Traffic in today’s cities is a serious problem that increases travel times,negatively affects the environment,and drains financial resources.This study presents an Artificial Intelligence(AI)augmentedMobile Ad Hoc Ne...Traffic in today’s cities is a serious problem that increases travel times,negatively affects the environment,and drains financial resources.This study presents an Artificial Intelligence(AI)augmentedMobile Ad Hoc Networks(MANETs)based real-time prediction paradigm for urban traffic challenges.MANETs are wireless networks that are based on mobile devices and may self-organize.The distributed nature of MANETs and the power of AI approaches are leveraged in this framework to provide reliable and timely traffic congestion forecasts.This study suggests a unique Chaotic Spatial Fuzzy Polynomial Neural Network(CSFPNN)technique to assess real-time data acquired from various sources within theMANETs.The framework uses the proposed approach to learn from the data and create predictionmodels to detect possible traffic problems and their severity in real time.Real-time traffic prediction allows for proactive actions like resource allocation,dynamic route advice,and traffic signal optimization to reduce congestion.The framework supports effective decision-making,decreases travel time,lowers fuel use,and enhances overall urban mobility by giving timely information to pedestrians,drivers,and urban planners.Extensive simulations and real-world datasets are used to test the proposed framework’s prediction accuracy,responsiveness,and scalability.Experimental results show that the suggested framework successfully anticipates urban traffic issues in real-time,enables proactive traffic management,and aids in creating smarter,more sustainable cities.展开更多
Predicting the mechanical behaviors of structure and perceiving the anomalies in advance are essential to ensuring the safe operation of infrastructures in the long run.In addition to the incomplete consideration of i...Predicting the mechanical behaviors of structure and perceiving the anomalies in advance are essential to ensuring the safe operation of infrastructures in the long run.In addition to the incomplete consideration of influencing factors,the prediction time scale of existing studies is rough.Therefore,this study focuses on the development of a real-time prediction model by coupling the spatio-temporal correlation with external load through autoencoder network(ATENet)based on structural health monitoring(SHM)data.An autoencoder mechanism is performed to acquire the high-level representation of raw monitoring data at different spatial positions,and the recurrent neural network is applied to understanding the temporal correlation from the time series.Then,the obtained temporal-spatial information is coupled with dynamic loads through a fully connected layer to predict structural performance in next 12 h.As a case study,the proposed model is formulated on the SHM data collected from a representative underwater shield tunnel.The robustness study is carried out to verify the reliability and the prediction capability of the proposed model.Finally,the ATENet model is compared with some typical models,and the results indicate that it has the best performance.ATENet model is of great value to predict the realtime evolution trend of tunnel structure.展开更多
Intelligent healthcare networks represent a significant component in digital applications,where the requirements hold within quality-of-service(QoS)reliability and safeguarding privacy.This paper addresses these requi...Intelligent healthcare networks represent a significant component in digital applications,where the requirements hold within quality-of-service(QoS)reliability and safeguarding privacy.This paper addresses these requirements through the integration of enabler paradigms,including federated learning(FL),cloud/edge computing,softwaredefined/virtualized networking infrastructure,and converged prediction algorithms.The study focuses on achieving reliability and efficiency in real-time prediction models,which depend on the interaction flows and network topology.In response to these challenges,we introduce a modified version of federated logistic regression(FLR)that takes into account convergence latencies and the accuracy of the final FL model within healthcare networks.To establish the FLR framework for mission-critical healthcare applications,we provide a comprehensive workflow in this paper,introducing framework setup,iterative round communications,and model evaluation/deployment.Our optimization process delves into the formulation of loss functions and gradients within the domain of federated optimization,which concludes with the generation of service experience batches for model deployment.To assess the practicality of our approach,we conducted experiments using a hypertension prediction model with data sourced from the 2019 annual dataset(Version 2.0.1)of the Korea Medical Panel Survey.Performance metrics,including end-to-end execution delays,model drop/delivery ratios,and final model accuracies,are captured and compared between the proposed FLR framework and other baseline schemes.Our study offers an FLR framework setup for the enhancement of real-time prediction modeling within intelligent healthcare networks,addressing the critical demands of QoS reliability and privacy preservation.展开更多
It is critical to determine whether a site has potential damage in real-time after an earthquake occurs,which is a challenge in earthquake disaster reduction.Here,we propose a real-time Earthquake Potential Damage pre...It is critical to determine whether a site has potential damage in real-time after an earthquake occurs,which is a challenge in earthquake disaster reduction.Here,we propose a real-time Earthquake Potential Damage predictor(EPDor)based on predicting peak ground velocities(PGVs)of sites.The EPDor is composed of three parts:(1)predicting the magnitude of an earthquake and PGVs of triggered stations based on the machine learning prediction models;(2)predicting the PGVs at distant sites based on the empirical ground motion prediction equation;(3)generating the PGV map through predicting the PGV of each grid point based on an interpolation process of weighted average based on the predicted values in(1)and(2).We apply the EPDor to the 2022 M_(S) 6.9 Menyuan earthquake in Qinghai Province,China to predict its potential damage.Within the initial few seconds after the first station is triggered,the EPDor can determine directly whether there is potential damage for some sites to a certain degree.Hence,we infer that the EPDor has potential application for future earthquakes.Meanwhile,it also has potential in Chinese earthquake early warning system.展开更多
Based on data from the Jilin Water Diversion Tunnels from the Songhua River(China),an improved and real-time prediction method optimized by multi-algorithm for tunnel boring machine(TBM)cutter-head torque is presented...Based on data from the Jilin Water Diversion Tunnels from the Songhua River(China),an improved and real-time prediction method optimized by multi-algorithm for tunnel boring machine(TBM)cutter-head torque is presented.Firstly,a function excluding invalid and abnormal data is established to distinguish TBM operating state,and a feature selection method based on the SelectKBest algorithm is proposed.Accordingly,ten features that are most closely related to the cutter-head torque are selected as input variables,which,in descending order of influence,include the sum of motor torque,cutter-head power,sum of motor power,sum of motor current,advance rate,cutter-head pressure,total thrust force,penetration rate,cutter-head rotational velocity,and field penetration index.Secondly,a real-time cutterhead torque prediction model’s structure is developed,based on the bidirectional long short-term memory(BLSTM)network integrating the dropout algorithm to prevent overfitting.Then,an algorithm to optimize hyperparameters of model based on Bayesian and cross-validation is proposed.Early stopping and checkpoint algorithms are integrated to optimize the training process.Finally,a BLSTMbased real-time cutter-head torque prediction model is developed,which fully utilizes the previous time-series tunneling information.The mean absolute percentage error(MAPE)of the model in the verification section is 7.3%,implying that the presented model is suitable for real-time cutter-head torque prediction.Furthermore,an incremental learning method based on the above base model is introduced to improve the adaptability of the model during the TBM tunneling.Comparison of the prediction performance between the base and incremental learning models in the same tunneling section shows that:(1)the MAPE of the predicted results of the BLSTM-based real-time cutter-head torque prediction model remains below 10%,and both the coefficient of determination(R^(2))and correlation coefficient(r)between measured and predicted values exceed 0.95;and(2)the incremental learning method is suitable for realtime cutter-head torque prediction and can effectively improve the prediction accuracy and generalization capacity of the model during the excavation process.展开更多
This paper has two purposes. One is to evaluate the ability of an atmospheric general circulation model (IAP9L-AGCM) to predict summer rainfall over China one season in advance. The other is to propose a new approach ...This paper has two purposes. One is to evaluate the ability of an atmospheric general circulation model (IAP9L-AGCM) to predict summer rainfall over China one season in advance. The other is to propose a new approach to improve the predictions made by the model. First, a set of hindcast experiments for summer climate over China during 1982-2010 are performed from the perspective of real-time prediction with the IAP9L-AGCM model and the IAP ENSO prediction system. Then a new approach that effectively combines the hind-cast with its correction is proposed to further improve the model's predictive ability. A systematic evaluation reveals that the model's real-time predictions for 41 stations across China show significant improvement using this new approach, especially in the lower reaches between the Yellow River and Yangtze River valleys.展开更多
Following triple La Nina events during 2020–2022,the future evolution of climate conditions over the tropical Pacific has been a focused interest in ENSO-related communities.Observations and modeling studies indicate...Following triple La Nina events during 2020–2022,the future evolution of climate conditions over the tropical Pacific has been a focused interest in ENSO-related communities.Observations and modeling studies indicate that an El Nino event is occurring in 2023;however,large uncertainties remain in terms of its detailed evolution,and the factors affecting its resultant amplitude remain to be understood.Here,a novel deep learning-based Transformer model is adopted to make real-time predictions for the 2023–2024 climate conditions in the tropical Pacific.Several key fields vital to the El Nino and Southern Oscillation(ENSO)in the tropical Pacific are collectively and simultaneously utilized in model training and in making predictions;therefore,this purely data-driven model is configured in both training and predicting procedures such that the coupled ocean-atmosphere interactions are adequately represented.Also similar to dynamic models,the prediction procedure is executed in a rolling manner to allow ocean-atmosphere anomaly exchanges month by month;the related key fields during multi-month time intervals(TIs)prior to prediction target months are taken as input predictors,serving as initial conditions to precondition the future evolution more effectively.Real-time predictions indicate that the climate conditions in the tropical Pacific are surely to develop into an El Nino state in late 2023.Furthermore,sensitivity experiments are conducted to examine how prediction skills are affected by the input predictor specifications,including TIs during which information on initial conditions is retained for making predictions.A comparison with other dynamic coupled models is also made to demonstrate the prediction performance for the 2023–2024 El Nino event.展开更多
The presented research introduces a novel hybrid deep learning approach for the dynamic prediction of the attitude and position of super-large diameter shields-a critical consideration for construction safety and tunn...The presented research introduces a novel hybrid deep learning approach for the dynamic prediction of the attitude and position of super-large diameter shields-a critical consideration for construction safety and tunnel lining quality.This study proposes a hybrid deep learning approach for predicting dynamic attitude and position prediction of super-large diameter shield.The approach consists of principal component analysis(PCA)and temporal convolutional network(TCN).The former is used for employing feature level fusion based on features of the shield data to reduce uncertainty,improve accuracy and the data effect,and 9 sets of required principal component characteristic data are obtained.The latter is adopted to process sequence data in predicting the dynamic attitude and position for the advantages and potential of convolution network.The approach’s effectiveness is exemplified using data from a tunnel construction project in China.The obtained results show remarkable accuracy in predicting the global attitude and position,with an average error ratio of less than 2 mm on four shield outputs in 97.30%of cases.Moreover,the approach displays strong performance in accurately predicting sudden fluctuations in shield attitude and position,with an average prediction accuracy of 89.68%.The proposed hybrid model demonstrates superiority over TCN,long short-term memory(LSTM),and recurrent neural network(RNN)in multiple indexes.Shapley additive exPlanations(SHAP)analysis is also performed to investigate the significance of different data features in the prediction process.This study provides a real-time warning for the shield driver to adjust the attitude and position of super-large diameter shields.展开更多
The research focuses on improving predictive accuracy in the financial sector through the exploration of machine learning algorithms for stock price prediction. The research follows an organized process combining Agil...The research focuses on improving predictive accuracy in the financial sector through the exploration of machine learning algorithms for stock price prediction. The research follows an organized process combining Agile Scrum and the Obtain, Scrub, Explore, Model, and iNterpret (OSEMN) methodology. Six machine learning models, namely Linear Forecast, Naive Forecast, Simple Moving Average with weekly window (SMA 5), Simple Moving Average with monthly window (SMA 20), Autoregressive Integrated Moving Average (ARIMA), and Long Short-Term Memory (LSTM), are compared and evaluated through Mean Absolute Error (MAE), with the LSTM model performing the best, showcasing its potential for practical financial applications. A Django web application “Predict It” is developed to implement the LSTM model. Ethical concerns related to predictive modeling in finance are addressed. Data quality, algorithm choice, feature engineering, and preprocessing techniques are emphasized for better model performance. The research acknowledges limitations and suggests future research directions, aiming to equip investors and financial professionals with reliable predictive models for dynamic markets.展开更多
Accurate prediction of multiphase flowing bottom-hole pressure(FBHP)in wellbores is an important factor required for optimal tubing design and production optimization.Existing empirical correlations and mechanistic mo...Accurate prediction of multiphase flowing bottom-hole pressure(FBHP)in wellbores is an important factor required for optimal tubing design and production optimization.Existing empirical correlations and mechanistic models provide inaccurate FBHP predictions when applied to real-time field datasets because they were developed with laboratory-dependent parameters.Most machine learning(ML)models for FBHP prediction are developed with real-time field data but presented as black-box models.In addition,these ML models cannot be reproduced by other users because the dataset used for training the machine learning algorithm is not open source.These make using the ML models on new datasets difficult.This study presents an artificial neural network(ANN)visible mathematical model for real-time multiphase FBHP prediction in wellbores.A total of 1001 normalized real-time field data points were first used in developing an ANN black-box model.The data points were randomly divided into three different sets;70%for training,15%for validation,and the remaining 15%for testing.Statistical analysis showed that using the Levenberg-Marquardt training optimization algorithm(trainlm),hyperbolic tangent activation function(tansig),and three hidden layers with 20,15 and 15 neurons in the first,second and third hidden layers respectively achieved the best performance.The trained ANN model was then translated into an ANN visible mathematical model by extracting the tuned weights and biases.Trend analysis shows that the new model produced the expected effects of physical attributes on FBHP.Furthermore,statistical and graphical error analysis results show that the new model outperformed existing empirical correlations,mechanistic models,and an ANN white-box model.Training of the ANN on a larger dataset containing new data points covering a wider range of each input parameter can broaden the applicability domain of the proposed ANN visible mathematical model.展开更多
Fuel consumption is one of the main concerns for heavy-duty trucks.Predictive cruise control(PCC)provides an intriguing opportunity to reduce fuel consumption by using the upcoming road information.In this study,a rea...Fuel consumption is one of the main concerns for heavy-duty trucks.Predictive cruise control(PCC)provides an intriguing opportunity to reduce fuel consumption by using the upcoming road information.In this study,a real-time implementable PCC,which simultaneously optimizes engine torque and gear shifting,is proposed for heavy-duty trucks.To minimize fuel consumption,the problem of the PCC is formulated as a nonlinear model predictive control(MPC),in which the upcoming road elevation information is used.Finding the solution of the nonlinear MPC is time consuming;thus,a real-time implementable solver is developed based on Pontryagin’s maximum principle and indirect shooting method.Dynamic programming(DP)algorithm,as a global optimization algorithm,is used as a performance benchmark for the proposed solver.Simulation,hardware-in-the-loop and real-truck experiments are conducted to verify the performance of the proposed controller.The results demonstrate that the MPC-based solution performs nearly as well as the DP-based solution,with less than 1%deviation for testing roads.Moreover,the proposed co-optimization controller is implementable in a real-truck,and the proposed MPC-based PCC algorithm achieves a fuel-saving rate of 7.9%without compromising the truck’s travel time.展开更多
Real-time perception of rock conditions based on continuously collected data to meet the requirements of continuous Tunnel Boring Machine(TBM)construction presents a critical challenge that warrants increased attentio...Real-time perception of rock conditions based on continuously collected data to meet the requirements of continuous Tunnel Boring Machine(TBM)construction presents a critical challenge that warrants increased attention.To achieve this goal,this paper establishes real-time prediction models for fractured and weak rock mass by comparing 6 different algorithms using real-time data collected by the TBM.The models are optimized in terms of selecting metric,selecting input features,and processing imbalanced data.The results demonstrate the following points.(1)The Youden's index and area under the ROC curve(AUC)are the most appropriate performance metrics,and the XGBoost Random Forest(XGBRF)algorithm exhibits superior prediction and generalization performance.(2)The duration of the TBM loading phase is short,usually within a few minutes after the disc cutter contacts the tunnel face.A model based on the features during the loading phase has a miss rate of 21.8%,indicating that it can meet the early warning needs of TBM construction well.As the TBM continues to operate,the inclusion of features calculated from subsequent data collection can continuously correct the results of the real-time prediction model,ultimately reducing the miss rate to 16.1%.(3)Resampling the imbalanced data set can effectively improve the prediction by the model,while the XGBRF algorithm has certain advantages in dealing with the imbalanced data issue.When the model gives an alarm,the TBM operator and on-site engineer can be reminded and take some necessary measures for avoiding potential tunnel collapse.The real-time predication model can be a useful tool to increase the safety of TBM excavation.展开更多
The tropical Pacific is currently experiencing an El Nifio event. Various coupled models with different degrees of complexity have been used to make real-time E1 Nifio predictions, but large uncertainties exist in the...The tropical Pacific is currently experiencing an El Nifio event. Various coupled models with different degrees of complexity have been used to make real-time E1 Nifio predictions, but large uncertainties exist in the inten- sity forecast and are strongly model dependent. An intermediate coupled model （ICM） is used at the Institute of Oceanology, Chinese Academy of Sciences （IOCAS）, named the IOCAS ICM, to predict the sea surface temper- ature （SST） evolution in the tropical Pacific during the 2015-2016 E! Nifio event. One unique feature of the IOCAS ICM is the way in which the temperature of subsurface water entrained in the mixed layer （Te） is parameterized. Observed SST anomalies are only field that is utilized to initialize the coupled prediction using the IOCAS ICM. Examples are given of the model＇s ability to predict the SST conditions in a real-time manner. As is commonly evident in E1 Nifio- Southern Oscillation predictions using coupled models, large discrepancies occur between the observed and pre- dicted SST anomalies in spring 2015. Starting from early summer 2015, the model can realistically predict warming conditions. Thereafter, good predictions can be made through the summer and fall seasons of 2015. A transition to normal and cold conditions is predictecl to occur in rote spring 2016. Comparisons with other model predictions are made and factors influencing the prediction performance of the IOCAS ICM are also discussed.展开更多
This work constructed a machine learning(ML)model to predict the atmospheric corrosion rate of low-alloy steels(LAS).The material properties of LAS,environmental factors,and exposure time were used as the input,while ...This work constructed a machine learning(ML)model to predict the atmospheric corrosion rate of low-alloy steels(LAS).The material properties of LAS,environmental factors,and exposure time were used as the input,while the corrosion rate as the output.6 dif-ferent ML algorithms were used to construct the proposed model.Through optimization and filtering,the eXtreme gradient boosting(XG-Boost)model exhibited good corrosion rate prediction accuracy.The features of material properties were then transformed into atomic and physical features using the proposed property transformation approach,and the dominant descriptors that affected the corrosion rate were filtered using the recursive feature elimination(RFE)as well as XGBoost methods.The established ML models exhibited better predic-tion performance and generalization ability via property transformation descriptors.In addition,the SHapley additive exPlanations(SHAP)method was applied to analyze the relationship between the descriptors and corrosion rate.The results showed that the property transformation model could effectively help with analyzing the corrosion behavior,thereby significantly improving the generalization ability of corrosion rate prediction models.展开更多
The scientific community recognizes the seriousness of rockbursts and the need for effective mitigation measures.The literature reports various successful applications of machine learning(ML)models for rockburst asses...The scientific community recognizes the seriousness of rockbursts and the need for effective mitigation measures.The literature reports various successful applications of machine learning(ML)models for rockburst assessment;however,a significant question remains unanswered:How reliable are these models,and at what confidence level are classifications made?Typically,ML models output single rockburst grade even in the face of intricate and out-of-distribution samples,without any associated confidence value.Given the susceptibility of ML models to errors,it becomes imperative to quantify their uncertainty to prevent consequential failures.To address this issue,we propose a conformal prediction(CP)framework built on traditional ML models(extreme gradient boosting and random forest)to generate valid classifications of rockburst while producing a measure of confidence for its output.The proposed framework guarantees marginal coverage and,in most cases,conditional coverage on the test dataset.The CP was evaluated on a rockburst case in the Sanshandao Gold Mine in China,where it achieved high coverage and efficiency at applicable confidence levels.Significantly,the CP identified several“confident”classifications from the traditional ML model as unreliable,necessitating expert verification for informed decision-making.The proposed framework improves the reliability and accuracy of rockburst assessments,with the potential to bolster user confidence.展开更多
Deep engineering disasters,such as rockbursts and collapses,are more related to the shear slip of rock joints.A novel multifunctional device was developed to study the shear failure mechanism in rocks.Using this devic...Deep engineering disasters,such as rockbursts and collapses,are more related to the shear slip of rock joints.A novel multifunctional device was developed to study the shear failure mechanism in rocks.Using this device,the complete shearedeformation process and long-term shear creep tests could be performed on rocks under constant normal stiffness(CNS)or constant normal loading(CNL)conditions in real-time at high temperature and true-triaxial stress.During the research and development process,five key technologies were successfully broken through:(1)the ability to perform true-triaxial compressioneshear loading tests on rock samples with high stiffness;(2)a shear box with ultra-low friction throughout the entire stress space of the rock sample during loading;(3)a control system capable of maintaining high stress for a long time and responding rapidly to the brittle fracture of a rock sample as well;(4)a refined ability to measure the volumetric deformation of rock samples subjected to true triaxial shearing;and(5)a heating system capable of maintaining uniform heating of the rock sample over a long time.By developing these technologies,loading under high true triaxial stress conditions was realized.The apparatus has a maximum normal stiffness of 1000 GPa/m and a maximum operating temperature of 300C.The differences in the surface temperature of the sample are constant to within5C.Five types of true triaxial shear tests were conducted on homogeneous sandstone to verify that the apparatus has good performance and reliability.The results show that temperature,lateral stress,normal stress and time influence the shear deformation,failure mode and strength of the sandstone.The novel apparatus can be reliably used to conduct true-triaxial shear tests on rocks subjected to high temperatures and stress.展开更多
Accurate prediction of tropical cyclone(TC)intensity is challenging due to the complex physical processes involved.Here,we introduce a new TC intensity prediction scheme for the western North Pacific(WNP)based on a ti...Accurate prediction of tropical cyclone(TC)intensity is challenging due to the complex physical processes involved.Here,we introduce a new TC intensity prediction scheme for the western North Pacific(WNP)based on a time-dependent theory of TC intensification,termed the energetically based dynamical system(EBDS)model,together with the use of a long short-term memory(LSTM)neural network.In time-dependent theory,TC intensity change is controlled by both the internal dynamics of the TC system and various environmental factors,expressed as environmental dynamical efficiency.The LSTM neural network is used to predict the environmental dynamical efficiency in the EBDS model trained using besttrack TC data and global reanalysis data during 1982–2017.The transfer learning and ensemble methods are used to retrain the scheme using the environmental factors predicted by the Global Forecast System(GFS)of the National Centers for Environmental Prediction during 2017–21.The predicted environmental dynamical efficiency is finally iterated into the EBDS equations to predict TC intensity.The new scheme is evaluated for TC intensity prediction using both reanalysis data and the GFS prediction data.The intensity prediction by the new scheme shows better skill than the official prediction from the China Meteorological Administration(CMA)and those by other state-of-art statistical and dynamical forecast systems,except for the 72-h forecast.Particularly at the longer lead times of 96 h and 120 h,the new scheme has smaller forecast errors,with a more than 30%improvement over the official forecasts.展开更多
The scarcity of in-situ ocean observations poses a challenge for real-time information acquisition in the ocean.Among the crucial hydroacoustic environmental parameters,ocean sound velocity exhibits significant spatia...The scarcity of in-situ ocean observations poses a challenge for real-time information acquisition in the ocean.Among the crucial hydroacoustic environmental parameters,ocean sound velocity exhibits significant spatial and temporal variability and it is highly relevant to oceanic research.In this study,we propose a new data-driven approach,leveraging deep learning techniques,for the prediction of sound velocity fields(SVFs).Our novel spatiotemporal prediction model,STLSTM-SA,combines Spatiotemporal Long Short-Term Memory(ST-LSTM) with a self-attention mechanism to enable accurate and real-time prediction of SVFs.To circumvent the limited amount of observational data,we employ transfer learning by first training the model using reanalysis datasets,followed by fine-tuning it using in-situ analysis data to obtain the final prediction model.By utilizing the historical 12-month SVFs as input,our model predicts the SVFs for the subsequent three months.We compare the performance of five models:Artificial Neural Networks(ANN),Long ShortTerm Memory(LSTM),Convolutional LSTM(ConvLSTM),ST-LSTM,and our proposed ST-LSTM-SA model in a test experiment spanning 2019 to 2022.Our results demonstrate that the ST-LSTM-SA model significantly improves the prediction accuracy and stability of sound velocity in both temporal and spatial dimensions.The ST-LSTM-SA model not only accurately predicts the ocean sound velocity field(SVF),but also provides valuable insights for spatiotemporal prediction of other oceanic environmental variables.展开更多
In recent years,deep learning methods have gradually been applied to prediction tasks related to Arctic sea ice concentration,but relatively little research has been conducted for larger spatial and temporal scales,ma...In recent years,deep learning methods have gradually been applied to prediction tasks related to Arctic sea ice concentration,but relatively little research has been conducted for larger spatial and temporal scales,mainly due to the limited time coverage of observations and reanalysis data.Meanwhile,deep learning predictions of sea ice thickness(SIT)have yet to receive ample attention.In this study,two data-driven deep learning(DL)models are built based on the ConvLSTM and fully convolutional U-net(FC-Unet)algorithms and trained using CMIP6 historical simulations for transfer learning and fine-tuned using reanalysis/observations.These models enable monthly predictions of Arctic SIT without considering the complex physical processes involved.Through comprehensive assessments of prediction skills by season and region,the results suggest that using a broader set of CMIP6 data for transfer learning,as well as incorporating multiple climate variables as predictors,contribute to better prediction results,although both DL models can effectively predict the spatiotemporal features of SIT anomalies.Regarding the predicted SIT anomalies of the FC-Unet model,the spatial correlations with reanalysis reach an average level of 89%over all months,while the temporal anomaly correlation coefficients are close to unity in most cases.The models also demonstrate robust performances in predicting SIT and SIE during extreme events.The effectiveness and reliability of the proposed deep transfer learning models in predicting Arctic SIT can facilitate more accurate pan-Arctic predictions,aiding climate change research and real-time business applications.展开更多
基金the Deanship of Scientific Research at Majmaah University for supporting this work under Project No.R-2024-1008.
文摘Traffic in today’s cities is a serious problem that increases travel times,negatively affects the environment,and drains financial resources.This study presents an Artificial Intelligence(AI)augmentedMobile Ad Hoc Networks(MANETs)based real-time prediction paradigm for urban traffic challenges.MANETs are wireless networks that are based on mobile devices and may self-organize.The distributed nature of MANETs and the power of AI approaches are leveraged in this framework to provide reliable and timely traffic congestion forecasts.This study suggests a unique Chaotic Spatial Fuzzy Polynomial Neural Network(CSFPNN)technique to assess real-time data acquired from various sources within theMANETs.The framework uses the proposed approach to learn from the data and create predictionmodels to detect possible traffic problems and their severity in real time.Real-time traffic prediction allows for proactive actions like resource allocation,dynamic route advice,and traffic signal optimization to reduce congestion.The framework supports effective decision-making,decreases travel time,lowers fuel use,and enhances overall urban mobility by giving timely information to pedestrians,drivers,and urban planners.Extensive simulations and real-world datasets are used to test the proposed framework’s prediction accuracy,responsiveness,and scalability.Experimental results show that the suggested framework successfully anticipates urban traffic issues in real-time,enables proactive traffic management,and aids in creating smarter,more sustainable cities.
基金This work is supported by the National Natural Science Foundation of China(Grant No.51991392)Key Deployment Projects of Chinese Academy of Sciences(Grant No.ZDRW-ZS-2021-3-3)the Second Tibetan Plateau Scientific Expedition and Research Program(STEP)(Grant No.2019QZKK0904).
文摘Predicting the mechanical behaviors of structure and perceiving the anomalies in advance are essential to ensuring the safe operation of infrastructures in the long run.In addition to the incomplete consideration of influencing factors,the prediction time scale of existing studies is rough.Therefore,this study focuses on the development of a real-time prediction model by coupling the spatio-temporal correlation with external load through autoencoder network(ATENet)based on structural health monitoring(SHM)data.An autoencoder mechanism is performed to acquire the high-level representation of raw monitoring data at different spatial positions,and the recurrent neural network is applied to understanding the temporal correlation from the time series.Then,the obtained temporal-spatial information is coupled with dynamic loads through a fully connected layer to predict structural performance in next 12 h.As a case study,the proposed model is formulated on the SHM data collected from a representative underwater shield tunnel.The robustness study is carried out to verify the reliability and the prediction capability of the proposed model.Finally,the ATENet model is compared with some typical models,and the results indicate that it has the best performance.ATENet model is of great value to predict the realtime evolution trend of tunnel structure.
基金supported by Institute of Information&Communications Technology Planning&Evaluation(IITP)grant funded by the Korea government(MSIT)(No.RS2022-00167197Development of Intelligent 5G/6G Infrastructure Technology for the Smart City)+2 种基金in part by the National Research Foundation of Korea(NRF),Ministry of Education,through Basic Science Research Program under Grant NRF-2020R1I1A3066543in part by BK21 FOUR(Fostering Outstanding Universities for Research)under Grant 5199990914048in part by the Soonchunhyang University Research Fund.
文摘Intelligent healthcare networks represent a significant component in digital applications,where the requirements hold within quality-of-service(QoS)reliability and safeguarding privacy.This paper addresses these requirements through the integration of enabler paradigms,including federated learning(FL),cloud/edge computing,softwaredefined/virtualized networking infrastructure,and converged prediction algorithms.The study focuses on achieving reliability and efficiency in real-time prediction models,which depend on the interaction flows and network topology.In response to these challenges,we introduce a modified version of federated logistic regression(FLR)that takes into account convergence latencies and the accuracy of the final FL model within healthcare networks.To establish the FLR framework for mission-critical healthcare applications,we provide a comprehensive workflow in this paper,introducing framework setup,iterative round communications,and model evaluation/deployment.Our optimization process delves into the formulation of loss functions and gradients within the domain of federated optimization,which concludes with the generation of service experience batches for model deployment.To assess the practicality of our approach,we conducted experiments using a hypertension prediction model with data sourced from the 2019 annual dataset(Version 2.0.1)of the Korea Medical Panel Survey.Performance metrics,including end-to-end execution delays,model drop/delivery ratios,and final model accuracies,are captured and compared between the proposed FLR framework and other baseline schemes.Our study offers an FLR framework setup for the enhancement of real-time prediction modeling within intelligent healthcare networks,addressing the critical demands of QoS reliability and privacy preservation.
基金financially supported by the National Natural Science Foundation of China (U2039209, U1839208, and 51408564)the Natural Science Foundation of Heilongjiang Province (LH2021E119)+1 种基金Spark Program of Earthquake Science (XH23027YB)the National Key Research and Development Program of China (2018YFC1504003).
文摘It is critical to determine whether a site has potential damage in real-time after an earthquake occurs,which is a challenge in earthquake disaster reduction.Here,we propose a real-time Earthquake Potential Damage predictor(EPDor)based on predicting peak ground velocities(PGVs)of sites.The EPDor is composed of three parts:(1)predicting the magnitude of an earthquake and PGVs of triggered stations based on the machine learning prediction models;(2)predicting the PGVs at distant sites based on the empirical ground motion prediction equation;(3)generating the PGV map through predicting the PGV of each grid point based on an interpolation process of weighted average based on the predicted values in(1)and(2).We apply the EPDor to the 2022 M_(S) 6.9 Menyuan earthquake in Qinghai Province,China to predict its potential damage.Within the initial few seconds after the first station is triggered,the EPDor can determine directly whether there is potential damage for some sites to a certain degree.Hence,we infer that the EPDor has potential application for future earthquakes.Meanwhile,it also has potential in Chinese earthquake early warning system.
基金financially supported by the National Natural Science Foundation of China (Grant Nos. 52074258, 41941018, and U21A20153)
文摘Based on data from the Jilin Water Diversion Tunnels from the Songhua River(China),an improved and real-time prediction method optimized by multi-algorithm for tunnel boring machine(TBM)cutter-head torque is presented.Firstly,a function excluding invalid and abnormal data is established to distinguish TBM operating state,and a feature selection method based on the SelectKBest algorithm is proposed.Accordingly,ten features that are most closely related to the cutter-head torque are selected as input variables,which,in descending order of influence,include the sum of motor torque,cutter-head power,sum of motor power,sum of motor current,advance rate,cutter-head pressure,total thrust force,penetration rate,cutter-head rotational velocity,and field penetration index.Secondly,a real-time cutterhead torque prediction model’s structure is developed,based on the bidirectional long short-term memory(BLSTM)network integrating the dropout algorithm to prevent overfitting.Then,an algorithm to optimize hyperparameters of model based on Bayesian and cross-validation is proposed.Early stopping and checkpoint algorithms are integrated to optimize the training process.Finally,a BLSTMbased real-time cutter-head torque prediction model is developed,which fully utilizes the previous time-series tunneling information.The mean absolute percentage error(MAPE)of the model in the verification section is 7.3%,implying that the presented model is suitable for real-time cutter-head torque prediction.Furthermore,an incremental learning method based on the above base model is introduced to improve the adaptability of the model during the TBM tunneling.Comparison of the prediction performance between the base and incremental learning models in the same tunneling section shows that:(1)the MAPE of the predicted results of the BLSTM-based real-time cutter-head torque prediction model remains below 10%,and both the coefficient of determination(R^(2))and correlation coefficient(r)between measured and predicted values exceed 0.95;and(2)the incremental learning method is suitable for realtime cutter-head torque prediction and can effectively improve the prediction accuracy and generalization capacity of the model during the excavation process.
基金jointly supported by the Special Fund for Meteorological Scientific Research in the Public Interest of China Meteorological Administration(GYHY201006022)the National Key Technologies R&D Program of China(2009BAC51B02)the National Basic Research Program of China(2010CB950304)
文摘This paper has two purposes. One is to evaluate the ability of an atmospheric general circulation model (IAP9L-AGCM) to predict summer rainfall over China one season in advance. The other is to propose a new approach to improve the predictions made by the model. First, a set of hindcast experiments for summer climate over China during 1982-2010 are performed from the perspective of real-time prediction with the IAP9L-AGCM model and the IAP ENSO prediction system. Then a new approach that effectively combines the hind-cast with its correction is proposed to further improve the model's predictive ability. A systematic evaluation reveals that the model's real-time predictions for 41 stations across China show significant improvement using this new approach, especially in the lower reaches between the Yellow River and Yangtze River valleys.
基金supported by the Laoshan Laboratory(Grant No.LSKJ202202402)the National Natural Science Foundation of China(Grant Nos.42030410&42176032)+2 种基金the Strategic Priority Research Program of the Chinese Academy of Sciences(Grant No.XDB40000000)the Startup Foundation for Introducing Talent of NUISTthe Jiangsu Innovation Research Group(Grant No.JSSCTD202346)。
文摘Following triple La Nina events during 2020–2022,the future evolution of climate conditions over the tropical Pacific has been a focused interest in ENSO-related communities.Observations and modeling studies indicate that an El Nino event is occurring in 2023;however,large uncertainties remain in terms of its detailed evolution,and the factors affecting its resultant amplitude remain to be understood.Here,a novel deep learning-based Transformer model is adopted to make real-time predictions for the 2023–2024 climate conditions in the tropical Pacific.Several key fields vital to the El Nino and Southern Oscillation(ENSO)in the tropical Pacific are collectively and simultaneously utilized in model training and in making predictions;therefore,this purely data-driven model is configured in both training and predicting procedures such that the coupled ocean-atmosphere interactions are adequately represented.Also similar to dynamic models,the prediction procedure is executed in a rolling manner to allow ocean-atmosphere anomaly exchanges month by month;the related key fields during multi-month time intervals(TIs)prior to prediction target months are taken as input predictors,serving as initial conditions to precondition the future evolution more effectively.Real-time predictions indicate that the climate conditions in the tropical Pacific are surely to develop into an El Nino state in late 2023.Furthermore,sensitivity experiments are conducted to examine how prediction skills are affected by the input predictor specifications,including TIs during which information on initial conditions is retained for making predictions.A comparison with other dynamic coupled models is also made to demonstrate the prediction performance for the 2023–2024 El Nino event.
基金financially supported by the National Natural Science Foundation of China(Grant Nos.52078304,51938008,52090084,and 52208354)Guangdong Province Key Field R&D Program Project(Grant Nos.2019B111108001 and 2022B0101070001)+1 种基金Shenzhen Fundamental Research(Grant No.20220525163716003)the Pearl River Delta Water Resources Allocation Project(CD88-GC022020-0038).
文摘The presented research introduces a novel hybrid deep learning approach for the dynamic prediction of the attitude and position of super-large diameter shields-a critical consideration for construction safety and tunnel lining quality.This study proposes a hybrid deep learning approach for predicting dynamic attitude and position prediction of super-large diameter shield.The approach consists of principal component analysis(PCA)and temporal convolutional network(TCN).The former is used for employing feature level fusion based on features of the shield data to reduce uncertainty,improve accuracy and the data effect,and 9 sets of required principal component characteristic data are obtained.The latter is adopted to process sequence data in predicting the dynamic attitude and position for the advantages and potential of convolution network.The approach’s effectiveness is exemplified using data from a tunnel construction project in China.The obtained results show remarkable accuracy in predicting the global attitude and position,with an average error ratio of less than 2 mm on four shield outputs in 97.30%of cases.Moreover,the approach displays strong performance in accurately predicting sudden fluctuations in shield attitude and position,with an average prediction accuracy of 89.68%.The proposed hybrid model demonstrates superiority over TCN,long short-term memory(LSTM),and recurrent neural network(RNN)in multiple indexes.Shapley additive exPlanations(SHAP)analysis is also performed to investigate the significance of different data features in the prediction process.This study provides a real-time warning for the shield driver to adjust the attitude and position of super-large diameter shields.
文摘The research focuses on improving predictive accuracy in the financial sector through the exploration of machine learning algorithms for stock price prediction. The research follows an organized process combining Agile Scrum and the Obtain, Scrub, Explore, Model, and iNterpret (OSEMN) methodology. Six machine learning models, namely Linear Forecast, Naive Forecast, Simple Moving Average with weekly window (SMA 5), Simple Moving Average with monthly window (SMA 20), Autoregressive Integrated Moving Average (ARIMA), and Long Short-Term Memory (LSTM), are compared and evaluated through Mean Absolute Error (MAE), with the LSTM model performing the best, showcasing its potential for practical financial applications. A Django web application “Predict It” is developed to implement the LSTM model. Ethical concerns related to predictive modeling in finance are addressed. Data quality, algorithm choice, feature engineering, and preprocessing techniques are emphasized for better model performance. The research acknowledges limitations and suggests future research directions, aiming to equip investors and financial professionals with reliable predictive models for dynamic markets.
文摘Accurate prediction of multiphase flowing bottom-hole pressure(FBHP)in wellbores is an important factor required for optimal tubing design and production optimization.Existing empirical correlations and mechanistic models provide inaccurate FBHP predictions when applied to real-time field datasets because they were developed with laboratory-dependent parameters.Most machine learning(ML)models for FBHP prediction are developed with real-time field data but presented as black-box models.In addition,these ML models cannot be reproduced by other users because the dataset used for training the machine learning algorithm is not open source.These make using the ML models on new datasets difficult.This study presents an artificial neural network(ANN)visible mathematical model for real-time multiphase FBHP prediction in wellbores.A total of 1001 normalized real-time field data points were first used in developing an ANN black-box model.The data points were randomly divided into three different sets;70%for training,15%for validation,and the remaining 15%for testing.Statistical analysis showed that using the Levenberg-Marquardt training optimization algorithm(trainlm),hyperbolic tangent activation function(tansig),and three hidden layers with 20,15 and 15 neurons in the first,second and third hidden layers respectively achieved the best performance.The trained ANN model was then translated into an ANN visible mathematical model by extracting the tuned weights and biases.Trend analysis shows that the new model produced the expected effects of physical attributes on FBHP.Furthermore,statistical and graphical error analysis results show that the new model outperformed existing empirical correlations,mechanistic models,and an ANN white-box model.Training of the ANN on a larger dataset containing new data points covering a wider range of each input parameter can broaden the applicability domain of the proposed ANN visible mathematical model.
基金Supported by International Technology Cooperation Program of Science and Technology Commission of Shanghai Municipality of China(Grant No.21160710600)National Nature Science Foundation of China(Grant No.52372393)Shanghai Pujiang Program of China(Grant No.21PJD075).
文摘Fuel consumption is one of the main concerns for heavy-duty trucks.Predictive cruise control(PCC)provides an intriguing opportunity to reduce fuel consumption by using the upcoming road information.In this study,a real-time implementable PCC,which simultaneously optimizes engine torque and gear shifting,is proposed for heavy-duty trucks.To minimize fuel consumption,the problem of the PCC is formulated as a nonlinear model predictive control(MPC),in which the upcoming road elevation information is used.Finding the solution of the nonlinear MPC is time consuming;thus,a real-time implementable solver is developed based on Pontryagin’s maximum principle and indirect shooting method.Dynamic programming(DP)algorithm,as a global optimization algorithm,is used as a performance benchmark for the proposed solver.Simulation,hardware-in-the-loop and real-truck experiments are conducted to verify the performance of the proposed controller.The results demonstrate that the MPC-based solution performs nearly as well as the DP-based solution,with less than 1%deviation for testing roads.Moreover,the proposed co-optimization controller is implementable in a real-truck,and the proposed MPC-based PCC algorithm achieves a fuel-saving rate of 7.9%without compromising the truck’s travel time.
基金the National Program on Key Basic Research Project of China(No.2015CB058100)China Railway Engineering Equipment Group Corporation and the Survey and Design Institute of Water Conservancy of Jilin Provincesupported by the Natural Key R&D Program ofChina(No.2022YFE0200400).
文摘Real-time perception of rock conditions based on continuously collected data to meet the requirements of continuous Tunnel Boring Machine(TBM)construction presents a critical challenge that warrants increased attention.To achieve this goal,this paper establishes real-time prediction models for fractured and weak rock mass by comparing 6 different algorithms using real-time data collected by the TBM.The models are optimized in terms of selecting metric,selecting input features,and processing imbalanced data.The results demonstrate the following points.(1)The Youden's index and area under the ROC curve(AUC)are the most appropriate performance metrics,and the XGBoost Random Forest(XGBRF)algorithm exhibits superior prediction and generalization performance.(2)The duration of the TBM loading phase is short,usually within a few minutes after the disc cutter contacts the tunnel face.A model based on the features during the loading phase has a miss rate of 21.8%,indicating that it can meet the early warning needs of TBM construction well.As the TBM continues to operate,the inclusion of features calculated from subsequent data collection can continuously correct the results of the real-time prediction model,ultimately reducing the miss rate to 16.1%.(3)Resampling the imbalanced data set can effectively improve the prediction by the model,while the XGBRF algorithm has certain advantages in dealing with the imbalanced data issue.When the model gives an alarm,the TBM operator and on-site engineer can be reminded and take some necessary measures for avoiding potential tunnel collapse.The real-time predication model can be a useful tool to increase the safety of TBM excavation.
基金the National Natural Science Foundation of China(41490644,41475101 and41421005)the CAS Strategic Priority Project+1 种基金the Western Pacific Ocean System(XDA11010105,XDA11020306 and XDA11010301)the NSFC-Shandong Joint Fund for Marine Science Research Centers(U1406401)
文摘The tropical Pacific is currently experiencing an El Nifio event. Various coupled models with different degrees of complexity have been used to make real-time E1 Nifio predictions, but large uncertainties exist in the inten- sity forecast and are strongly model dependent. An intermediate coupled model （ICM） is used at the Institute of Oceanology, Chinese Academy of Sciences （IOCAS）, named the IOCAS ICM, to predict the sea surface temper- ature （SST） evolution in the tropical Pacific during the 2015-2016 E! Nifio event. One unique feature of the IOCAS ICM is the way in which the temperature of subsurface water entrained in the mixed layer （Te） is parameterized. Observed SST anomalies are only field that is utilized to initialize the coupled prediction using the IOCAS ICM. Examples are given of the model＇s ability to predict the SST conditions in a real-time manner. As is commonly evident in E1 Nifio- Southern Oscillation predictions using coupled models, large discrepancies occur between the observed and pre- dicted SST anomalies in spring 2015. Starting from early summer 2015, the model can realistically predict warming conditions. Thereafter, good predictions can be made through the summer and fall seasons of 2015. A transition to normal and cold conditions is predictecl to occur in rote spring 2016. Comparisons with other model predictions are made and factors influencing the prediction performance of the IOCAS ICM are also discussed.
基金the National Key R&D Program of China(No.2021YFB3701705).
文摘This work constructed a machine learning(ML)model to predict the atmospheric corrosion rate of low-alloy steels(LAS).The material properties of LAS,environmental factors,and exposure time were used as the input,while the corrosion rate as the output.6 dif-ferent ML algorithms were used to construct the proposed model.Through optimization and filtering,the eXtreme gradient boosting(XG-Boost)model exhibited good corrosion rate prediction accuracy.The features of material properties were then transformed into atomic and physical features using the proposed property transformation approach,and the dominant descriptors that affected the corrosion rate were filtered using the recursive feature elimination(RFE)as well as XGBoost methods.The established ML models exhibited better predic-tion performance and generalization ability via property transformation descriptors.In addition,the SHapley additive exPlanations(SHAP)method was applied to analyze the relationship between the descriptors and corrosion rate.The results showed that the property transformation model could effectively help with analyzing the corrosion behavior,thereby significantly improving the generalization ability of corrosion rate prediction models.
文摘The scientific community recognizes the seriousness of rockbursts and the need for effective mitigation measures.The literature reports various successful applications of machine learning(ML)models for rockburst assessment;however,a significant question remains unanswered:How reliable are these models,and at what confidence level are classifications made?Typically,ML models output single rockburst grade even in the face of intricate and out-of-distribution samples,without any associated confidence value.Given the susceptibility of ML models to errors,it becomes imperative to quantify their uncertainty to prevent consequential failures.To address this issue,we propose a conformal prediction(CP)framework built on traditional ML models(extreme gradient boosting and random forest)to generate valid classifications of rockburst while producing a measure of confidence for its output.The proposed framework guarantees marginal coverage and,in most cases,conditional coverage on the test dataset.The CP was evaluated on a rockburst case in the Sanshandao Gold Mine in China,where it achieved high coverage and efficiency at applicable confidence levels.Significantly,the CP identified several“confident”classifications from the traditional ML model as unreliable,necessitating expert verification for informed decision-making.The proposed framework improves the reliability and accuracy of rockburst assessments,with the potential to bolster user confidence.
基金financial support from the National Natural Science Foundation of China(Grant Nos.52209125 and 51839003).
文摘Deep engineering disasters,such as rockbursts and collapses,are more related to the shear slip of rock joints.A novel multifunctional device was developed to study the shear failure mechanism in rocks.Using this device,the complete shearedeformation process and long-term shear creep tests could be performed on rocks under constant normal stiffness(CNS)or constant normal loading(CNL)conditions in real-time at high temperature and true-triaxial stress.During the research and development process,five key technologies were successfully broken through:(1)the ability to perform true-triaxial compressioneshear loading tests on rock samples with high stiffness;(2)a shear box with ultra-low friction throughout the entire stress space of the rock sample during loading;(3)a control system capable of maintaining high stress for a long time and responding rapidly to the brittle fracture of a rock sample as well;(4)a refined ability to measure the volumetric deformation of rock samples subjected to true triaxial shearing;and(5)a heating system capable of maintaining uniform heating of the rock sample over a long time.By developing these technologies,loading under high true triaxial stress conditions was realized.The apparatus has a maximum normal stiffness of 1000 GPa/m and a maximum operating temperature of 300C.The differences in the surface temperature of the sample are constant to within5C.Five types of true triaxial shear tests were conducted on homogeneous sandstone to verify that the apparatus has good performance and reliability.The results show that temperature,lateral stress,normal stress and time influence the shear deformation,failure mode and strength of the sandstone.The novel apparatus can be reliably used to conduct true-triaxial shear tests on rocks subjected to high temperatures and stress.
基金supported by the National Key R&D Program of China(Grant No.2017YFC1501604)the National Natural Science Foundation of China(Grant Nos.41875114 and 41875057).
文摘Accurate prediction of tropical cyclone(TC)intensity is challenging due to the complex physical processes involved.Here,we introduce a new TC intensity prediction scheme for the western North Pacific(WNP)based on a time-dependent theory of TC intensification,termed the energetically based dynamical system(EBDS)model,together with the use of a long short-term memory(LSTM)neural network.In time-dependent theory,TC intensity change is controlled by both the internal dynamics of the TC system and various environmental factors,expressed as environmental dynamical efficiency.The LSTM neural network is used to predict the environmental dynamical efficiency in the EBDS model trained using besttrack TC data and global reanalysis data during 1982–2017.The transfer learning and ensemble methods are used to retrain the scheme using the environmental factors predicted by the Global Forecast System(GFS)of the National Centers for Environmental Prediction during 2017–21.The predicted environmental dynamical efficiency is finally iterated into the EBDS equations to predict TC intensity.The new scheme is evaluated for TC intensity prediction using both reanalysis data and the GFS prediction data.The intensity prediction by the new scheme shows better skill than the official prediction from the China Meteorological Administration(CMA)and those by other state-of-art statistical and dynamical forecast systems,except for the 72-h forecast.Particularly at the longer lead times of 96 h and 120 h,the new scheme has smaller forecast errors,with a more than 30%improvement over the official forecasts.
基金supported by the National Natural Science Foundation of China(Grant No.42004030)Basic Scientific Fund for National Public Research Institutes of China(Grant No.2022S03)+1 种基金Science and Technology Innovation Project(LSKJ202205102)funded by Laoshan Laboratory,and the National Key Research and Development Program of China(2020YFB0505805).
文摘The scarcity of in-situ ocean observations poses a challenge for real-time information acquisition in the ocean.Among the crucial hydroacoustic environmental parameters,ocean sound velocity exhibits significant spatial and temporal variability and it is highly relevant to oceanic research.In this study,we propose a new data-driven approach,leveraging deep learning techniques,for the prediction of sound velocity fields(SVFs).Our novel spatiotemporal prediction model,STLSTM-SA,combines Spatiotemporal Long Short-Term Memory(ST-LSTM) with a self-attention mechanism to enable accurate and real-time prediction of SVFs.To circumvent the limited amount of observational data,we employ transfer learning by first training the model using reanalysis datasets,followed by fine-tuning it using in-situ analysis data to obtain the final prediction model.By utilizing the historical 12-month SVFs as input,our model predicts the SVFs for the subsequent three months.We compare the performance of five models:Artificial Neural Networks(ANN),Long ShortTerm Memory(LSTM),Convolutional LSTM(ConvLSTM),ST-LSTM,and our proposed ST-LSTM-SA model in a test experiment spanning 2019 to 2022.Our results demonstrate that the ST-LSTM-SA model significantly improves the prediction accuracy and stability of sound velocity in both temporal and spatial dimensions.The ST-LSTM-SA model not only accurately predicts the ocean sound velocity field(SVF),but also provides valuable insights for spatiotemporal prediction of other oceanic environmental variables.
基金supported by the National Natural Science Foundation of China(Grant Nos.41976193 and 42176243).
文摘In recent years,deep learning methods have gradually been applied to prediction tasks related to Arctic sea ice concentration,but relatively little research has been conducted for larger spatial and temporal scales,mainly due to the limited time coverage of observations and reanalysis data.Meanwhile,deep learning predictions of sea ice thickness(SIT)have yet to receive ample attention.In this study,two data-driven deep learning(DL)models are built based on the ConvLSTM and fully convolutional U-net(FC-Unet)algorithms and trained using CMIP6 historical simulations for transfer learning and fine-tuned using reanalysis/observations.These models enable monthly predictions of Arctic SIT without considering the complex physical processes involved.Through comprehensive assessments of prediction skills by season and region,the results suggest that using a broader set of CMIP6 data for transfer learning,as well as incorporating multiple climate variables as predictors,contribute to better prediction results,although both DL models can effectively predict the spatiotemporal features of SIT anomalies.Regarding the predicted SIT anomalies of the FC-Unet model,the spatial correlations with reanalysis reach an average level of 89%over all months,while the temporal anomaly correlation coefficients are close to unity in most cases.The models also demonstrate robust performances in predicting SIT and SIE during extreme events.The effectiveness and reliability of the proposed deep transfer learning models in predicting Arctic SIT can facilitate more accurate pan-Arctic predictions,aiding climate change research and real-time business applications.
