation between in-plane bond distortions and spin-orbit splitting.Our model achieves 100%accuracy in qualitatively identifying systems with observable spin splitting,and over 80%quantitative accuracy in predicting its magnitude and location,confirming that in-plane structural distortions are key descriptors of spin splitting.The trained model can be readily extended to real 2D HOIP systems and is expected to benefit experimentalists by enabling rapid screening and discovery of functional materials,especially in caseswhere ab initio calculations are not feasible due to computational cost.
基金supported by research grants from China Petroleum&Chemical Corp(funding number 124014)the financial support from the National Key R&D Program of China(Grant No.2024YFA1510200).
文摘The escalating energy crisis has spurred extensive research into organic compounds for energyefficient applications,taking advantage of their environmental friendliness,cost-effective synthesis,and adaptable molecular structures.Traditional trial-and-error methods for discovering highly functional organic compounds are expensive and time-consuming.We employed a 3D transformerbased molecular representation learning algorithm to create the Org-Mol pre-trained model,using 60 million semi-empirically optimized small organic molecule structures.After fine-tuning with public experimental data,the model can accurately predict various physical properties of pure organics,with test set R2 values exceeding 0.92.These fine-tuned models are used in high-throughput screening among millions of ester molecules to identify novel immersion coolants,resulting in the experimental validation of two promising candidates.This work not only demonstrates the potential of Org-Mol in predicting bulk properties for pure organic compounds but also paves the way for the rational and efficient development of ideal candidates for energy-saving materials.
基金supported by the Research Grants Council,Hong Kong SAR through the General Research Fund(17210723,17200424)the support of The University of Hong Kong via seed fund(2201100392)+2 种基金supported by the National Key R&D Program of China(Grant No.2022YFA1004300)the National Natural Science Foundation of China(Grant No.12122103)startup funding from Materials Innovation Institute for Life Sciences and Energy(MILES),HKU-SIRI in Shenzhen for support of this manuscript.
文摘The ability to rapidly evaluate materials properties through atomistic simulation approaches is the foundation of many new artificial intelligence-based approaches to materials identification and design.This depends on the availability of accurate descriptions of atomic bonding and an efficient means for determining materials properties.We present an efficient,robust platform for calculating materials properties from a wide-range of atomic bonding descriptions,i.e.,APEX,the Alloy Property Explorer.APEX enables the rapid evolution of interatomic potential development and optimization,which is of particular importance in fine-tuning new classes of general AI-based foundation models for applications in materials science and engineering.APEX is an open-source,extendable,cloud-native platform for material property calculations using a range of atomistic simulation methodologies that effectively manages diverse computational resources and is built upon user-friendly features including automatic results visualization,a web-based platform and a NoSQL database client.It is designed for expert and non-specialist users,lowering the barrier to entry for interdisciplinary research within an“AI for Materials”framework.We describe the foundation and use of APEX,as well as provide two examples of its application to properties of titanium and 179 metals and alloys for a wide-range of bonding descriptions.
基金supported in part by the National Science and Technology Major Project(Grants No.2023ZD0120702)Key Research Program of Frontier Sciences of CAS(Grant No.ZDBS-LY-SLH008)National Nature Science Foundation of China(Grants No.12304049).We thank Bowen Deng and Dr.Peichen Zhong,the authors of CHGNet,for inspiring discussions.We also appreciate valuable advice by Dr.Qisheng Wu.The computational resource was supported by the Bohrium Cloud Platform at DP technology.
文摘Solid electrolytes with fast ion transport are crucial for solid state lithium metal batteries.Chemical doping has been the most effective strategy for improving ion condictiviy,and atomistic simulation with machine-learning potentials helps optimize doping by predicting ion conductivity for various composition.Yet most existing machine-learning models are trained on narrow chemistry,requiring retraining for each new system,which wastes transferable knowledge and incurs significant cost.Here,we propose a pre-trained deep potential model purpose-built for sulfide solid electrolytes with attention mechanism,known as DPA-SSE.The training set includes 15 elements and consists of both equilibrium and extensive out-of-equilibrium configurations.DPA-SSE achieves a high energy resolution of less than 2 meV/atom for dynamical trajectories up to 1150 K,and reproduces experimental ion conductivity with remarkable accuracy.DPA-SSE generalizes well to complex electrolytes with mixes of cation and anion atoms,and enables highly efficient dynamical simulation via model distillation.DPA-SSE also serves as a platform for continuous learning and can be fine-tuned with minimal downstream data.These results demonstrate the possibility of a new pathway for the AIdriven development of solid electrolytes with exceptional performance.
基金supported by the Natural Science Foundation of Jiangsu Province(BK20250472)the Advanced Materials-National Science and Technology Major Project(2025ZD0618401)+2 种基金National Natural Science Foundation of China(12504285)National Key R&D Program of China(2024YFA1208203)Q.G.also acknowledges the funding support from the AI for Science Institute,Beijing(AISI).
文摘Quantum transport simulations are essential for understanding and designing nanoelectronic devices,yet the long-standing trade-off between accuracy and computational efficiency has limited their practical applications.We present DeePTB-NEGF,an integrated framework combining deep learning tight-binding Hamiltonian prediction with non-equilibrium Green’s function methodology to enable accurate quantum transport simulations in open boundary conditions with 2–3 orders of magnitude acceleration.We demonstrate DeePTB-NEGF through two challenging applications:comprehensive break junction simulations with over 104 snapshots,showing excellent agreement with experimental conductance histograms;and carbon nanotube field-effect transistors(CNT-FETs)at experimental dimensions,reproducing measured transfer characteristics for a 41 nm channel CNT-FET(~8000 atoms,3×10^(4)orbitals)and predicting zero-bias transmission spectra for a 180 nm CNT(~3×10^(4)atoms,10^(5)orbitals),showcasing the framework’s capability for large-scale device simulations.Our systematic studies across varying geometries confirm the necessity of simulating realistic experimental structures for precise predictions.DeePTB-NEGF bridges the longstanding gap between first-principles accuracy and computational efficiency,providing a scalable tool for highthroughput and large-scale quantum transport simulations that enable previously inaccessible nanoscale device investigations.
基金supported in part by NSFC’s Major Research Project 92270001Z.Z.’s work is supported in part by the Beijing Nova Program(20250484934).
文摘The rational design of organic functional devices relies on understanding structure-propertyperformance relationships through multi-scale characterization.However,traditional characterizations are costly and require multidisciplinary expertise.Here we present OCNet,a domain-knowledge-enhanced representation learning framework that,for the first time,enables unified virtual characterization from molecules to devices.Pre-trained on over ten million selfgenerated conjugated molecules and dimers,OCNet learns generalizable microscopic representations comparable to expert-crafted features.As a result,it surpasses state-of-the-art models by over 20%in predicting key computed and experimental molecular optoelectronic properties.OCNet further provides the first transferable model for predicting transfer integrals in thin films,enabling accurate mesoscale carrier mobility estimation via multiscale simulations.By integrating tight-binding-level electronic descriptors,OCNet achieves near real-time,accurate prediction of device power conversion efficiency.Together,OCNet offers a unified and scalable foundation for virtual characterization of organic materials across multiple scales,with broad applicability in photovoltaics,displays,and sensing.
