The prediction of sea surface partial pressure of carbon dioxide(pCO_(2))in the South China Sea is crucial for understanding the region’s contribution to the global carbon budget and its interactions with climate cha...The prediction of sea surface partial pressure of carbon dioxide(pCO_(2))in the South China Sea is crucial for understanding the region’s contribution to the global carbon budget and its interactions with climate change.We applied the Spatiotemporal Convolutional Long Short-Term Memory(STConvLSTM)model,integrating key environmental factors including sea surface temperature(SST),sea surface salinity(SSS),and chlorophyll a(Chl a),to predict and analyze sea surface pCO_(2)in the South China Sea.The model demonstrated high accuracy in short-term predictions(1 month),with a mean absolute error(MAE)of 0.394,a root mean square error(RMSE)of 0.659,and a coefficient of determination(R^(2))of 0.998.For long-term predictions(12 months),the model maintained its predictive capability,with an MAE of 0.667,RMSE of 1.255,and R^(2)of 0.994.Feature importance analysis revealed that sea surface pCO_(2)and SST were the main drivers of the model’s predictions,whereas Chl a and SSS had relatively minor impacts.The model’s generalization ability was further validated in the northwest Pacific Ocean and tropical Pacific Ocean,where it successfully captured the spatiotemporal variation in pCO_(2)with small prediction errors.The ST-ConvLSTM model provides an efficient and accurate tool for forecasting and analyzing sea surface pCO_(2)in the South China Sea,offering new insights into global carbon cycling and climate change.This study demonstrates the potential of deep learning in marine science and provides a significant technical support for global changes and marine ecosystem research.展开更多
El Niño-Southern Oscillation(ENSO)affects the changes in ocean physical elements in Taiwan Strait(TWS)primarily by regulating the strength of the East Asian Winter Monsoon(EAWM)and the intrusion of the Kuroshio.A...El Niño-Southern Oscillation(ENSO)affects the changes in ocean physical elements in Taiwan Strait(TWS)primarily by regulating the strength of the East Asian Winter Monsoon(EAWM)and the intrusion of the Kuroshio.Additionally,the fluctuating impact between nutrient-poor seawater with high dissolved inorganic carbon(DIC)that infiltrates owing to the Kuroshio during El Niño phases and nutrient-rich seawater with low DIC from the South China Sea(SCS)carried by the EAWM during La Niña phases determines the nutrient content in TWS,thereby sculpting appropriate or unsuitable biochemical environment.In this study,based on high-resolution sea-surface partial pressure of carbon dioxide(pCO_(2))data,we investigate the relationship between pCO_(2)level of TWS and ENSO events in winter.The physical mechanisms affecting the anomalous distribution of pCO_(2)level during ENSO are also explored.Stepwise regression was employed to identify the optimal influencing factors for modeling pCO_(2).Results indicate a significant positive correlation between Niño3.4 index and pCO_(2),which is significantly influenced by factors such as sea-surface temperature(SST),chlorophyll-a(Chl a),and DIC.These are related to the anomalously strong Kuroshio intrusion and weaker EAWM during El Niño years.It brings a large amount of high SST water with low nutrient concentration and high DIC,which is detrimental to CO_(2)dissolution and phytoplankton growth over the TWS,leading to an increase in pCO_(2).Conversely,pCO_(2)level is significantly low under the influence of SCS seawater during La Niña years.Based on the characterization of the pCO_(2)level response to ENSO,the carbon balance at TWS can be explored.展开更多
Employing flow space theory and multi-source data,this study examines the spatial net-work structure and factors influencing railway passenger flow,which is crucial for rail planning in densely populated megalopolises...Employing flow space theory and multi-source data,this study examines the spatial net-work structure and factors influencing railway passenger flow,which is crucial for rail planning in densely populated megalopolises.Focusing on China’s Yangtze River Delta(YRD)megalopolis,we utilize social network analysis(SNA)to explore the characteristics of various flow networks and their interactions with the railway passenger flow network.Key findings include:(1)a pronounced polarization effect and core-periphery structure exist in the YRD,notably within industry and railway flow networks;(2)industry and cor-poration flow significantly contributes to rail passenger flow,with corporation networks in commerce,technical services,and finance showing higher similarity to the railway passen-ger flow network;(3)there is significant heterogeneity in the correlation between rail pas-senger flow and other flows within sub-networks formed by connections among nodes of different levels;(4)enhancing railway services at lower-level nodes is essential to mitigate the disparity between population mobility and rail passenger flow and to promote rail transportation equity.This research offers valuable insights for policymakers in developing countries to strategically plan railroad networks in megalopolises.展开更多
Amidst a global decline in bus ridership,this study pioneers a longitudinal approach to understanding individual-level transitions and churning in urban bus systems.Utilizing a novel framework that leverages smart car...Amidst a global decline in bus ridership,this study pioneers a longitudinal approach to understanding individual-level transitions and churning in urban bus systems.Utilizing a novel framework that leverages smart card data,we construct and analyze user behavior transition matrices over time,employing Markov processes and the Chapman-Kolmogorov Equation.Our analysis,derived from a 22-month dataset from Shenzhen,reveals a two-stage churning process:users first decrease travel frequency before transitioning to irreg-ular travel patterns.Crucially,this study introduces targeted retention policies,including tiered usage incentives and personalized communication strategies,aimed at different stages of the user lifecycle.By offering free subsequent trips to irregular travelers and com-bining policy approaches for users at high risk of churning,we provide actionable insights for transit operators to counter the trend of declining ridership.展开更多
With the increasingly prominent energy and environmental issues,the supercapacitors,as a highly efficient and clean energy conversion and storage devices,meet the requirements well.However,it is still a challenge to e...With the increasingly prominent energy and environmental issues,the supercapacitors,as a highly efficient and clean energy conversion and storage devices,meet the requirements well.However,it is still a challenge to enhance the capacitance and energy density of supercapacitors.A novel and highly conductive dodecaborate/MXene composites have been designed for high performance supercapacitors.The surface charge property of MXene was modified by a simple ultrasonic treatment with ammonium ion,and the dodecaborate ion can be inserted into the inner surface of MXene by electrostatic adsorption.Due to the unique icosahedral cage conjugate structure formed by the B-B bond and the highly delocalized three-dimensionalπbond structure of the electrons,the negative charge is delocalied on the whole dodecaborate ion,which reduces the ability to bind to cations.Therefore,the cations can move easily,and the dodecaborate can act as a“lubricant”for ion diffusion between the MXene layers,which significantly improves the ion transfer rate of supercapacitors.The dodecaborate/MXene composites can achieve an extremely high specific capacitance of 366 F.g^-1 at a scan rate of 2 mV.s^-1,which is more than eight times higher than that of MXene(43 F1-)at the same scan rate.Our finding provides a novel route on the fabrication of the high performance supercapacitors.展开更多
Effective control of post-extraction hemorrhage and alveolar bone resorption is critical for successful extraction socket treatment,which remains an unmet clinical challenge.Herein,an injectable Tetra-PEG hydrogel tha...Effective control of post-extraction hemorrhage and alveolar bone resorption is critical for successful extraction socket treatment,which remains an unmet clinical challenge.Herein,an injectable Tetra-PEG hydrogel that possesses rapid gelation,firm tissue adhesion,high mechanical strength,suitable degradability,and excellent biocompatibility is developed as a sutureless and coagulation-independent bioadhesive for the management of extraction sockets.Our results demonstrate that the rapid and robust adhesive sealing of the extraction socket by the Tetra-PEG hydrogel can provide reliable protection for the underlying wound and stabilize blood clots to facilitate tissue healing.In vivo experiments using an anticoagulated rat tooth extraction model show that the hydrogel significantly outperformed clinically used cotton and gelatin sponge in hemostatic efficacy,wound closure,alveolar ridge preservation,and in situ alveolar bone regeneration.Histomorphological evaluations reveal the mechanisms for accelerated bone repair through suppressed long-term inflammation,elevated collagen deposition,higher osteoblast activity,and enhanced angiogenesis.Together,our study highlights the clinical potential of the developed injectable Tetra-PEG hydrogel for treating anticoagulant-related post-extraction hemorrhage and improving socket healing.展开更多
A social stream refers to the data stream that records a series of social entities and the dynamic interac-tions between two entities. It can be employed to model the changes of entity states in numerous applications....A social stream refers to the data stream that records a series of social entities and the dynamic interac-tions between two entities. It can be employed to model the changes of entity states in numerous applications. The social streams, the combination of graph and streaming data, pose great challenge to efficient analytical query processing, and are key to better understanding users' behavior. Considering of privacy and other related issues, a social stream genera-tor is of great significance. A framework of synthetic social stream generator (SSG) is proposed in this paper. The gener-ated social streams using SSG can be tuned to capture sev-eral kinds of fundamental social stream properties, includ-ing patterns about users' behavior and graph patterns. Ex-tensive empirical studies with several real-life social stream data sets show that SSG can produce data that better fit to real data. It is also confirmed that SSG can generate social stream data continuously with stable throughput and memory consumption. Furthermore, we propose a parallel implemen-tation of SSG with the help of asynchronized parallel pro-cessing model and delayed update strategy. Our experiments verify that the throughput of the parallel implementation can increase linearly by increasing nodes.展开更多
Due to the increasing demand for goods movement,externalities from freight mobility have attracted much concern among local citizens and policymakers.Freight truck-related crash is one of these externalities and impac...Due to the increasing demand for goods movement,externalities from freight mobility have attracted much concern among local citizens and policymakers.Freight truck-related crash is one of these externalities and impacts urban freight transportation most drastically.Previous studies have mainly focused on correlation analyses of influencing factors based on crash density/count data,but have paid little attention to the inherent uncertainties of freight truck-related crashes(FTCs)from a spatial perspective.While establishing an interpretable analysis model for freight truck-related accidents that consid-ers uncertainties is of great significance for promoting the robust development of urban freight transportation systems.Hence,this study proposes the concept of FTC hazard(FTCH),and employs the Bayesian neural network(BNN)model based on stochastic varia-tional inference to model uncertainty.Considering the difficulty in interpreting deep learning-based models,this study introduces the local interpretable modelagnostic expla-nation(LIME)model into the analysis framework to explain the results of the neural net-work model.This study then verifies the feasibility of the proposed analysis framework using data from California from 2011 to 2020.Results show that FTCHs can be effectively modeled by predicting confidence intervals for effects of built environment factors,in par-ticular demographics,land use,and road network structure.Results based on LIME values indicate the spatial heterogeneity in influence mechanisms on FTCHs between areas within the metropolitan regions and alongside the freeways.These findings may help transport planners and logistic managers develop more effective measures to avoid potential nega-tive effects brought by FTCHs in local communities.展开更多
The accurate estimation of the remaining charge time(RCT)is essential in a battery management system(BMS),because it guarantees the safety and dependability of the power battery systems of new energy vehicles.However,...The accurate estimation of the remaining charge time(RCT)is essential in a battery management system(BMS),because it guarantees the safety and dependability of the power battery systems of new energy vehicles.However,the direct estimation of RCT is challenging because of the variability of actual charging scenarios and the complex charging process,which complicates the estimation of RCT in actual scenarios.Hence,this paper proposes an estimation framework based on deep learning for multi-scenario charging data to estimate the remaining charging times.Through an in-depth analysis of multi-scenario charging data,the RCT of the charging process is estimated using the temporal convolutional network(TCN)model,which has a strong generalization ability.Additionally,a dynamic learning rate(DLR)mechanism and an early stopping strategy(ES)are designed in the TCN model(DLR-ES TCN)for the nonlinear characteristics of the battery system to balance the relationship between model convergence speed and accuracy.Finally,compared with the traditional TCN model and four common deep learning models under three different scenarios,the experimental results show the mean absolute percentage error(MAPE)of the proposed method is less than 2%,indicating better accuracy and stability.This research can improve the safety monitoring of power batteries when applied to various target domains.展开更多
基金Supported by the National Key Research and Development Program of China(No.2023YFC3008202)the National Natural Science Foundation of China(No.42406019)the Scientific Research Fund of Zhejiang Provincial Education Department(No.Y202353066)。
文摘The prediction of sea surface partial pressure of carbon dioxide(pCO_(2))in the South China Sea is crucial for understanding the region’s contribution to the global carbon budget and its interactions with climate change.We applied the Spatiotemporal Convolutional Long Short-Term Memory(STConvLSTM)model,integrating key environmental factors including sea surface temperature(SST),sea surface salinity(SSS),and chlorophyll a(Chl a),to predict and analyze sea surface pCO_(2)in the South China Sea.The model demonstrated high accuracy in short-term predictions(1 month),with a mean absolute error(MAE)of 0.394,a root mean square error(RMSE)of 0.659,and a coefficient of determination(R^(2))of 0.998.For long-term predictions(12 months),the model maintained its predictive capability,with an MAE of 0.667,RMSE of 1.255,and R^(2)of 0.994.Feature importance analysis revealed that sea surface pCO_(2)and SST were the main drivers of the model’s predictions,whereas Chl a and SSS had relatively minor impacts.The model’s generalization ability was further validated in the northwest Pacific Ocean and tropical Pacific Ocean,where it successfully captured the spatiotemporal variation in pCO_(2)with small prediction errors.The ST-ConvLSTM model provides an efficient and accurate tool for forecasting and analyzing sea surface pCO_(2)in the South China Sea,offering new insights into global carbon cycling and climate change.This study demonstrates the potential of deep learning in marine science and provides a significant technical support for global changes and marine ecosystem research.
基金The Key R&D Project of Zhejiang Province under contract No.2023C03120the General Scientific Research Project of Zhejiang Province under contract No.Y202353957the National Natural Science Foundation of China under contract No.42106017.
文摘El Niño-Southern Oscillation(ENSO)affects the changes in ocean physical elements in Taiwan Strait(TWS)primarily by regulating the strength of the East Asian Winter Monsoon(EAWM)and the intrusion of the Kuroshio.Additionally,the fluctuating impact between nutrient-poor seawater with high dissolved inorganic carbon(DIC)that infiltrates owing to the Kuroshio during El Niño phases and nutrient-rich seawater with low DIC from the South China Sea(SCS)carried by the EAWM during La Niña phases determines the nutrient content in TWS,thereby sculpting appropriate or unsuitable biochemical environment.In this study,based on high-resolution sea-surface partial pressure of carbon dioxide(pCO_(2))data,we investigate the relationship between pCO_(2)level of TWS and ENSO events in winter.The physical mechanisms affecting the anomalous distribution of pCO_(2)level during ENSO are also explored.Stepwise regression was employed to identify the optimal influencing factors for modeling pCO_(2).Results indicate a significant positive correlation between Niño3.4 index and pCO_(2),which is significantly influenced by factors such as sea-surface temperature(SST),chlorophyll-a(Chl a),and DIC.These are related to the anomalously strong Kuroshio intrusion and weaker EAWM during El Niño years.It brings a large amount of high SST water with low nutrient concentration and high DIC,which is detrimental to CO_(2)dissolution and phytoplankton growth over the TWS,leading to an increase in pCO_(2).Conversely,pCO_(2)level is significantly low under the influence of SCS seawater during La Niña years.Based on the characterization of the pCO_(2)level response to ENSO,the carbon balance at TWS can be explored.
基金funding support from NSFC grants(Grant No.52072263)Shanghai Collaborative Innovation Research Center for Multi-network&Multi-modal Rail Transit.
文摘Employing flow space theory and multi-source data,this study examines the spatial net-work structure and factors influencing railway passenger flow,which is crucial for rail planning in densely populated megalopolises.Focusing on China’s Yangtze River Delta(YRD)megalopolis,we utilize social network analysis(SNA)to explore the characteristics of various flow networks and their interactions with the railway passenger flow network.Key findings include:(1)a pronounced polarization effect and core-periphery structure exist in the YRD,notably within industry and railway flow networks;(2)industry and cor-poration flow significantly contributes to rail passenger flow,with corporation networks in commerce,technical services,and finance showing higher similarity to the railway passen-ger flow network;(3)there is significant heterogeneity in the correlation between rail pas-senger flow and other flows within sub-networks formed by connections among nodes of different levels;(4)enhancing railway services at lower-level nodes is essential to mitigate the disparity between population mobility and rail passenger flow and to promote rail transportation equity.This research offers valuable insights for policymakers in developing countries to strategically plan railroad networks in megalopolises.
基金supported by the National Natural Science Foundation of China(No.52172305).
文摘Amidst a global decline in bus ridership,this study pioneers a longitudinal approach to understanding individual-level transitions and churning in urban bus systems.Utilizing a novel framework that leverages smart card data,we construct and analyze user behavior transition matrices over time,employing Markov processes and the Chapman-Kolmogorov Equation.Our analysis,derived from a 22-month dataset from Shenzhen,reveals a two-stage churning process:users first decrease travel frequency before transitioning to irreg-ular travel patterns.Crucially,this study introduces targeted retention policies,including tiered usage incentives and personalized communication strategies,aimed at different stages of the user lifecycle.By offering free subsequent trips to irregular travelers and com-bining policy approaches for users at high risk of churning,we provide actionable insights for transit operators to counter the trend of declining ridership.
基金support from the National Natural Science Foundation of China(No.61674109)the National Key R&D Program of China(No.2016YFA0202400)+3 种基金the Natural Science Foundation of Jiangsu Province(No.BK20170059)the Beijing Natural Science Foundation(No.2182061)Science Foundation of China University of Petroleum,Beijing(No.2462019BJRC001)funded by the Collaborative Innovation Center of Suzhou Nano Science and Technology,the Priority Academic Program Development of Jiangsu Higher Education Institutions(PAPD).
文摘With the increasingly prominent energy and environmental issues,the supercapacitors,as a highly efficient and clean energy conversion and storage devices,meet the requirements well.However,it is still a challenge to enhance the capacitance and energy density of supercapacitors.A novel and highly conductive dodecaborate/MXene composites have been designed for high performance supercapacitors.The surface charge property of MXene was modified by a simple ultrasonic treatment with ammonium ion,and the dodecaborate ion can be inserted into the inner surface of MXene by electrostatic adsorption.Due to the unique icosahedral cage conjugate structure formed by the B-B bond and the highly delocalized three-dimensionalπbond structure of the electrons,the negative charge is delocalied on the whole dodecaborate ion,which reduces the ability to bind to cations.Therefore,the cations can move easily,and the dodecaborate can act as a“lubricant”for ion diffusion between the MXene layers,which significantly improves the ion transfer rate of supercapacitors.The dodecaborate/MXene composites can achieve an extremely high specific capacitance of 366 F.g^-1 at a scan rate of 2 mV.s^-1,which is more than eight times higher than that of MXene(43 F1-)at the same scan rate.Our finding provides a novel route on the fabrication of the high performance supercapacitors.
基金support for the work from the Ministry of Science and Technology of China (2020YFA0908900)National Natural Science Foundation of China (21935011 and 21725403)+2 种基金Shenzhen Science and Technology Innovation Commission (KQTD20200820113012029,JCYJ20190814114605162,and JCYJ20220818100601003)Guangdong Basic and Applied Basic Research Foundation (2022A1515110321)Guangdong Provincial Key Laboratory of Advanced Biomaterials (2022B1212010003).
文摘Effective control of post-extraction hemorrhage and alveolar bone resorption is critical for successful extraction socket treatment,which remains an unmet clinical challenge.Herein,an injectable Tetra-PEG hydrogel that possesses rapid gelation,firm tissue adhesion,high mechanical strength,suitable degradability,and excellent biocompatibility is developed as a sutureless and coagulation-independent bioadhesive for the management of extraction sockets.Our results demonstrate that the rapid and robust adhesive sealing of the extraction socket by the Tetra-PEG hydrogel can provide reliable protection for the underlying wound and stabilize blood clots to facilitate tissue healing.In vivo experiments using an anticoagulated rat tooth extraction model show that the hydrogel significantly outperformed clinically used cotton and gelatin sponge in hemostatic efficacy,wound closure,alveolar ridge preservation,and in situ alveolar bone regeneration.Histomorphological evaluations reveal the mechanisms for accelerated bone repair through suppressed long-term inflammation,elevated collagen deposition,higher osteoblast activity,and enhanced angiogenesis.Together,our study highlights the clinical potential of the developed injectable Tetra-PEG hydrogel for treating anticoagulant-related post-extraction hemorrhage and improving socket healing.
文摘A social stream refers to the data stream that records a series of social entities and the dynamic interac-tions between two entities. It can be employed to model the changes of entity states in numerous applications. The social streams, the combination of graph and streaming data, pose great challenge to efficient analytical query processing, and are key to better understanding users' behavior. Considering of privacy and other related issues, a social stream genera-tor is of great significance. A framework of synthetic social stream generator (SSG) is proposed in this paper. The gener-ated social streams using SSG can be tuned to capture sev-eral kinds of fundamental social stream properties, includ-ing patterns about users' behavior and graph patterns. Ex-tensive empirical studies with several real-life social stream data sets show that SSG can produce data that better fit to real data. It is also confirmed that SSG can generate social stream data continuously with stable throughput and memory consumption. Furthermore, we propose a parallel implemen-tation of SSG with the help of asynchronized parallel pro-cessing model and delayed update strategy. Our experiments verify that the throughput of the parallel implementation can increase linearly by increasing nodes.
基金supported by the Shanghai Sailing Program of China(ID:20YF1451700)the Science and Technology Commission of Shanghai Municipality of China(Nos.23692119000&21692112203)the Fundamental Research Funds for the Central Universities of China(No.2023-4-YB-01).
文摘Due to the increasing demand for goods movement,externalities from freight mobility have attracted much concern among local citizens and policymakers.Freight truck-related crash is one of these externalities and impacts urban freight transportation most drastically.Previous studies have mainly focused on correlation analyses of influencing factors based on crash density/count data,but have paid little attention to the inherent uncertainties of freight truck-related crashes(FTCs)from a spatial perspective.While establishing an interpretable analysis model for freight truck-related accidents that consid-ers uncertainties is of great significance for promoting the robust development of urban freight transportation systems.Hence,this study proposes the concept of FTC hazard(FTCH),and employs the Bayesian neural network(BNN)model based on stochastic varia-tional inference to model uncertainty.Considering the difficulty in interpreting deep learning-based models,this study introduces the local interpretable modelagnostic expla-nation(LIME)model into the analysis framework to explain the results of the neural net-work model.This study then verifies the feasibility of the proposed analysis framework using data from California from 2011 to 2020.Results show that FTCHs can be effectively modeled by predicting confidence intervals for effects of built environment factors,in par-ticular demographics,land use,and road network structure.Results based on LIME values indicate the spatial heterogeneity in influence mechanisms on FTCHs between areas within the metropolitan regions and alongside the freeways.These findings may help transport planners and logistic managers develop more effective measures to avoid potential nega-tive effects brought by FTCHs in local communities.
基金supported in part by the National Natural Science Foundation of China(Grant No.5217051006)the Shandong Province Natural Science Foundation(Grant No.ZR2021ME223)+1 种基金the Yantai Science and Technology Planning Project(Grant No.2022GCCRC158)the Graduate Innovation Foundation of Yantai University,GIFYTU(Grant No.GGIFYTU2349).
文摘The accurate estimation of the remaining charge time(RCT)is essential in a battery management system(BMS),because it guarantees the safety and dependability of the power battery systems of new energy vehicles.However,the direct estimation of RCT is challenging because of the variability of actual charging scenarios and the complex charging process,which complicates the estimation of RCT in actual scenarios.Hence,this paper proposes an estimation framework based on deep learning for multi-scenario charging data to estimate the remaining charging times.Through an in-depth analysis of multi-scenario charging data,the RCT of the charging process is estimated using the temporal convolutional network(TCN)model,which has a strong generalization ability.Additionally,a dynamic learning rate(DLR)mechanism and an early stopping strategy(ES)are designed in the TCN model(DLR-ES TCN)for the nonlinear characteristics of the battery system to balance the relationship between model convergence speed and accuracy.Finally,compared with the traditional TCN model and four common deep learning models under three different scenarios,the experimental results show the mean absolute percentage error(MAPE)of the proposed method is less than 2%,indicating better accuracy and stability.This research can improve the safety monitoring of power batteries when applied to various target domains.
