Since the initiation of the subseasonal-to-seasonal prediction project by the World Meteorological Organization,the accuracy of model forecasts has improved notably.However,substantial discrepancies have been observed...Since the initiation of the subseasonal-to-seasonal prediction project by the World Meteorological Organization,the accuracy of model forecasts has improved notably.However,substantial discrepancies have been observed among forecast results produced by different ensemble members when applied to South China.To enhance the accuracy of sub-seasonal forecasts in this region,it is essential to develop new methods that can effectively leverage multiple predictive models.This study introduces a weighted ensemble forecasting method based on online learning to improve forecast accuracy.We utilized ensemble forecasts from three models:the Integrated Forecasting System model from the European Centre for Medium-Range Weather Forecasts,the Climate Forecast System Version 2 model from the National Centers for Environmental Prediction,and the Beijing Climate Center-Climate Prediction System version 3 model from the China Meteorological Administration.The ensemble weights are trained using an online learning approach.The results indicate that the forecasts obtained through online learning outperform those of the original dynamical models.Compared to the simple ensemble results of the three models,the weighted ensemble model showed a stronger capability to capture temperature and precipitation patterns in South China.Therefore,this method has the potential to improve the accuracy of sub-seasonal forecasts in this region.展开更多
Wind speed is a crucial parameter affecting wind energy utilization.However,its volatility leads to time-varying power output.Herein,a novel Seq2Seq model integrating deep learning,data denoising,and a shape-aware los...Wind speed is a crucial parameter affecting wind energy utilization.However,its volatility leads to time-varying power output.Herein,a novel Seq2Seq model integrating deep learning,data denoising,and a shape-aware loss function is proposed for accurate multistep wind speed forecasting.In this model,the wind speed data is first denoised using the maximal overlap discrete wavelet transform.Next,an encoder-decoder network based on a temporal convolutional network,bidirectional gated recurrent unit,and multihead self-attention is employed for forecasting.Additionally,to enhance the ability of the model to identify temporal dynamics,a shape-aware loss function,ITILDE-Q,is employed in the model.To verify the effectiveness of the proposed model,a comparative experiment and an ablation experiment were conducted using three datasets of measured wind speeds.Three error metrics and a similarity metric were adopted for comprehensive evaluation.The experimental results showed that the proposed model consistently outperforms benchmark models in all tested forecasting scenarios,with particularly pronounced differences in performance over longer forecast horizons.Furthermore,the synergistic interaction of the three key components contributes to the extraordinary performance of the proposed model.展开更多
The solar cycle(SC),a phenomenon caused by the quasi-periodic regular activities in the Sun,occurs approximately every 11 years.Intense solar activity can disrupt the Earth’s ionosphere,affecting communication and na...The solar cycle(SC),a phenomenon caused by the quasi-periodic regular activities in the Sun,occurs approximately every 11 years.Intense solar activity can disrupt the Earth’s ionosphere,affecting communication and navigation systems.Consequently,accurately predicting the intensity of the SC holds great significance,but predicting the SC involves a long-term time series,and many existing time series forecasting methods have fallen short in terms of accuracy and efficiency.The Time-series Dense Encoder model is a deep learning solution tailored for long time series prediction.Based on a multi-layer perceptron structure,it outperforms the best previously existing models in accuracy,while being efficiently trainable on general datasets.We propose a method based on this model for SC forecasting.Using a trained model,we predict the test set from SC 19 to SC 25 with an average mean absolute percentage error of 32.02,root mean square error of 30.3,mean absolute error of 23.32,and R^(2)(coefficient of determination)of 0.76,outperforming other deep learning models in terms of accuracy and training efficiency on sunspot number datasets.Subsequently,we use it to predict the peaks of SC 25 and SC 26.For SC 25,the peak time has ended,but a stronger peak is predicted for SC 26,of 199.3,within a range of 170.8-221.9,projected to occur during April 2034.展开更多
Accurate short-term electricity price forecasts are essential for market participants to optimize bidding strategies,hedge risk and plan generation schedules.By leveraging advanced data analytics and machine learning ...Accurate short-term electricity price forecasts are essential for market participants to optimize bidding strategies,hedge risk and plan generation schedules.By leveraging advanced data analytics and machine learning methods,accurate and reliable price forecasts can be achieved.This study forecasts day-ahead prices in Türkiye’s electricity market using eXtreme Gradient Boosting(XGBoost).We benchmark XGBoost against four alternatives—Support Vector Machines(SVM),Long Short-Term Memory(LSTM),Random Forest(RF),and Gradient Boosting(GBM)—using 8760 hourly observations from 2023 provided by Energy Exchange Istanbul(EXIST).All models were trained on an identical chronological 80/20 train–test split,with hyperparameters tuned via 5-fold cross-validation on the training set.XGBoost achieved the best performance(Mean Absolute Error(MAE)=144.8 TRY/MWh,Root Mean Square Error(RMSE)=201.8 TRY/MWh,coefficient of determination(R^(2))=0.923)while training in 94 s.To enhance interpretability and identify key drivers,we employed Shapley Additive Explanations(SHAP),which highlighted a strong association between higher prices and increased natural-gas-based generation.The results provide a clear performance benchmark and practical guidance for selecting forecasting approaches in day-ahead electricity markets.展开更多
Underwater gas-liquid two-phase propulsion technology is an emerging propulsion method that offers high efficiency and unrestricted navigation speed.The integration of this technology into water ramjet engines can sig...Underwater gas-liquid two-phase propulsion technology is an emerging propulsion method that offers high efficiency and unrestricted navigation speed.The integration of this technology into water ramjet engines can significantly enhance propulsion efficiency and holds substantial potential for broad applications.However,forming a gas-liquid two-phase flow within the nozzle requires introducing a large amount of rammed seawater.At this time,there is a complex phase transition problem of combustion products in the combustion chamber,which makes the thermodynamic calculation for gas-liquid two-phase water ramjet engines particularly challenging.This paper proposes a thermodynamic calculation method for gas-liquid two-phase water ramjet engines,based on the energy equation for gas-liquid two-phase flow and traditional thermodynamic principles,enabling thermodynamic calculations under conditions of ultra-high water-fuel ratios.Additionally,ground ignition tests of the gas-liquid two-phase engine were conducted,yielding critical engine test parameters.The results demonstrate that the gas-liquid two-phase water ramjet engine achieves a high specific impulse,with a theoretical maximum specific impulse of up to 7000(N s)/kg.The multiphase flow effects significantly impact engine performance,with specific impulse losses reaching up to 25.86%.The error between the thrust and specific impulse in the ground test and the theoretical values is within 10%,validating the proposed thermodynamic calculation method as a reliable reference for further research on gas-liquid two-phase water ramjet engines.展开更多
With the rapid proliferation of electric vehicles,their charging loads pose new challenges to power grid stability and operational efficiency.To address this,this study employs a Monte Carlo simulation model to analyz...With the rapid proliferation of electric vehicles,their charging loads pose new challenges to power grid stability and operational efficiency.To address this,this study employs a Monte Carlo simulation model to analyze the charging load characteristics of six battery electric vehicle categories in Hebei Province,leveraging multi-source probabilistic distribution data under typical operational scenarios.The findings reveal that electric vehicle charging loads are primarily concentrated during midday and nighttime periods,with significant load fluctuations exerting substantial pressure on the grid.In response,this paper proposes strategic interventions including optimized charging infrastructure planning,time-of-use electricity pricing mechanisms,and smart charging technologies to balance grid loads.The results provide a theoretical foundation for electric vehicle load forecasting,smart grid dispatching,and vehicle-grid integration,thereby enhancing grid operational efficiency and sustainability.展开更多
In permafrost regions of the QinghaiXizang Plateau,embankments of the Qinghai-Xizang Highway and Qinghai-Xizang Railway experiencing roadside water accumulation exhibit more pronounced engineering deteriorations.A wid...In permafrost regions of the QinghaiXizang Plateau,embankments of the Qinghai-Xizang Highway and Qinghai-Xizang Railway experiencing roadside water accumulation exhibit more pronounced engineering deteriorations.A widely accepted view is that the accumulated water adjacent to the embankment possesses substantial thermal energy,which accelerates the degradation-even disappearance-of the underlying permafrost.Moreover,the presence of roadside water keeps the embankment soil in a persistently high-moisture state,thereby making the frozen-soil embankment more susceptible to deformation under traffic loading.However,in the permafrost regions of the QinghaiXizang Plateau,deteriorations of embankments affected by roadside water are more commonly manifested as undulating pavement surfaces,and extensive crack networks appear on the embankment crest even where thermosyphons are installed.These manifestations are not fully consistent with the deterioration mechanisms proposed by existing viewpoints.We propose the hypothesis that temperature gradients,formed due to the freezing and thawing processes between the roadside wateraffected soil and the roadbed soil,lead to moisture migration under the influence of temperature gradients,resulting in frost heave and thaw settlement in the roadbed soil.To validate this hypothesis,we conducted the following investigations sequentially.Initially,we selected a roadbed with a thermosyphon(TPCT)system,which has a significant cooling effect,as the study object.By analyzing the temperature monitoring data of the roadbed section,the temperature variance was calculated to identify the time nodes where the temperature gradient of the roadbed soil was maximum and minimum.Subsequently,corresponding roadbed temperature distribution maps were drawn,illustrating the changes in the temperature and position of the lowtemperature core near the TPCT over time.Furthermore,using small-scale indoor model experiments,we qualitatively concluded that moisture in the soil migrates toward the TPCT due to the temperature gradient.Thereafter,combining borehole water content data and precipitation data from the sloped terrain construction site,the formation mechanisms and timing characteristics of roadside water accumulation were analyzed.Ultimately,by integrating the ground temperature data,air temperature data,roadside water formation mechanisms,and the operating characteristics of the TPCT,it was concluded that roadside water,while in a thawed state during TPCT operation,acts as a supplementary source for moisture migration in the roadbed soil.This migration leads to cracking in the TPCT roadbed.Therefore,this study reveals a novel damage mechanism:asynchronous freeze-thaw processes induce temperature gradients,which drive the migration of roadside water into the roadbed and are responsible for the cracking damage.展开更多
This study investigates the droplet formation for the liquid–liquid two-phase flow within a square T-junction microchannel through numerical simulation using volume of fluid method and experimental visualization usin...This study investigates the droplet formation for the liquid–liquid two-phase flow within a square T-junction microchannel through numerical simulation using volume of fluid method and experimental visualization using high-speed camera imaging.The T-junction microchannel has a cross-sectional width of 0.6 mm and a total length of 27.3 mm.The solution of cyclohexane with 2%and 3%mass concentrations of sorbitan trioleate surfactant were used as the continuous phase,and water was used as the dispersed phase.Slug flow,characteristic of squeezing regime,were predominantly observed.The effects of liquid–liquid two-phase flow rate ratio,and dimensionless number on droplet size,and pressure drop were investigated.The squeezing regime was mapped for 0.0005≤Ca_(c)≤0.0052(capillary number)and 0.1≤q≤10(flow rate ratio).The pressure drops of slugs were in the range from 40 Pa to 200 Pa.The slug lengths were measured between 1 mm and 9 mm.A universal flow map dependent on Ca_(c)Re_(d)^(0.5) are projected to investigate the droplet formation behavior in T-junction microchannel.Correlation expressions are proposed to predict pressure drops and the slug lengths for liquid–liquid two-phase flow in a square T-junction microchannel,using dimensionless numbers such as flow rate ratio and capillary number.The result shows that large continuous phase flow rates facilitate smaller slugs,whereas higher dispersed phase flow rates result in longer shorts.展开更多
Deep learning-based methods have become alternatives to traditional numerical weather prediction systems,offering faster computation and the ability to utilize large historical datasets.However,the application of deep...Deep learning-based methods have become alternatives to traditional numerical weather prediction systems,offering faster computation and the ability to utilize large historical datasets.However,the application of deep learning to medium-range regional weather forecasting with limited data remains a significant challenge.In this work,three key solutions are proposed:(1)motivated by the need to improve model performance in data-scarce regional forecasting scenarios,the authors innovatively apply semantic segmentation models,to better capture spatiotemporal features and improve prediction accuracy;(2)recognizing the challenge of overfitting and the inability of traditional noise-based data augmentation methods to effectively enhance model robustness,a novel learnable Gaussian noise mechanism is introduced that allows the model to adaptively optimize perturbations for different locations,ensuring more effective learning;and(3)to address the issue of error accumulation in autoregressive prediction,as well as the challenge of learning difficulty and the lack of intermediate data utilization in one-shot prediction,the authors propose a cascade prediction approach that effectively resolves these problems while significantly improving model forecasting performance.The method achieves a competitive result in The East China Regional AI Medium Range Weather Forecasting Competition.Ablation experiments further validate the effectiveness of each component,highlighting their contributions to enhancing prediction performance.展开更多
Sustainable energy systems will entail a change in the carbon intensity projections,which should be carried out in a proper manner to facilitate the smooth running of the grid and reduce greenhouse emissions.The prese...Sustainable energy systems will entail a change in the carbon intensity projections,which should be carried out in a proper manner to facilitate the smooth running of the grid and reduce greenhouse emissions.The present article outlines the TransCarbonNet,a novel hybrid deep learning framework with self-attention characteristics added to the bidirectional Long Short-Term Memory(Bi-LSTM)network to forecast the carbon intensity of the grid several days.The proposed temporal fusion model not only learns the local temporal interactions but also the long-term patterns of the carbon emission data;hence,it is able to give suitable forecasts over a period of seven days.TransCarbonNet takes advantage of a multi-head self-attention element to identify significant temporal connections,which means the Bi-LSTM element calculates sequential dependencies in both directions.Massive tests on two actual data sets indicate much improved results in comparison with the existing results,with mean relative errors of 15.3 percent and 12.7 percent,respectively.The framework has given explicable weights of attention that reveal critical periods that influence carbon intensity alterations,and informed decisions on the management of carbon sustainability.The effectiveness of the proposed solution has been validated in numerous cases of operations,and TransCarbonNet is established to be an effective tool when it comes to carbon-friendly optimization of the grid.展开更多
Predicting the behavior of renewable energy systems requires models capable of generating accurate forecasts from limited historical data,a challenge that becomes especially pronounced when commissioning new facil-iti...Predicting the behavior of renewable energy systems requires models capable of generating accurate forecasts from limited historical data,a challenge that becomes especially pronounced when commissioning new facil-ities where operational records are scarce.This review aims to synthesize recent progress in data-efficient deep learning approaches for addressing such“cold-start”forecasting problems.It primarily covers three interrelated domains—solar photovoltaic(PV),wind power,and electrical load forecasting—where data scarcity and operational variability are most critical,while also including representative studies on hydropower and carbon emission prediction to provide a broader systems perspective.To this end,we examined trends from over 150 predominantly peer-reviewed studies published between 2019 and mid-2025,highlighting advances in zero-shot and few-shot meta-learning frameworks that enable rapid model adaptation with minimal labeled data.Moreover,transfer learning approaches combined with spatiotemporal graph neural networks have been employed to transfer knowledge from existing energy assets to new,data-sparse environments,effectively capturing hidden dependencies among geographic features,meteorological dynamics,and grid structures.Synthetic data generation has further proven valuable for expanding training samples and mitigating overfitting in cold-start scenarios.In addition,large language models and explainable artificial intelligence(XAI)—notably conversational XAI systems—have been used to interpret and communicate complex model behaviors in accessible terms,fostering operator trust from the earliest deployment stages.By consolidating methodological advances,unresolved challenges,and open-source resources,this review provides a coherent overview of deep learning strategies that can shorten the data-sparse ramp-up period of new energy infrastructures and accelerate the transition toward resilient,low-carbon electricity grids.展开更多
Deep-sea mineral resource transportation predominantly utilizes hydraulic pipeline methodology.Environmental factors induce vibrations in flexible pipelines,thereby affecting the internal flow characteristics.Therefor...Deep-sea mineral resource transportation predominantly utilizes hydraulic pipeline methodology.Environmental factors induce vibrations in flexible pipelines,thereby affecting the internal flow characteristics.Therefore,real-time monitoring of solid–liquid two-phase flow in pipelines is crucial for system maintenance.This study develops an autoencoder-based deep learning framework to reconstruct three-dimensional solid–liquid two-phase flow within flexible vibrating pipelines utilizing sparse wall information from sensors.Within this framework,separate X-model and F-model with distinct hidden-layer structures are established to reconstruct the coordinates and flow field information on the computational domain grid of the pipeline under traveling wave vibration.Following hyperparameter optimization,the models achieved high reconstruction accuracy,demonstrating R^(2)values of 0.990 and 0.945,respectively.The models’robustness is evaluated across three aspects:vibration parameters,physical fields,and vibration modes,demonstrating good reconstruction performance.Results concerning sensors show that 20 sensors(0.06%of total grids)achieve a balance between accuracy and cost,with superior accuracy obtained when arranged along the full length of the pipe compared to a dense arrangement at the front end.The models exhibited a signal-to-noise ratio tolerance of approximately 27 dB,with reconstruction accuracy being more affected by sensor failures at both ends of the pipeline.展开更多
The influence of the squeeze film between the tube and the support structure on flow-induced vibrations is a critical factor in tube bundles subjected to two-phase cross-flow.This aspect can significantly alter the th...The influence of the squeeze film between the tube and the support structure on flow-induced vibrations is a critical factor in tube bundles subjected to two-phase cross-flow.This aspect can significantly alter the threshold for fluidelastic instability and affect heat transfer efficiency.This paper presents a mathematical model incorporating the squeeze film force between the tube and the support structure.We aim to clarify the mechanisms underlying fluidelastic instability in tube bundle systems exposed to two-phase flow.Using a self-developed computer program,we performed numerical calculations to examine the influence of the squeeze film on the threshold of fluidelastic instability in the tube bundle system.Furthermore,we analyzed how the thickness and length of the squeeze film affect both the underlying mechanisms and the critical velocity of fluidelastic instability.展开更多
Deep learning(DL)has revolutionized time series forecasting(TSF),surpassing traditional statistical methods(e.g.,ARIMA)and machine learning techniques in modeling complex nonlinear dynamics and long-term dependencies ...Deep learning(DL)has revolutionized time series forecasting(TSF),surpassing traditional statistical methods(e.g.,ARIMA)and machine learning techniques in modeling complex nonlinear dynamics and long-term dependencies prevalent in real-world temporal data.This comprehensive survey reviews state-of-the-art DL architectures forTSF,focusing on four core paradigms:(1)ConvolutionalNeuralNetworks(CNNs),adept at extracting localized temporal features;(2)Recurrent Neural Networks(RNNs)and their advanced variants(LSTM,GRU),designed for sequential dependency modeling;(3)Graph Neural Networks(GNNs),specialized for forecasting structured relational data with spatial-temporal dependencies;and(4)Transformer-based models,leveraging self-attention mechanisms to capture global temporal patterns efficiently.We provide a rigorous analysis of the theoretical underpinnings,recent algorithmic advancements(e.g.,TCNs,attention mechanisms,hybrid architectures),and practical applications of each framework,supported by extensive benchmark datasets(e.g.,ETT,traffic flow,financial indicators)and standardized evaluation metrics(MAE,MSE,RMSE).Critical challenges,including handling irregular sampling intervals,integrating domain knowledge for robustness,and managing computational complexity,are thoroughly discussed.Emerging research directions highlighted include diffusion models for uncertainty quantification,hybrid pipelines combining classical statistical and DL techniques for enhanced interpretability,quantile regression with Transformers for riskaware forecasting,and optimizations for real-time deployment.This work serves as an essential reference,consolidating methodological innovations,empirical resources,and future trends to bridge the gap between theoretical research and practical implementation needs for researchers and practitioners in the field.展开更多
Clayey-silt natural gas hydrate reservoirs in the South China Sea exhibit loose and unconsolidated structures, heterogeneous pore structures, high clay mineral contents, and strong hydrophilicity. These characteristic...Clayey-silt natural gas hydrate reservoirs in the South China Sea exhibit loose and unconsolidated structures, heterogeneous pore structures, high clay mineral contents, and strong hydrophilicity. These characteristics complicate the gas-water two-phase flow process in porous media following hydrate decomposition, posing challenges for efficient development. This study examines the transport response of clayey-silt reservoir samples from the Shenhu area using gas-water two-phase flow experiments and CT scanning to explore changes in pore structure, gas-water distribution, and relative permeability under varying flow conditions. The results indicate that pore heterogeneity significantly influences flow characteristics. Gas preferentially displaces water in larger pores, forming fracture-like pores, which serve as preferential flow channels for gas migration. The preferential flow channels enhance gas-phase permeability up to 19 times that of the water phase when fluid pressures exceed total stresses. However,small pores retain liquid, leading to a high residual water saturation of 0.561. CT imaging reveals that these hydro-fractures improve gas permeability but also confine gas flow to specific channels. Pore network analysis shows that gas injection expands the pore-throat network, enhancing connectivity and forming fracture-like pores. Residual water remains trapped in smaller pores and throats, while structural changes, including new fractures, improve gas flow pathways and overall connectivity. Relative permeability curves demonstrate a narrow gas-water cocurrent-flow zone, a right-shifted iso-permeability point and high reservoir capillary pressure, indicating a strong "water-blocking" effect. The findings suggest that optimizing reservoir stimulation techniques to enhance fracture formation, reduce residual water saturation, and improve gas flow capacity is critical for efficient hydrate reservoir development.展开更多
This work investigated the dynamic behavior of vertical pipes conveying gas-liquid two-phase flow when subjected to external excitations at both ends.Even with minimal excitation amplitude,resonance can occur when the...This work investigated the dynamic behavior of vertical pipes conveying gas-liquid two-phase flow when subjected to external excitations at both ends.Even with minimal excitation amplitude,resonance can occur when the excitation frequency aligns with the natural frequency of the pipe,significantly increasing the degree of operational risk.The governing equation of motion based on the Euler-Bernoulli beam is derived for the relative deflection with stationary simply supported ends,with the effects of the external excitations represented by source terms distributed along the pipe length.The fourth-order partial differential equation is solved via the generalized integral transform technique(GITT),with the solution successfully verified via comparison with results in the literature.A comprehensive analysis of the vibration phenomena and changes in the motion state of the pipe is conducted for three classes of external excitation conditions:same frequency and amplitude(SFSA),same frequency but different amplitudes(SFDA),and different frequencies and amplitudes(DFDA).The numerical results show that with increasing gas volume fraction,the position corresponding to the maximum vibration displacement shifts upward.Compared with conditions without external excitation,the vibration displacement of the pipe conveying two-phase flow under external excitation increases significantly.The frequency of external excitation has a significant effect on the dynamic behavior of a pipe conveying two-phase flow.展开更多
Forecasting landslide deformation is challenging due to influence of various internal and external factors on the occurrence of systemic and localized heterogeneities.Despite the potential to improve landslide predict...Forecasting landslide deformation is challenging due to influence of various internal and external factors on the occurrence of systemic and localized heterogeneities.Despite the potential to improve landslide predictability,deep learning has yet to be sufficiently explored for complex deformation patterns associated with landslides and is inherently opaque.Herein,we developed a holistic landslide deformation forecasting method that considers spatiotemporal correlations of landslide deformation by integrating domain knowledge into interpretable deep learning.By spatially capturing the interconnections between multiple deformations from different observation points,our method contributes to the understanding and forecasting of landslide systematic behavior.By integrating specific domain knowledge relevant to each observation point and merging internal properties with external variables,the local heterogeneity is considered in our method,identifying deformation temporal patterns in different landslide zones.Case studies involving reservoir-induced landslides and creeping landslides demonstrated that our approach(1)enhances the accuracy of landslide deformation forecasting,(2)identifies significant contributing factors and their influence on spatiotemporal deformation characteristics,and(3)demonstrates how identifying these factors and patterns facilitates landslide forecasting.Our research offers a promising and pragmatic pathway toward a deeper understanding and forecasting of complex landslide behaviors.展开更多
Polymer flooding is an important means of improving oil recovery and is widely used in Daqing,Xinjiang,and Shengli oilfields,China.Different from conventional injection media such as water and gas,viscoelastic polymer...Polymer flooding is an important means of improving oil recovery and is widely used in Daqing,Xinjiang,and Shengli oilfields,China.Different from conventional injection media such as water and gas,viscoelastic polymer solutions exhibit non-Newtonian and nonlinear flow behavior including shear thinning and shear thickening,polymer convection,diffusion,adsorption,retention,inaccessible pore volume,and reduced effective permeability.However,available well test model of polymer flooding wells generally simplifies these characteristics on pressure transient response,which may lead to inaccurate results.This work proposes a novel two-phase numerical well test model to better describe the polymer viscoelasticity and nonlinear flow behavior.Different influence factors that related to near-well blockage during polymer flooding process,including the degree of blockage(inner zone permeability),the extent of blockage(composite radius),and polymer flooding front radius are explored to investigate these impacts on bottom hole pressure responses.Results show that polymer viscoelasticity has a significant impact on the transitional flow segment of type curves,and the effects of near-well formation blockage and polymer concentration distribution on well test curves are very similar.Thus,to accurately interpret the degree of near-well blockage in injection wells,it is essential to first eliminate the influence of polymer viscoelasticity.Finally,a field case is comprehensively analyzed and discussed to illustrate the applicability of the proposed model.展开更多
Photovoltaic(PV)power forecasting is essential for balancing energy supply and demand in renewable energy systems.However,the performance of PV panels varies across different technologies due to differences in efficie...Photovoltaic(PV)power forecasting is essential for balancing energy supply and demand in renewable energy systems.However,the performance of PV panels varies across different technologies due to differences in efficiency and how they process solar radiation.This study evaluates the effectiveness of deep learning models in predicting PV power generation for three panel technologies:Hybrid-Si,Mono-Si,and Poly-Si,across three forecasting horizons:1-step,12-step,and 24-step.Among the tested models,the Convolutional Neural Network—Long Short-Term Memory(CNN-LSTM)architecture exhibited superior performance,particularly for the 24-step horizon,achieving R^(2)=0.9793 and MAE 0.0162 for the Poly-Si array,followed by Mono-Si(R^(2)=0.9768)and Hybrid-Si arrays(R^(2)=0.9769).These findings demonstrate that the CNN-LSTM model can provide accurate and reliable PV power predictions for all studied technologies.By identifying the most suitable predictive model for each panel technology,this study contributes to optimizing PV power forecasting and improving energy management strategies.展开更多
It is fundamental and useful to investigate how deep learning forecasting models(DLMs)perform compared to operational oceanography forecast systems(OFSs).However,few studies have intercompared their performances using...It is fundamental and useful to investigate how deep learning forecasting models(DLMs)perform compared to operational oceanography forecast systems(OFSs).However,few studies have intercompared their performances using an identical reference.In this study,three physically reasonable DLMs are implemented for the forecasting of the sea surface temperature(SST),sea level anomaly(SLA),and sea surface velocity in the South China Sea.The DLMs are validated against both the testing dataset and the“OceanPredict”Class 4 dataset.Results show that the DLMs'RMSEs against the latter increase by 44%,245%,302%,and 109%for SST,SLA,current speed,and direction,respectively,compared to those against the former.Therefore,different references have significant influences on the validation,and it is necessary to use an identical and independent reference to intercompare the DLMs and OFSs.Against the Class 4 dataset,the DLMs present significantly better performance for SLA than the OFSs,and slightly better performances for other variables.The error patterns of the DLMs and OFSs show a high degree of similarity,which is reasonable from the viewpoint of predictability,facilitating further applications of the DLMs.For extreme events,the DLMs and OFSs both present large but similar forecast errors for SLA and current speed,while the DLMs are likely to give larger errors for SST and current direction.This study provides an evaluation of the forecast skills of commonly used DLMs and provides an example to objectively intercompare different DLMs.展开更多
基金Science and Technology Development Program of the“Taihu Light”(K20231023)CMA Numerical Weather Prediction R&D Project(TCYF2024QH007)+1 种基金“Qing Lan”Project of Jiangsu Province for C.H.LUWuxi University Research Start-up Fund for Introduced Talents(2023r037)。
文摘Since the initiation of the subseasonal-to-seasonal prediction project by the World Meteorological Organization,the accuracy of model forecasts has improved notably.However,substantial discrepancies have been observed among forecast results produced by different ensemble members when applied to South China.To enhance the accuracy of sub-seasonal forecasts in this region,it is essential to develop new methods that can effectively leverage multiple predictive models.This study introduces a weighted ensemble forecasting method based on online learning to improve forecast accuracy.We utilized ensemble forecasts from three models:the Integrated Forecasting System model from the European Centre for Medium-Range Weather Forecasts,the Climate Forecast System Version 2 model from the National Centers for Environmental Prediction,and the Beijing Climate Center-Climate Prediction System version 3 model from the China Meteorological Administration.The ensemble weights are trained using an online learning approach.The results indicate that the forecasts obtained through online learning outperform those of the original dynamical models.Compared to the simple ensemble results of the three models,the weighted ensemble model showed a stronger capability to capture temperature and precipitation patterns in South China.Therefore,this method has the potential to improve the accuracy of sub-seasonal forecasts in this region.
基金supported by the National Natural Science Foundation of China(No.52171284)。
文摘Wind speed is a crucial parameter affecting wind energy utilization.However,its volatility leads to time-varying power output.Herein,a novel Seq2Seq model integrating deep learning,data denoising,and a shape-aware loss function is proposed for accurate multistep wind speed forecasting.In this model,the wind speed data is first denoised using the maximal overlap discrete wavelet transform.Next,an encoder-decoder network based on a temporal convolutional network,bidirectional gated recurrent unit,and multihead self-attention is employed for forecasting.Additionally,to enhance the ability of the model to identify temporal dynamics,a shape-aware loss function,ITILDE-Q,is employed in the model.To verify the effectiveness of the proposed model,a comparative experiment and an ablation experiment were conducted using three datasets of measured wind speeds.Three error metrics and a similarity metric were adopted for comprehensive evaluation.The experimental results showed that the proposed model consistently outperforms benchmark models in all tested forecasting scenarios,with particularly pronounced differences in performance over longer forecast horizons.Furthermore,the synergistic interaction of the three key components contributes to the extraordinary performance of the proposed model.
基金supported by the Academic Research Projects of Beijing Union University(ZK20202204)the National Natural Science Foundation of China(12250005,12073040,12273059,11973056,12003051,11573037,12073041,11427901,11572005,11611530679 and 12473052)+1 种基金the Strategic Priority Research Program of the China Academy of Sciences(XDB0560000,XDA15052200,XDB09040200,XDA15010700,XDB0560301,and XDA15320102)the Chinese Meridian Project(CMP).
文摘The solar cycle(SC),a phenomenon caused by the quasi-periodic regular activities in the Sun,occurs approximately every 11 years.Intense solar activity can disrupt the Earth’s ionosphere,affecting communication and navigation systems.Consequently,accurately predicting the intensity of the SC holds great significance,but predicting the SC involves a long-term time series,and many existing time series forecasting methods have fallen short in terms of accuracy and efficiency.The Time-series Dense Encoder model is a deep learning solution tailored for long time series prediction.Based on a multi-layer perceptron structure,it outperforms the best previously existing models in accuracy,while being efficiently trainable on general datasets.We propose a method based on this model for SC forecasting.Using a trained model,we predict the test set from SC 19 to SC 25 with an average mean absolute percentage error of 32.02,root mean square error of 30.3,mean absolute error of 23.32,and R^(2)(coefficient of determination)of 0.76,outperforming other deep learning models in terms of accuracy and training efficiency on sunspot number datasets.Subsequently,we use it to predict the peaks of SC 25 and SC 26.For SC 25,the peak time has ended,but a stronger peak is predicted for SC 26,of 199.3,within a range of 170.8-221.9,projected to occur during April 2034.
文摘Accurate short-term electricity price forecasts are essential for market participants to optimize bidding strategies,hedge risk and plan generation schedules.By leveraging advanced data analytics and machine learning methods,accurate and reliable price forecasts can be achieved.This study forecasts day-ahead prices in Türkiye’s electricity market using eXtreme Gradient Boosting(XGBoost).We benchmark XGBoost against four alternatives—Support Vector Machines(SVM),Long Short-Term Memory(LSTM),Random Forest(RF),and Gradient Boosting(GBM)—using 8760 hourly observations from 2023 provided by Energy Exchange Istanbul(EXIST).All models were trained on an identical chronological 80/20 train–test split,with hyperparameters tuned via 5-fold cross-validation on the training set.XGBoost achieved the best performance(Mean Absolute Error(MAE)=144.8 TRY/MWh,Root Mean Square Error(RMSE)=201.8 TRY/MWh,coefficient of determination(R^(2))=0.923)while training in 94 s.To enhance interpretability and identify key drivers,we employed Shapley Additive Explanations(SHAP),which highlighted a strong association between higher prices and increased natural-gas-based generation.The results provide a clear performance benchmark and practical guidance for selecting forecasting approaches in day-ahead electricity markets.
基金supported by the Stable Support Fund forBasic Disciplines,China(No.3072024WD0201)。
文摘Underwater gas-liquid two-phase propulsion technology is an emerging propulsion method that offers high efficiency and unrestricted navigation speed.The integration of this technology into water ramjet engines can significantly enhance propulsion efficiency and holds substantial potential for broad applications.However,forming a gas-liquid two-phase flow within the nozzle requires introducing a large amount of rammed seawater.At this time,there is a complex phase transition problem of combustion products in the combustion chamber,which makes the thermodynamic calculation for gas-liquid two-phase water ramjet engines particularly challenging.This paper proposes a thermodynamic calculation method for gas-liquid two-phase water ramjet engines,based on the energy equation for gas-liquid two-phase flow and traditional thermodynamic principles,enabling thermodynamic calculations under conditions of ultra-high water-fuel ratios.Additionally,ground ignition tests of the gas-liquid two-phase engine were conducted,yielding critical engine test parameters.The results demonstrate that the gas-liquid two-phase water ramjet engine achieves a high specific impulse,with a theoretical maximum specific impulse of up to 7000(N s)/kg.The multiphase flow effects significantly impact engine performance,with specific impulse losses reaching up to 25.86%.The error between the thrust and specific impulse in the ground test and the theoretical values is within 10%,validating the proposed thermodynamic calculation method as a reliable reference for further research on gas-liquid two-phase water ramjet engines.
基金funded by Humanities and Social Sciences of Ministry of Education Planning Fund of China,grant number 21YJA790009National Natural Science Foundation of China,grant number 72140001.
文摘With the rapid proliferation of electric vehicles,their charging loads pose new challenges to power grid stability and operational efficiency.To address this,this study employs a Monte Carlo simulation model to analyze the charging load characteristics of six battery electric vehicle categories in Hebei Province,leveraging multi-source probabilistic distribution data under typical operational scenarios.The findings reveal that electric vehicle charging loads are primarily concentrated during midday and nighttime periods,with significant load fluctuations exerting substantial pressure on the grid.In response,this paper proposes strategic interventions including optimized charging infrastructure planning,time-of-use electricity pricing mechanisms,and smart charging technologies to balance grid loads.The results provide a theoretical foundation for electric vehicle load forecasting,smart grid dispatching,and vehicle-grid integration,thereby enhancing grid operational efficiency and sustainability.
基金supported by the Major Science and Technology Project of Gansu Province(Grant No.24ZD13FA003 and 23ZDWA005)National Natural Science Foundation of China(Grant No.42371140,42301163,41971087 and 42272332)the program of the State Key Laboratory of Cryospheric Science and Frozen Soil Engineering,CAS(No.CSFSEZZ-2411)。
文摘In permafrost regions of the QinghaiXizang Plateau,embankments of the Qinghai-Xizang Highway and Qinghai-Xizang Railway experiencing roadside water accumulation exhibit more pronounced engineering deteriorations.A widely accepted view is that the accumulated water adjacent to the embankment possesses substantial thermal energy,which accelerates the degradation-even disappearance-of the underlying permafrost.Moreover,the presence of roadside water keeps the embankment soil in a persistently high-moisture state,thereby making the frozen-soil embankment more susceptible to deformation under traffic loading.However,in the permafrost regions of the QinghaiXizang Plateau,deteriorations of embankments affected by roadside water are more commonly manifested as undulating pavement surfaces,and extensive crack networks appear on the embankment crest even where thermosyphons are installed.These manifestations are not fully consistent with the deterioration mechanisms proposed by existing viewpoints.We propose the hypothesis that temperature gradients,formed due to the freezing and thawing processes between the roadside wateraffected soil and the roadbed soil,lead to moisture migration under the influence of temperature gradients,resulting in frost heave and thaw settlement in the roadbed soil.To validate this hypothesis,we conducted the following investigations sequentially.Initially,we selected a roadbed with a thermosyphon(TPCT)system,which has a significant cooling effect,as the study object.By analyzing the temperature monitoring data of the roadbed section,the temperature variance was calculated to identify the time nodes where the temperature gradient of the roadbed soil was maximum and minimum.Subsequently,corresponding roadbed temperature distribution maps were drawn,illustrating the changes in the temperature and position of the lowtemperature core near the TPCT over time.Furthermore,using small-scale indoor model experiments,we qualitatively concluded that moisture in the soil migrates toward the TPCT due to the temperature gradient.Thereafter,combining borehole water content data and precipitation data from the sloped terrain construction site,the formation mechanisms and timing characteristics of roadside water accumulation were analyzed.Ultimately,by integrating the ground temperature data,air temperature data,roadside water formation mechanisms,and the operating characteristics of the TPCT,it was concluded that roadside water,while in a thawed state during TPCT operation,acts as a supplementary source for moisture migration in the roadbed soil.This migration leads to cracking in the TPCT roadbed.Therefore,this study reveals a novel damage mechanism:asynchronous freeze-thaw processes induce temperature gradients,which drive the migration of roadside water into the roadbed and are responsible for the cracking damage.
基金supports for this project from the National Natural Science Foundation of China(22378295).
文摘This study investigates the droplet formation for the liquid–liquid two-phase flow within a square T-junction microchannel through numerical simulation using volume of fluid method and experimental visualization using high-speed camera imaging.The T-junction microchannel has a cross-sectional width of 0.6 mm and a total length of 27.3 mm.The solution of cyclohexane with 2%and 3%mass concentrations of sorbitan trioleate surfactant were used as the continuous phase,and water was used as the dispersed phase.Slug flow,characteristic of squeezing regime,were predominantly observed.The effects of liquid–liquid two-phase flow rate ratio,and dimensionless number on droplet size,and pressure drop were investigated.The squeezing regime was mapped for 0.0005≤Ca_(c)≤0.0052(capillary number)and 0.1≤q≤10(flow rate ratio).The pressure drops of slugs were in the range from 40 Pa to 200 Pa.The slug lengths were measured between 1 mm and 9 mm.A universal flow map dependent on Ca_(c)Re_(d)^(0.5) are projected to investigate the droplet formation behavior in T-junction microchannel.Correlation expressions are proposed to predict pressure drops and the slug lengths for liquid–liquid two-phase flow in a square T-junction microchannel,using dimensionless numbers such as flow rate ratio and capillary number.The result shows that large continuous phase flow rates facilitate smaller slugs,whereas higher dispersed phase flow rates result in longer shorts.
基金supported by the National Natural Science Foundation of China[grant number 62376217]the Young Elite Scientists Sponsorship Program by CAST[grant number 2023QNRC001]the Joint Research Project for Meteorological Capacity Improvement[grant number 24NLTSZ003]。
文摘Deep learning-based methods have become alternatives to traditional numerical weather prediction systems,offering faster computation and the ability to utilize large historical datasets.However,the application of deep learning to medium-range regional weather forecasting with limited data remains a significant challenge.In this work,three key solutions are proposed:(1)motivated by the need to improve model performance in data-scarce regional forecasting scenarios,the authors innovatively apply semantic segmentation models,to better capture spatiotemporal features and improve prediction accuracy;(2)recognizing the challenge of overfitting and the inability of traditional noise-based data augmentation methods to effectively enhance model robustness,a novel learnable Gaussian noise mechanism is introduced that allows the model to adaptively optimize perturbations for different locations,ensuring more effective learning;and(3)to address the issue of error accumulation in autoregressive prediction,as well as the challenge of learning difficulty and the lack of intermediate data utilization in one-shot prediction,the authors propose a cascade prediction approach that effectively resolves these problems while significantly improving model forecasting performance.The method achieves a competitive result in The East China Regional AI Medium Range Weather Forecasting Competition.Ablation experiments further validate the effectiveness of each component,highlighting their contributions to enhancing prediction performance.
基金funded by the Deanship of Scientific Research and Libraries at Princess Nourah bint Abdulrahman University,through the“Nafea”Program,Grant No.(NP-45-082).
文摘Sustainable energy systems will entail a change in the carbon intensity projections,which should be carried out in a proper manner to facilitate the smooth running of the grid and reduce greenhouse emissions.The present article outlines the TransCarbonNet,a novel hybrid deep learning framework with self-attention characteristics added to the bidirectional Long Short-Term Memory(Bi-LSTM)network to forecast the carbon intensity of the grid several days.The proposed temporal fusion model not only learns the local temporal interactions but also the long-term patterns of the carbon emission data;hence,it is able to give suitable forecasts over a period of seven days.TransCarbonNet takes advantage of a multi-head self-attention element to identify significant temporal connections,which means the Bi-LSTM element calculates sequential dependencies in both directions.Massive tests on two actual data sets indicate much improved results in comparison with the existing results,with mean relative errors of 15.3 percent and 12.7 percent,respectively.The framework has given explicable weights of attention that reveal critical periods that influence carbon intensity alterations,and informed decisions on the management of carbon sustainability.The effectiveness of the proposed solution has been validated in numerous cases of operations,and TransCarbonNet is established to be an effective tool when it comes to carbon-friendly optimization of the grid.
文摘Predicting the behavior of renewable energy systems requires models capable of generating accurate forecasts from limited historical data,a challenge that becomes especially pronounced when commissioning new facil-ities where operational records are scarce.This review aims to synthesize recent progress in data-efficient deep learning approaches for addressing such“cold-start”forecasting problems.It primarily covers three interrelated domains—solar photovoltaic(PV),wind power,and electrical load forecasting—where data scarcity and operational variability are most critical,while also including representative studies on hydropower and carbon emission prediction to provide a broader systems perspective.To this end,we examined trends from over 150 predominantly peer-reviewed studies published between 2019 and mid-2025,highlighting advances in zero-shot and few-shot meta-learning frameworks that enable rapid model adaptation with minimal labeled data.Moreover,transfer learning approaches combined with spatiotemporal graph neural networks have been employed to transfer knowledge from existing energy assets to new,data-sparse environments,effectively capturing hidden dependencies among geographic features,meteorological dynamics,and grid structures.Synthetic data generation has further proven valuable for expanding training samples and mitigating overfitting in cold-start scenarios.In addition,large language models and explainable artificial intelligence(XAI)—notably conversational XAI systems—have been used to interpret and communicate complex model behaviors in accessible terms,fostering operator trust from the earliest deployment stages.By consolidating methodological advances,unresolved challenges,and open-source resources,this review provides a coherent overview of deep learning strategies that can shorten the data-sparse ramp-up period of new energy infrastructures and accelerate the transition toward resilient,low-carbon electricity grids.
基金financial support by the National Natural Science Foundation of China (Nos.52471293 and 12372270)the National Youth Science Foundation of China (Nos.52101322 and 52108375)+3 种基金the Program for Intergovernmental International S&T Cooperation Projects of Shanghai Municipality, China (Nos.24510711100 and 22160710200)The Oceanic Interdisciplinary Program of Shanghai Jiao Tong University (No.SL2022PT101)funded by the Open Fund of the State Key Laboratory of Coastal and Offshore Engineering of Dalian University of Technology (No.LP2415)National Key R&D Program of China (No.2023YFC2811600)
文摘Deep-sea mineral resource transportation predominantly utilizes hydraulic pipeline methodology.Environmental factors induce vibrations in flexible pipelines,thereby affecting the internal flow characteristics.Therefore,real-time monitoring of solid–liquid two-phase flow in pipelines is crucial for system maintenance.This study develops an autoencoder-based deep learning framework to reconstruct three-dimensional solid–liquid two-phase flow within flexible vibrating pipelines utilizing sparse wall information from sensors.Within this framework,separate X-model and F-model with distinct hidden-layer structures are established to reconstruct the coordinates and flow field information on the computational domain grid of the pipeline under traveling wave vibration.Following hyperparameter optimization,the models achieved high reconstruction accuracy,demonstrating R^(2)values of 0.990 and 0.945,respectively.The models’robustness is evaluated across three aspects:vibration parameters,physical fields,and vibration modes,demonstrating good reconstruction performance.Results concerning sensors show that 20 sensors(0.06%of total grids)achieve a balance between accuracy and cost,with superior accuracy obtained when arranged along the full length of the pipe compared to a dense arrangement at the front end.The models exhibited a signal-to-noise ratio tolerance of approximately 27 dB,with reconstruction accuracy being more affected by sensor failures at both ends of the pipeline.
基金financially supported by the National Natural Science Foundation of China(Grant No.12072336).
文摘The influence of the squeeze film between the tube and the support structure on flow-induced vibrations is a critical factor in tube bundles subjected to two-phase cross-flow.This aspect can significantly alter the threshold for fluidelastic instability and affect heat transfer efficiency.This paper presents a mathematical model incorporating the squeeze film force between the tube and the support structure.We aim to clarify the mechanisms underlying fluidelastic instability in tube bundle systems exposed to two-phase flow.Using a self-developed computer program,we performed numerical calculations to examine the influence of the squeeze film on the threshold of fluidelastic instability in the tube bundle system.Furthermore,we analyzed how the thickness and length of the squeeze film affect both the underlying mechanisms and the critical velocity of fluidelastic instability.
基金funded by Natural Science Foundation of Heilongjiang Province,grant number LH2023F020.
文摘Deep learning(DL)has revolutionized time series forecasting(TSF),surpassing traditional statistical methods(e.g.,ARIMA)and machine learning techniques in modeling complex nonlinear dynamics and long-term dependencies prevalent in real-world temporal data.This comprehensive survey reviews state-of-the-art DL architectures forTSF,focusing on four core paradigms:(1)ConvolutionalNeuralNetworks(CNNs),adept at extracting localized temporal features;(2)Recurrent Neural Networks(RNNs)and their advanced variants(LSTM,GRU),designed for sequential dependency modeling;(3)Graph Neural Networks(GNNs),specialized for forecasting structured relational data with spatial-temporal dependencies;and(4)Transformer-based models,leveraging self-attention mechanisms to capture global temporal patterns efficiently.We provide a rigorous analysis of the theoretical underpinnings,recent algorithmic advancements(e.g.,TCNs,attention mechanisms,hybrid architectures),and practical applications of each framework,supported by extensive benchmark datasets(e.g.,ETT,traffic flow,financial indicators)and standardized evaluation metrics(MAE,MSE,RMSE).Critical challenges,including handling irregular sampling intervals,integrating domain knowledge for robustness,and managing computational complexity,are thoroughly discussed.Emerging research directions highlighted include diffusion models for uncertainty quantification,hybrid pipelines combining classical statistical and DL techniques for enhanced interpretability,quantile regression with Transformers for riskaware forecasting,and optimizations for real-time deployment.This work serves as an essential reference,consolidating methodological innovations,empirical resources,and future trends to bridge the gap between theoretical research and practical implementation needs for researchers and practitioners in the field.
基金the National Natural Science Foundation of China (Nos. 42302143, 42172159)China Geological Survey Project (No. DD20211350)support from the G. Albert Shoemaker endowment
文摘Clayey-silt natural gas hydrate reservoirs in the South China Sea exhibit loose and unconsolidated structures, heterogeneous pore structures, high clay mineral contents, and strong hydrophilicity. These characteristics complicate the gas-water two-phase flow process in porous media following hydrate decomposition, posing challenges for efficient development. This study examines the transport response of clayey-silt reservoir samples from the Shenhu area using gas-water two-phase flow experiments and CT scanning to explore changes in pore structure, gas-water distribution, and relative permeability under varying flow conditions. The results indicate that pore heterogeneity significantly influences flow characteristics. Gas preferentially displaces water in larger pores, forming fracture-like pores, which serve as preferential flow channels for gas migration. The preferential flow channels enhance gas-phase permeability up to 19 times that of the water phase when fluid pressures exceed total stresses. However,small pores retain liquid, leading to a high residual water saturation of 0.561. CT imaging reveals that these hydro-fractures improve gas permeability but also confine gas flow to specific channels. Pore network analysis shows that gas injection expands the pore-throat network, enhancing connectivity and forming fracture-like pores. Residual water remains trapped in smaller pores and throats, while structural changes, including new fractures, improve gas flow pathways and overall connectivity. Relative permeability curves demonstrate a narrow gas-water cocurrent-flow zone, a right-shifted iso-permeability point and high reservoir capillary pressure, indicating a strong "water-blocking" effect. The findings suggest that optimizing reservoir stimulation techniques to enhance fracture formation, reduce residual water saturation, and improve gas flow capacity is critical for efficient hydrate reservoir development.
基金financially supported by the Key Research and Development Program of Shandong Province(Grant Nos.2022CXGC020405,2023CXGC010415 and 2025TSGCCZZB0238)the National Natural Science Foundation of China(Grant No.52171288)the financial support from CNPq,FAPERJ,ANP,Embrapii,and China National Petroleum Corporation(CNPC).
文摘This work investigated the dynamic behavior of vertical pipes conveying gas-liquid two-phase flow when subjected to external excitations at both ends.Even with minimal excitation amplitude,resonance can occur when the excitation frequency aligns with the natural frequency of the pipe,significantly increasing the degree of operational risk.The governing equation of motion based on the Euler-Bernoulli beam is derived for the relative deflection with stationary simply supported ends,with the effects of the external excitations represented by source terms distributed along the pipe length.The fourth-order partial differential equation is solved via the generalized integral transform technique(GITT),with the solution successfully verified via comparison with results in the literature.A comprehensive analysis of the vibration phenomena and changes in the motion state of the pipe is conducted for three classes of external excitation conditions:same frequency and amplitude(SFSA),same frequency but different amplitudes(SFDA),and different frequencies and amplitudes(DFDA).The numerical results show that with increasing gas volume fraction,the position corresponding to the maximum vibration displacement shifts upward.Compared with conditions without external excitation,the vibration displacement of the pipe conveying two-phase flow under external excitation increases significantly.The frequency of external excitation has a significant effect on the dynamic behavior of a pipe conveying two-phase flow.
基金supported by the Postdoctoral Fellowship Program of CPSF(Grant No.GZB20230685)the National Science Foundation of China(Grant No.42277161).
文摘Forecasting landslide deformation is challenging due to influence of various internal and external factors on the occurrence of systemic and localized heterogeneities.Despite the potential to improve landslide predictability,deep learning has yet to be sufficiently explored for complex deformation patterns associated with landslides and is inherently opaque.Herein,we developed a holistic landslide deformation forecasting method that considers spatiotemporal correlations of landslide deformation by integrating domain knowledge into interpretable deep learning.By spatially capturing the interconnections between multiple deformations from different observation points,our method contributes to the understanding and forecasting of landslide systematic behavior.By integrating specific domain knowledge relevant to each observation point and merging internal properties with external variables,the local heterogeneity is considered in our method,identifying deformation temporal patterns in different landslide zones.Case studies involving reservoir-induced landslides and creeping landslides demonstrated that our approach(1)enhances the accuracy of landslide deformation forecasting,(2)identifies significant contributing factors and their influence on spatiotemporal deformation characteristics,and(3)demonstrates how identifying these factors and patterns facilitates landslide forecasting.Our research offers a promising and pragmatic pathway toward a deeper understanding and forecasting of complex landslide behaviors.
基金supported by the National Natural Science Foundation of China(52104049)the Young Elite Scientist Sponsorship Program by Beijing Association for Science and Technology(BYESS2023262)。
文摘Polymer flooding is an important means of improving oil recovery and is widely used in Daqing,Xinjiang,and Shengli oilfields,China.Different from conventional injection media such as water and gas,viscoelastic polymer solutions exhibit non-Newtonian and nonlinear flow behavior including shear thinning and shear thickening,polymer convection,diffusion,adsorption,retention,inaccessible pore volume,and reduced effective permeability.However,available well test model of polymer flooding wells generally simplifies these characteristics on pressure transient response,which may lead to inaccurate results.This work proposes a novel two-phase numerical well test model to better describe the polymer viscoelasticity and nonlinear flow behavior.Different influence factors that related to near-well blockage during polymer flooding process,including the degree of blockage(inner zone permeability),the extent of blockage(composite radius),and polymer flooding front radius are explored to investigate these impacts on bottom hole pressure responses.Results show that polymer viscoelasticity has a significant impact on the transitional flow segment of type curves,and the effects of near-well formation blockage and polymer concentration distribution on well test curves are very similar.Thus,to accurately interpret the degree of near-well blockage in injection wells,it is essential to first eliminate the influence of polymer viscoelasticity.Finally,a field case is comprehensively analyzed and discussed to illustrate the applicability of the proposed model.
文摘Photovoltaic(PV)power forecasting is essential for balancing energy supply and demand in renewable energy systems.However,the performance of PV panels varies across different technologies due to differences in efficiency and how they process solar radiation.This study evaluates the effectiveness of deep learning models in predicting PV power generation for three panel technologies:Hybrid-Si,Mono-Si,and Poly-Si,across three forecasting horizons:1-step,12-step,and 24-step.Among the tested models,the Convolutional Neural Network—Long Short-Term Memory(CNN-LSTM)architecture exhibited superior performance,particularly for the 24-step horizon,achieving R^(2)=0.9793 and MAE 0.0162 for the Poly-Si array,followed by Mono-Si(R^(2)=0.9768)and Hybrid-Si arrays(R^(2)=0.9769).These findings demonstrate that the CNN-LSTM model can provide accurate and reliable PV power predictions for all studied technologies.By identifying the most suitable predictive model for each panel technology,this study contributes to optimizing PV power forecasting and improving energy management strategies.
基金supported by the National Natural Science Foundation of China(Grant Nos.42375062 and 42275158)the National Key Scientific and Technological Infrastructure project“Earth System Science Numerical Simulator Facility”(EarthLab)the Natural Science Foundation of Gansu Province(Grant No.22JR5RF1080)。
文摘It is fundamental and useful to investigate how deep learning forecasting models(DLMs)perform compared to operational oceanography forecast systems(OFSs).However,few studies have intercompared their performances using an identical reference.In this study,three physically reasonable DLMs are implemented for the forecasting of the sea surface temperature(SST),sea level anomaly(SLA),and sea surface velocity in the South China Sea.The DLMs are validated against both the testing dataset and the“OceanPredict”Class 4 dataset.Results show that the DLMs'RMSEs against the latter increase by 44%,245%,302%,and 109%for SST,SLA,current speed,and direction,respectively,compared to those against the former.Therefore,different references have significant influences on the validation,and it is necessary to use an identical and independent reference to intercompare the DLMs and OFSs.Against the Class 4 dataset,the DLMs present significantly better performance for SLA than the OFSs,and slightly better performances for other variables.The error patterns of the DLMs and OFSs show a high degree of similarity,which is reasonable from the viewpoint of predictability,facilitating further applications of the DLMs.For extreme events,the DLMs and OFSs both present large but similar forecast errors for SLA and current speed,while the DLMs are likely to give larger errors for SST and current direction.This study provides an evaluation of the forecast skills of commonly used DLMs and provides an example to objectively intercompare different DLMs.
