Symposium overview The International Symposium on Earthquake Forecasting to Commemorate the 50th Anniversary of the 1975 Haicheng M7.3 Earthquake,Liaoning,China,was held in Shenyang,China,from 8 to 11 July 2025.The sy...Symposium overview The International Symposium on Earthquake Forecasting to Commemorate the 50th Anniversary of the 1975 Haicheng M7.3 Earthquake,Liaoning,China,was held in Shenyang,China,from 8 to 11 July 2025.The symposium was organized by the Institute of Earthquake Forecasting,China Earthquake Administration(CEA),the State Key Laboratory of Earthquake Dynamics and Forecasting,and the China Seismic Experimental Site(CSES),in collaboration with the International Association of Seismology and Physics of the Earth’s Interior(IASPEI),the APEC Cooperation for Earthquake Science(ACES).展开更多
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
With the increasing penetration of variable renewable energy,flexible resources are highly needed to hedge the growing uncertainty,and variability in the power system.Demand response has served as a cost-effective typ...With the increasing penetration of variable renewable energy,flexible resources are highly needed to hedge the growing uncertainty,and variability in the power system.Demand response has served as a cost-effective type of flexible resource in recent years.In order to balance the uncertainty of the system,it is crucial to assess how much flexibility demand response programs can provide.Thus,forecasting demand response potential is important for the operation of the bulk system.This paper proposes a modeling approach that can characterize the multi-timescale flexibility of demand response so that not only the power potential but also temporal-coupling characteristics can be considered.Furthermore,a day-ahead demand response potential forecasting method is proposed using deep convolutional generative adversarial networks.The proposed forecasting method is tested using data from 170 users in Pecan Street Dataport.The results show that the proposed method can forecast the multi-timescale flexibility of demand response with high accuracy.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
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
Clouds are one of the leading causes of sun shading,which reduces the direct horizontal irradiance and curtails the photovoltaic(PV)power.It is critical to estimate cloud cover to accurately predict PV generation with...Clouds are one of the leading causes of sun shading,which reduces the direct horizontal irradiance and curtails the photovoltaic(PV)power.It is critical to estimate cloud cover to accurately predict PV generation within a very short horizon(second/minute).To achieve the precise forecasting of cloud cover,an image preprocessing method based on total-sky images is proposed to remove the interference and address the image edge distortion issue.An optimal threshold estimation method is further designed to achieve higher cloud identification precision.Considering the cloud's meteorological properties,a random hypersurface model(RHM)based on the Gaussian mixture probability hypothesis density(GM-PHD)filter is applied to track the cloud.The GM-PHD can track the rotation and diffusion of clouds,which helps to estimate sun-cloud collision.Furthermore,a hybrid autoregressive integrated moving average(ARIMA)and backpropagation(BP)neural network-based model is applied for intra-hour PV power forecasting.The experiment results demonstrate that the proposed cloud-tracking-based PV power forecasting model can capture the ramp behavior of PV power,improving forecasting precision.展开更多
Accurate forecasting of crude oil futures prices is crucial for understanding global energy market dynamics and formulating effective macroeconomic and energy strategies.However,the strong nonlinearity and multi-scale...Accurate forecasting of crude oil futures prices is crucial for understanding global energy market dynamics and formulating effective macroeconomic and energy strategies.However,the strong nonlinearity and multi-scale temporal characteristics of crude oil prices pose significant challenges to traditional forecasting methods.To address these issues,this study proposes a hybrid CEEMDAN–HOA–Transformer–GRU model that integrates decomposition,complexity analysis,adaptive modeling,and intelligent optimization.Specifically,Complete Ensemble Empirical Mode Decomposition with Adaptive Noise(CEEMDAN)is employed to decompose the original series into multi-scale components,after which entropy-based complexity analysis quantitatively evaluates each component.A differentiated modeling strategy is then applied:Transformer networks capture long-term dependencies in high-complexity components,while Gated Recurrent Units(GRU)model short-term dynamics in relatively simple components.To further enhance robustness,the Hiking Optimization Algorithm(HOA)is used for joint hyperparameter optimization across both base learners.Empirical analysis of WTI and Brent crude oil futures demonstrates the technical effectiveness of the framework.Compared with benchmark models,the proposed method reduces RMSE by 79.16% for WTI and 77.47% for Brent.Incorporating complexity analysis further decreases RMSE by 36.51%for WTI and 34.93%for Brent,confirming the superior nonlinear modeling capacity and generalization performance of the integrated framework.Overall,this study provides not only a technically reliable tool for modeling complex financial time series but also practical guidance for improving the accuracy and stability of crude oil price forecasting,thereby supporting market monitoring,risk management,and policy formulation.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
The basic condition of earthquake disasters in China is featured by high frequency,strong intensity,wide distribution,and heavy losses.Earthquake forecasting plays a critical role in reducing seismic risks.To better a...The basic condition of earthquake disasters in China is featured by high frequency,strong intensity,wide distribution,and heavy losses.Earthquake forecasting plays a critical role in reducing seismic risks.To better advance earthquake predicting efforts,the China Earthquake Administration released the Strategic Plan for Earthquake Forecasting in China(2025−2035)on the occasion of the 50th anniversary of the Haicheng earthquake.Here we briefly introduce the main contents of the Strategic Plan,including the main progress,strategic objectives,and development directions of earthquake forecasting in China.展开更多
Multivariate time series forecasting plays a crucial role in decision-making for systems like energy grids and transportation networks,where temporal patterns emerge across diverse scales from short-term fluctuations ...Multivariate time series forecasting plays a crucial role in decision-making for systems like energy grids and transportation networks,where temporal patterns emerge across diverse scales from short-term fluctuations to long-term trends.However,existing Transformer-based methods often process data at a single resolution or handle multiple scales independently,overlooking critical cross-scale interactions that influence prediction accuracy.To address this gap,we introduce the Hierarchical Attention Transformer(HAT),which enables direct information exchange between temporal hierarchies through a novel cross-scale attention mechanism.HAT extracts multi-scale features using hierarchical convolutional-recurrent blocks,fuses them via temperature-controlled mechanisms,and optimizes gradient flow with residual connections for stable training.Evaluations on eight benchmark datasets show HAT outperforming state-of-the-art baselines,with average reductions of 8.2%in MSE and 7.5%in MAE across horizons,while achieving a 6.1×training speedup over patch-based methods.These advancements highlight HAT’s potential for applications requiring multi-resolution temporal modeling.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
The accuracy of photovoltaic(PV)power prediction is significantly influenced by meteorological and environmental factors.To enhance ultra-short-term forecasting precision,this paper proposes an interpretable feedback ...The accuracy of photovoltaic(PV)power prediction is significantly influenced by meteorological and environmental factors.To enhance ultra-short-term forecasting precision,this paper proposes an interpretable feedback prediction method based on a parallel dual-stream Temporal Convolutional Network-Bidirectional Long Short-Term Memory(TCN-BiLSTM)architecture incorporating a spatiotemporal attention mechanism.Firstly,during data preprocessing,the optimal historical time window is determined through autocorrelation analysis while highly correlated features are selected as model inputs using Pearson correlation coefficients.Subsequently,a parallel dual-stream TCN-BiLSTM model is constructed where the TCN branch extracts localized transient features and the BiLSTM branch captures long-term periodic patterns,with spatiotemporal attention dynamically weighting spatiotemporal dependencies.Finally,Shapley Additive explanations(SHAP)additive analysis quantifies feature contribution rates and provides optimization feedback to the model.Validation using operational data from a PV power station in Northeast China demonstrates that compared to conventional deep learning models,the proposed method achieves a 17.6%reduction in root mean square error(RMSE),a 5.4%decrease in training time consumption,and a 4.78%improvement in continuous ranked probability score(CRPS),exhibiting significant advantages in both prediction accuracy and generalization capability.This approach enhances the application effectiveness of ultra-short-term PV power forecasting while simultaneously improving prediction accuracy and computational efficiency.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
Accurate multi-step PM_(2.5)(particulate matter with diameters≤2.5 um)concentration prediction is critical for humankinds’health and air populationmanagement because it could provide strong evidence for decisionmaki...Accurate multi-step PM_(2.5)(particulate matter with diameters≤2.5 um)concentration prediction is critical for humankinds’health and air populationmanagement because it could provide strong evidence for decisionmaking.However,it is very challenging due to its randomness and variability.This paper proposed a novel method based on convolutional neural network(CNN)and long-short-term memory(LSTM)with a space-shared mechanism,named space-shared CNN-LSTM(SCNN-LSTM)for multi-site dailyahead multi-step PM_(2.5)forecasting with self-historical series.The proposed SCNN-LSTM contains multi-channel inputs,each channel corresponding to one-site historical PM_(2.5)concentration series.In which,CNN and LSTM are used to extract each site’s rich hidden feature representations in a stack mode.Especially,CNN is to extract the hidden short-time gap PM_(2.5)concentration patterns;LSTM is to mine the hidden features with long-time dependency.Each channel extracted features aremerged as the comprehensive features for future multi-step PM_(2.5)concentration forecasting.Besides,the space-shared mechanism is implemented by multi-loss functions to achieve space information sharing.Therefore,the final features are the fusion of short-time gap,long-time dependency,and space information,which enables forecasting more accurately.To validate the proposed method’s effectiveness,the authors designed,trained,and compared it with various leading methods in terms of RMSE,MAE,MAPE,and R^(2)on four real-word PM_(2.5)data sets in Seoul,South Korea.The massive experiments proved that the proposed method could accurately forecast multi-site multi-step PM_(2.5)concentration only using self-historical PM_(2.5)concentration time series and running once.Specifically,the proposed method obtained averaged RMSE of 8.05,MAE of 5.04,MAPE of 23.96%,and R^(2)of 0.7 for four-site daily ahead 10-hourPM_(2.5)concentration forecasting.展开更多
Due to global energy depletion,solar energy technology has been widely used in the world.The output power of the solar energy systems is affected by solar radiation.Accurate short-term forecasting of solar radiation c...Due to global energy depletion,solar energy technology has been widely used in the world.The output power of the solar energy systems is affected by solar radiation.Accurate short-term forecasting of solar radiation can ensure the safety of photovoltaic grids and improve the utilization efficiency of the solar energy systems.In the study,a new decomposition-boosting model using artificial intelligence is proposed to realize the solar radiation multi-step prediction.The proposed model includes four parts:signal decomposition(EWT),neural network(NARX),Adaboost and ARIMA.Three real solar radiation datasets from Changde,China were used to validate the efficiency of the proposed model.To verify the robustness of the multi-step prediction model,this experiment compared nine models and made 1,3,and 5 steps ahead predictions for the time series.It is verified that the proposed model has the best performance among all models.展开更多
A new methodology for multi-step-ahead forecasting was proposed herein which combined the wavelet transform(WT), artificial neural network(ANN) and forecasting strategies based on the changing characteristics of avail...A new methodology for multi-step-ahead forecasting was proposed herein which combined the wavelet transform(WT), artificial neural network(ANN) and forecasting strategies based on the changing characteristics of available parking spaces(APS). First, several APS time series were decomposed and reconstituted by the wavelet transform. Then, using an artificial neural network, the following five strategies for multi-step-ahead time series forecasting were used to forecast the reconstructed time series: recursive strategy, direct strategy, multi-input multi-output(MIMO) strategy, DIRMO strategy(a combination of the direct and MIMO strategies), and newly proposed recursive multi-input multi-output(RECMO) strategy which is a combination of the recursive and MIMO strategies. Finally, integrating the predicted results with the reconstructed time series produced the final forecasted available parking spaces. Three findings appear to be consistently supported by the experimental results. First, applying the wavelet transform to multi-step ahead available parking spaces forecasting can effectively improve the forecasting accuracy. Second, the forecasting resulted from the DIRMO and RECMO strategies is more accurate than that of the other strategies. Finally, the RECMO strategy requires less model training time than the DIRMO strategy and consumes the least amount of training time among five forecasting strategies.展开更多
Affected by the pandemic coronavirus-19(COVID-19),significant changes have taken place in all aspects of social production and residents’lives,as well as in the energy supply and consumption characteristics of the po...Affected by the pandemic coronavirus-19(COVID-19),significant changes have taken place in all aspects of social production and residents’lives,as well as in the energy supply and consumption characteristics of the power system.COVID-19 has brought unpredictable uncertainties to the power grid.These changes and uncertainties pose a challenge to conventional electric load forecasting.Therefore,aiming to load forecasting under the background of the pandemic,this paper proposes a power load segmented forecasting method based on the pandemic stage division method,attention mechanism,and bi-directional long and short-term memory artificial neural network quantile regression model(ESD-ABiLSTMQR).According to the development degree of the pandemic,considering characteristics of different development stages of the pandemic,the pandemic is divided into four stages by using the analytic hierarchy process method(AHP):initial stage,outbreak stage,control stage,and recovery stage.A segmented load forecasting model based on LSTM and attention mechanism is established to forecast load in different time series.Cases used data from the pandemic in Wuhan,China,for verification.Results show the segmented forecasting method can analyze load characteristics of each stage and can effectively improve the accuracy of load forecasting.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
基金supported by the National Natural Science Foundation of China (No.U2039207)
文摘Symposium overview The International Symposium on Earthquake Forecasting to Commemorate the 50th Anniversary of the 1975 Haicheng M7.3 Earthquake,Liaoning,China,was held in Shenyang,China,from 8 to 11 July 2025.The symposium was organized by the Institute of Earthquake Forecasting,China Earthquake Administration(CEA),the State Key Laboratory of Earthquake Dynamics and Forecasting,and the China Seismic Experimental Site(CSES),in collaboration with the International Association of Seismology and Physics of the Earth’s Interior(IASPEI),the APEC Cooperation for Earthquake Science(ACES).
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 National Key R&D Program of China(No.2021YFB2401200)National Natural Science Foundation of China(72242105)Organized Research Support Program,Department of Electrical Engineering,Tsinghua University.
文摘With the increasing penetration of variable renewable energy,flexible resources are highly needed to hedge the growing uncertainty,and variability in the power system.Demand response has served as a cost-effective type of flexible resource in recent years.In order to balance the uncertainty of the system,it is crucial to assess how much flexibility demand response programs can provide.Thus,forecasting demand response potential is important for the operation of the bulk system.This paper proposes a modeling approach that can characterize the multi-timescale flexibility of demand response so that not only the power potential but also temporal-coupling characteristics can be considered.Furthermore,a day-ahead demand response potential forecasting method is proposed using deep convolutional generative adversarial networks.The proposed forecasting method is tested using data from 170 users in Pecan Street Dataport.The results show that the proposed method can forecast the multi-timescale flexibility of demand response with high accuracy.
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 National Natural Science Foundation of China(U1909201,62206062).
文摘Clouds are one of the leading causes of sun shading,which reduces the direct horizontal irradiance and curtails the photovoltaic(PV)power.It is critical to estimate cloud cover to accurately predict PV generation within a very short horizon(second/minute).To achieve the precise forecasting of cloud cover,an image preprocessing method based on total-sky images is proposed to remove the interference and address the image edge distortion issue.An optimal threshold estimation method is further designed to achieve higher cloud identification precision.Considering the cloud's meteorological properties,a random hypersurface model(RHM)based on the Gaussian mixture probability hypothesis density(GM-PHD)filter is applied to track the cloud.The GM-PHD can track the rotation and diffusion of clouds,which helps to estimate sun-cloud collision.Furthermore,a hybrid autoregressive integrated moving average(ARIMA)and backpropagation(BP)neural network-based model is applied for intra-hour PV power forecasting.The experiment results demonstrate that the proposed cloud-tracking-based PV power forecasting model can capture the ramp behavior of PV power,improving forecasting precision.
基金funded by the Henan Provincial Natural Science Foundation(grant no.242300421257).
文摘Accurate forecasting of crude oil futures prices is crucial for understanding global energy market dynamics and formulating effective macroeconomic and energy strategies.However,the strong nonlinearity and multi-scale temporal characteristics of crude oil prices pose significant challenges to traditional forecasting methods.To address these issues,this study proposes a hybrid CEEMDAN–HOA–Transformer–GRU model that integrates decomposition,complexity analysis,adaptive modeling,and intelligent optimization.Specifically,Complete Ensemble Empirical Mode Decomposition with Adaptive Noise(CEEMDAN)is employed to decompose the original series into multi-scale components,after which entropy-based complexity analysis quantitatively evaluates each component.A differentiated modeling strategy is then applied:Transformer networks capture long-term dependencies in high-complexity components,while Gated Recurrent Units(GRU)model short-term dynamics in relatively simple components.To further enhance robustness,the Hiking Optimization Algorithm(HOA)is used for joint hyperparameter optimization across both base learners.Empirical analysis of WTI and Brent crude oil futures demonstrates the technical effectiveness of the framework.Compared with benchmark models,the proposed method reduces RMSE by 79.16% for WTI and 77.47% for Brent.Incorporating complexity analysis further decreases RMSE by 36.51%for WTI and 34.93%for Brent,confirming the superior nonlinear modeling capacity and generalization performance of the integrated framework.Overall,this study provides not only a technically reliable tool for modeling complex financial time series but also practical guidance for improving the accuracy and stability of crude oil price forecasting,thereby supporting market monitoring,risk management,and policy formulation.
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.
文摘The basic condition of earthquake disasters in China is featured by high frequency,strong intensity,wide distribution,and heavy losses.Earthquake forecasting plays a critical role in reducing seismic risks.To better advance earthquake predicting efforts,the China Earthquake Administration released the Strategic Plan for Earthquake Forecasting in China(2025−2035)on the occasion of the 50th anniversary of the Haicheng earthquake.Here we briefly introduce the main contents of the Strategic Plan,including the main progress,strategic objectives,and development directions of earthquake forecasting in China.
文摘Multivariate time series forecasting plays a crucial role in decision-making for systems like energy grids and transportation networks,where temporal patterns emerge across diverse scales from short-term fluctuations to long-term trends.However,existing Transformer-based methods often process data at a single resolution or handle multiple scales independently,overlooking critical cross-scale interactions that influence prediction accuracy.To address this gap,we introduce the Hierarchical Attention Transformer(HAT),which enables direct information exchange between temporal hierarchies through a novel cross-scale attention mechanism.HAT extracts multi-scale features using hierarchical convolutional-recurrent blocks,fuses them via temperature-controlled mechanisms,and optimizes gradient flow with residual connections for stable training.Evaluations on eight benchmark datasets show HAT outperforming state-of-the-art baselines,with average reductions of 8.2%in MSE and 7.5%in MAE across horizons,while achieving a 6.1×training speedup over patch-based methods.These advancements highlight HAT’s potential for applications requiring multi-resolution temporal modeling.
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.
基金funded by the National Natural Science Foundation of China(NSFC)(No.62066024)funded by Basic Scientific Research Projects of Higher Education Institutions in Liaoning Province(LJ212411632063)the National Undergraduate Training Program for Innovation and Entrepreneurship(S202511632045).
文摘The accuracy of photovoltaic(PV)power prediction is significantly influenced by meteorological and environmental factors.To enhance ultra-short-term forecasting precision,this paper proposes an interpretable feedback prediction method based on a parallel dual-stream Temporal Convolutional Network-Bidirectional Long Short-Term Memory(TCN-BiLSTM)architecture incorporating a spatiotemporal attention mechanism.Firstly,during data preprocessing,the optimal historical time window is determined through autocorrelation analysis while highly correlated features are selected as model inputs using Pearson correlation coefficients.Subsequently,a parallel dual-stream TCN-BiLSTM model is constructed where the TCN branch extracts localized transient features and the BiLSTM branch captures long-term periodic patterns,with spatiotemporal attention dynamically weighting spatiotemporal dependencies.Finally,Shapley Additive explanations(SHAP)additive analysis quantifies feature contribution rates and provides optimization feedback to the model.Validation using operational data from a PV power station in Northeast China demonstrates that compared to conventional deep learning models,the proposed method achieves a 17.6%reduction in root mean square error(RMSE),a 5.4%decrease in training time consumption,and a 4.78%improvement in continuous ranked probability score(CRPS),exhibiting significant advantages in both prediction accuracy and generalization capability.This approach enhances the application effectiveness of ultra-short-term PV power forecasting while simultaneously improving prediction accuracy and computational efficiency.
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This work was supported by a Research Grant from Pukyong National University(2021).
文摘Accurate multi-step PM_(2.5)(particulate matter with diameters≤2.5 um)concentration prediction is critical for humankinds’health and air populationmanagement because it could provide strong evidence for decisionmaking.However,it is very challenging due to its randomness and variability.This paper proposed a novel method based on convolutional neural network(CNN)and long-short-term memory(LSTM)with a space-shared mechanism,named space-shared CNN-LSTM(SCNN-LSTM)for multi-site dailyahead multi-step PM_(2.5)forecasting with self-historical series.The proposed SCNN-LSTM contains multi-channel inputs,each channel corresponding to one-site historical PM_(2.5)concentration series.In which,CNN and LSTM are used to extract each site’s rich hidden feature representations in a stack mode.Especially,CNN is to extract the hidden short-time gap PM_(2.5)concentration patterns;LSTM is to mine the hidden features with long-time dependency.Each channel extracted features aremerged as the comprehensive features for future multi-step PM_(2.5)concentration forecasting.Besides,the space-shared mechanism is implemented by multi-loss functions to achieve space information sharing.Therefore,the final features are the fusion of short-time gap,long-time dependency,and space information,which enables forecasting more accurately.To validate the proposed method’s effectiveness,the authors designed,trained,and compared it with various leading methods in terms of RMSE,MAE,MAPE,and R^(2)on four real-word PM_(2.5)data sets in Seoul,South Korea.The massive experiments proved that the proposed method could accurately forecast multi-site multi-step PM_(2.5)concentration only using self-historical PM_(2.5)concentration time series and running once.Specifically,the proposed method obtained averaged RMSE of 8.05,MAE of 5.04,MAPE of 23.96%,and R^(2)of 0.7 for four-site daily ahead 10-hourPM_(2.5)concentration forecasting.
基金Project(2020TJ-Q06)supported by Hunan Provincial Science&Technology Talent Support,ChinaProject(KQ1707017)supported by the Changsha Science&Technology,ChinaProject(2019CX005)supported by the Innovation Driven Project of the Central South University,China。
文摘Due to global energy depletion,solar energy technology has been widely used in the world.The output power of the solar energy systems is affected by solar radiation.Accurate short-term forecasting of solar radiation can ensure the safety of photovoltaic grids and improve the utilization efficiency of the solar energy systems.In the study,a new decomposition-boosting model using artificial intelligence is proposed to realize the solar radiation multi-step prediction.The proposed model includes four parts:signal decomposition(EWT),neural network(NARX),Adaboost and ARIMA.Three real solar radiation datasets from Changde,China were used to validate the efficiency of the proposed model.To verify the robustness of the multi-step prediction model,this experiment compared nine models and made 1,3,and 5 steps ahead predictions for the time series.It is verified that the proposed model has the best performance among all models.
基金Project(51561135003)supported by the International Cooperation and Exchange of the National Natural Science Foundation of ChinaProject(51338003)supported by the Key Project of National Natural Science Foundation of China
文摘A new methodology for multi-step-ahead forecasting was proposed herein which combined the wavelet transform(WT), artificial neural network(ANN) and forecasting strategies based on the changing characteristics of available parking spaces(APS). First, several APS time series were decomposed and reconstituted by the wavelet transform. Then, using an artificial neural network, the following five strategies for multi-step-ahead time series forecasting were used to forecast the reconstructed time series: recursive strategy, direct strategy, multi-input multi-output(MIMO) strategy, DIRMO strategy(a combination of the direct and MIMO strategies), and newly proposed recursive multi-input multi-output(RECMO) strategy which is a combination of the recursive and MIMO strategies. Finally, integrating the predicted results with the reconstructed time series produced the final forecasted available parking spaces. Three findings appear to be consistently supported by the experimental results. First, applying the wavelet transform to multi-step ahead available parking spaces forecasting can effectively improve the forecasting accuracy. Second, the forecasting resulted from the DIRMO and RECMO strategies is more accurate than that of the other strategies. Finally, the RECMO strategy requires less model training time than the DIRMO strategy and consumes the least amount of training time among five forecasting strategies.
基金supported by National Natural Science Foundation of China(No.52407074)Anhui Provincial Natural Science Foundation Youth Project,China(2308085QE177)Key Research Projects in Natural Sciences of Universities funded by the Department of Education in Anhui Province,China(2023AH050092).
文摘Affected by the pandemic coronavirus-19(COVID-19),significant changes have taken place in all aspects of social production and residents’lives,as well as in the energy supply and consumption characteristics of the power system.COVID-19 has brought unpredictable uncertainties to the power grid.These changes and uncertainties pose a challenge to conventional electric load forecasting.Therefore,aiming to load forecasting under the background of the pandemic,this paper proposes a power load segmented forecasting method based on the pandemic stage division method,attention mechanism,and bi-directional long and short-term memory artificial neural network quantile regression model(ESD-ABiLSTMQR).According to the development degree of the pandemic,considering characteristics of different development stages of the pandemic,the pandemic is divided into four stages by using the analytic hierarchy process method(AHP):initial stage,outbreak stage,control stage,and recovery stage.A segmented load forecasting model based on LSTM and attention mechanism is established to forecast load in different time series.Cases used data from the pandemic in Wuhan,China,for verification.Results show the segmented forecasting method can analyze load characteristics of each stage and can effectively improve the accuracy of load forecasting.
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.
