The accurate prediction of displacement is crucial for landslide deformation monitoring and early warning.This study focuses on a landslide in Wenzhou Belt Highway and proposes a novel multivariate landslide displacem...The accurate prediction of displacement is crucial for landslide deformation monitoring and early warning.This study focuses on a landslide in Wenzhou Belt Highway and proposes a novel multivariate landslide displacement prediction method that relies on graph deep learning and Global Navigation Satellite System(GNSS)positioning.First model the graph structure of the monitoring system based on the engineering positions of the GNSS monitoring points and build the adjacent matrix of graph nodes.Then construct the historical and predicted time series feature matrixes using the processed temporal data including GNSS displacement,rainfall,groundwater table and soil moisture content and the graph structure.Last introduce the state-of-the-art graph deep learning GTS(Graph for Time Series)model to improve the accuracy and reliability of landslide displacement prediction which utilizes the temporal-spatial dependency of the monitoring system.This approach outperforms previous studies that only learned temporal features from a single monitoring point and maximally weighs the prediction performance and the priori graph of the monitoring system.The proposed method performs better than SVM,XGBoost,LSTM and DCRNN models in terms of RMSE(1.35 mm),MAE(1.14 mm)and MAPE(0.25)evaluation metrics,which is provided to be effective in future landslide failure early warning.展开更多
Machine learning potentials(MLPs)have become an indispensable tool in large-scale atomistic simulations.However,mostMLPs today are trained on data computed using relatively cheap density functional theory(DFT)methods ...Machine learning potentials(MLPs)have become an indispensable tool in large-scale atomistic simulations.However,mostMLPs today are trained on data computed using relatively cheap density functional theory(DFT)methods such as the Perdew-Burke-Ernzerhof(PBE)generalized gradient approximation(GGA)functional.While meta-GGAs such as the strongly constrained and appropriately normed(SCAN)functional have been shown to yield significantly improved descriptions of atomic interactions for diversely bonded systems,their higher computational cost remains an impediment to their use in MLP development.In this work,we outline a data-efficient multi-fidelity approach to constructing Materials 3-body Graph Network(M3GNet)interatomic potentials that integrate different levels of theory within a singlemodel.Using silicon and water as examples,we show that a multi-fidelity M3GNet model trained on a combined dataset of low-fidelityGGAcalculations with 10%of high-fidelity SCAN calculations can achieve accuracies comparable to a single-fidelity M3GNet model trained on a dataset comprising 8×the number of SCAN calculations.This work provides a pathway to the development of high-fidelity MLPs in a cost-effective manner by leveraging existing low-fidelity datasets.展开更多
Graph deep learning models,which incorporate a natural inductive bias for atomic structures,are of immense interest in materials science and chemistry.Here,we introduce the Materials Graph Library(MatGL),an open-sourc...Graph deep learning models,which incorporate a natural inductive bias for atomic structures,are of immense interest in materials science and chemistry.Here,we introduce the Materials Graph Library(MatGL),an open-source graph deep learning library for materials science and chemistry.Built on top of the popular Deep Graph Library(DGL)and Python Materials Genomics(Pymatgen)packages,MatGL is designed to be an extensible“batteries-included”library for developing advanced model architectures for materials property predictions and interatomic potentials.At present,MatGL has efficient implementations for both invariant and equivariant graph deep learning models,including the Materials 3-body Graph Network(M3GNet),MatErials Graph Network(MEGNet),Crystal Hamiltonian Graph Network(CHGNet),TensorNet and SO3Net architectures.MatGL also provides several pretrained foundation potentials(FPs)with coverage of the entire periodic table,and property prediction models for out-of-box usage,benchmarking and fine-tuning.Finally,MatGL integrates with PyTorch Lightning to enable efficient model training.展开更多
Accurate identification and effective support of key blocks are crucial for ensuring the stability and safety of rock slopes.The number of structural planes and rock blocks were reduced in previous studies.This impair...Accurate identification and effective support of key blocks are crucial for ensuring the stability and safety of rock slopes.The number of structural planes and rock blocks were reduced in previous studies.This impairs the ability to characterize complex rock slopes accurately and inhibits the identification of key blocks.In this paper,a knowledge-data dually driven paradigm for accurate identification of key blocks in complex rock slopes is proposed.Our basic idea is to integrate key block theory into data-driven models based on finely characterizing structural features to identify key blocks in complex rock slopes accurately.The proposed novel paradigm consists of(1)representing rock slopes as graph-structured data based on complex systems theory,(2)identifying key nodes in the graph-structured data using graph deep learning,and(3)mapping the key nodes of graph-structured data to corresponding key blocks in the rock slope.Verification experiments and real-case applications are conducted by the proposed method.The verification results demonstrate excellent model performance,strong generalization capability,and effective classification results.Moreover,the real case application is conducted on the northern slope of the Yanqianshan Iron Mine.The results show that the proposed method can accurately identify key blocks in complex rock slopes,which can provide a decision-making basis and rational recommendations for effective support and instability prevention of rock slopes,thereby ensuring the stability of rock engineering and the safety of life and property.展开更多
Accurate and timely fault diagnosis is of great significance for the safe operation and power supply reliability of distribution systems.However,traditional intelligent methods limit the use of the physical structures...Accurate and timely fault diagnosis is of great significance for the safe operation and power supply reliability of distribution systems.However,traditional intelligent methods limit the use of the physical structures and data information of power networks.To this end,this study proposes a fault diagnostic model for distribution systems based on deep graph learning.This model considers the physical structure of the power network as a significant constraint during model training,which endows the model with stronger information perception to resist abnormal data input and unknown application conditions.In addition,a special spatiotemporal convolutional block is utilized to enhance the waveform feature extraction ability.This enables the proposed fault diagnostic model to be more effective in dealing with both fault waveform changes and the spatial effects of faults.In addition,a multi-task learning framework is constructed for fault location and fault type analysis,which improves the performance and generalization ability of the model.The IEEE 33-bus and IEEE 37-bus test systems are modeled to verify the effectiveness of the proposed fault diagnostic model.Finally,different fault conditions,topological changes,and interference factors are considered to evaluate the anti-interference and generalization performance of the proposed model.Experimental results demonstrate that the proposed model outperforms other state-of-the-art methods.展开更多
financial services:for example,GPS and Bluetooth inspire location-based services,and search and web technologies motivate online shopping,reviews,and payments.These business services have become more connected than ev...financial services:for example,GPS and Bluetooth inspire location-based services,and search and web technologies motivate online shopping,reviews,and payments.These business services have become more connected than ever,and as a result,financial frauds have become a significant challenge.Therefore,combating financial risks in the big data era requires breaking the borders of traditional data,algorithms,and systems.An increasing number of studies have addressed these challenges and proposed new methods for risk detection,assessment,and forecasting.As a key contribution,we categorize these works in a rational framework:first,we identify the data that can be used to identify risks.We then discuss how big data can be combined with the emerging tools to effectively learn or analyze financial risk.Finally,we highlight the effectiveness of these methods in real-world applications.Furthermore,we stress on the importance of utilizing multi-channel information,graphs,and networks of long-range dependence for the effective identification of financial risks.We conclude our survey with a discussion on the new challenges faced by the financial sector,namely,deep fake technology,adversaries,causal and interpretable inference,privacy protection,and microsimulations.展开更多
基金funded by the National Natural Science Foundation of China (Grant No.41902240).
文摘The accurate prediction of displacement is crucial for landslide deformation monitoring and early warning.This study focuses on a landslide in Wenzhou Belt Highway and proposes a novel multivariate landslide displacement prediction method that relies on graph deep learning and Global Navigation Satellite System(GNSS)positioning.First model the graph structure of the monitoring system based on the engineering positions of the GNSS monitoring points and build the adjacent matrix of graph nodes.Then construct the historical and predicted time series feature matrixes using the processed temporal data including GNSS displacement,rainfall,groundwater table and soil moisture content and the graph structure.Last introduce the state-of-the-art graph deep learning GTS(Graph for Time Series)model to improve the accuracy and reliability of landslide displacement prediction which utilizes the temporal-spatial dependency of the monitoring system.This approach outperforms previous studies that only learned temporal features from a single monitoring point and maximally weighs the prediction performance and the priori graph of the monitoring system.The proposed method performs better than SVM,XGBoost,LSTM and DCRNN models in terms of RMSE(1.35 mm),MAE(1.14 mm)and MAPE(0.25)evaluation metrics,which is provided to be effective in future landslide failure early warning.
基金ntellectually led by the U.S. Department of Energy, Office of Science, Office of Basic Energy Sciences, Materials Sciences and Engineering Division under contract No. DE-AC02-05-CH11231 (Materials Project program KC23MP)This research used resources of the National Energy Research Scientific Computing Center (NERSC), a Department of Energy Office of Science User Facility using NERSC award DOE-ERCAP0026371the support of the Eric and Wendy Schmidt AI in Science Postdoctoral Fellowship, a Schmidt Futures program.
文摘Machine learning potentials(MLPs)have become an indispensable tool in large-scale atomistic simulations.However,mostMLPs today are trained on data computed using relatively cheap density functional theory(DFT)methods such as the Perdew-Burke-Ernzerhof(PBE)generalized gradient approximation(GGA)functional.While meta-GGAs such as the strongly constrained and appropriately normed(SCAN)functional have been shown to yield significantly improved descriptions of atomic interactions for diversely bonded systems,their higher computational cost remains an impediment to their use in MLP development.In this work,we outline a data-efficient multi-fidelity approach to constructing Materials 3-body Graph Network(M3GNet)interatomic potentials that integrate different levels of theory within a singlemodel.Using silicon and water as examples,we show that a multi-fidelity M3GNet model trained on a combined dataset of low-fidelityGGAcalculations with 10%of high-fidelity SCAN calculations can achieve accuracies comparable to a single-fidelity M3GNet model trained on a dataset comprising 8×the number of SCAN calculations.This work provides a pathway to the development of high-fidelity MLPs in a cost-effective manner by leveraging existing low-fidelity datasets.
基金intellectually led by the U.S. Department of Energy, Office of Science, Office of Basic Energy Sciences, Materials Sciences and Engineering Division under contract No. DE-AC02-05-CH11231 (Materials Project program KC23MP). This research used resources of the National Energy Research Scientific Computing Center (NERSC), a Department of Energy Office of Science User Facility using NERSC award DOE-ERCAP0026371. T.W.Ko also acknowledges the support of the Eric and Wendy Schmidt AI in Science Postdoctoral Fellowship, a Schmidt Futures program. We also acknowledged AdvanceSoft Corporation for implementing the LAMMPS interface.
文摘Graph deep learning models,which incorporate a natural inductive bias for atomic structures,are of immense interest in materials science and chemistry.Here,we introduce the Materials Graph Library(MatGL),an open-source graph deep learning library for materials science and chemistry.Built on top of the popular Deep Graph Library(DGL)and Python Materials Genomics(Pymatgen)packages,MatGL is designed to be an extensible“batteries-included”library for developing advanced model architectures for materials property predictions and interatomic potentials.At present,MatGL has efficient implementations for both invariant and equivariant graph deep learning models,including the Materials 3-body Graph Network(M3GNet),MatErials Graph Network(MEGNet),Crystal Hamiltonian Graph Network(CHGNet),TensorNet and SO3Net architectures.MatGL also provides several pretrained foundation potentials(FPs)with coverage of the entire periodic table,and property prediction models for out-of-box usage,benchmarking and fine-tuning.Finally,MatGL integrates with PyTorch Lightning to enable efficient model training.
基金supported by the National Natural Science Foundation of China(Grant Nos.42277161,42230709).
文摘Accurate identification and effective support of key blocks are crucial for ensuring the stability and safety of rock slopes.The number of structural planes and rock blocks were reduced in previous studies.This impairs the ability to characterize complex rock slopes accurately and inhibits the identification of key blocks.In this paper,a knowledge-data dually driven paradigm for accurate identification of key blocks in complex rock slopes is proposed.Our basic idea is to integrate key block theory into data-driven models based on finely characterizing structural features to identify key blocks in complex rock slopes accurately.The proposed novel paradigm consists of(1)representing rock slopes as graph-structured data based on complex systems theory,(2)identifying key nodes in the graph-structured data using graph deep learning,and(3)mapping the key nodes of graph-structured data to corresponding key blocks in the rock slope.Verification experiments and real-case applications are conducted by the proposed method.The verification results demonstrate excellent model performance,strong generalization capability,and effective classification results.Moreover,the real case application is conducted on the northern slope of the Yanqianshan Iron Mine.The results show that the proposed method can accurately identify key blocks in complex rock slopes,which can provide a decision-making basis and rational recommendations for effective support and instability prevention of rock slopes,thereby ensuring the stability of rock engineering and the safety of life and property.
基金supported by National Natural Science Foundation of China(No.52277083)。
文摘Accurate and timely fault diagnosis is of great significance for the safe operation and power supply reliability of distribution systems.However,traditional intelligent methods limit the use of the physical structures and data information of power networks.To this end,this study proposes a fault diagnostic model for distribution systems based on deep graph learning.This model considers the physical structure of the power network as a significant constraint during model training,which endows the model with stronger information perception to resist abnormal data input and unknown application conditions.In addition,a special spatiotemporal convolutional block is utilized to enhance the waveform feature extraction ability.This enables the proposed fault diagnostic model to be more effective in dealing with both fault waveform changes and the spatial effects of faults.In addition,a multi-task learning framework is constructed for fault location and fault type analysis,which improves the performance and generalization ability of the model.The IEEE 33-bus and IEEE 37-bus test systems are modeled to verify the effectiveness of the proposed fault diagnostic model.Finally,different fault conditions,topological changes,and interference factors are considered to evaluate the anti-interference and generalization performance of the proposed model.Experimental results demonstrate that the proposed model outperforms other state-of-the-art methods.
基金supported by the National Natural Science Foundation of China under Grant Nos.91746301,61772498,61802370,and 61902380.
文摘financial services:for example,GPS and Bluetooth inspire location-based services,and search and web technologies motivate online shopping,reviews,and payments.These business services have become more connected than ever,and as a result,financial frauds have become a significant challenge.Therefore,combating financial risks in the big data era requires breaking the borders of traditional data,algorithms,and systems.An increasing number of studies have addressed these challenges and proposed new methods for risk detection,assessment,and forecasting.As a key contribution,we categorize these works in a rational framework:first,we identify the data that can be used to identify risks.We then discuss how big data can be combined with the emerging tools to effectively learn or analyze financial risk.Finally,we highlight the effectiveness of these methods in real-world applications.Furthermore,we stress on the importance of utilizing multi-channel information,graphs,and networks of long-range dependence for the effective identification of financial risks.We conclude our survey with a discussion on the new challenges faced by the financial sector,namely,deep fake technology,adversaries,causal and interpretable inference,privacy protection,and microsimulations.
