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
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
This study presents a comprehensive evaluation of tropical cyclone(TC)forecast performance in the western North Pacific from 2013 to 2022,based on operational forecasts issued by the China Meteorological Administratio...This study presents a comprehensive evaluation of tropical cyclone(TC)forecast performance in the western North Pacific from 2013 to 2022,based on operational forecasts issued by the China Meteorological Administration.The analysis reveals systematic improvements in both track and intensity forecasts over the decade,with distinct error characteristics observed across various forecast parameters.Track forecast errors have steadily decreased,particularly for longer lead times,while error magnitudes have increased with longer forecast lead times.Intensity forecasts show similar progressive enhancements,with maximum sustained wind speed errors decreasing by 0.26 m/s per year for 120 h forecasts.The study also identifies several key patterns in forecast performance:typhoon-grade or stronger TCs exhibit smaller track errors than week or weaker systems;intensity forecasts systematically overestimate weaker TCs while underestimating stronger systems;and spatial error distributions show greater track inaccuracies near landmasses and regional intensity biases.These findings highlight both the significant advances in TC forecasting capability achieved through improved modeling and observational systems,and the remaining challenges in predicting TC changes and landfall behavior,providing valuable benchmarks for future forecast system development.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 photovoltaic(PV)power generation forecasting is essential for the efficient integration of renewable energy into power grids.However,the nonlinear and non-stationary characteristics of PV power signals,driven...Accurate photovoltaic(PV)power generation forecasting is essential for the efficient integration of renewable energy into power grids.However,the nonlinear and non-stationary characteristics of PV power signals,driven by fluctuating weather conditions,pose significant challenges for reliable prediction.This study proposes a DOEP(Decomposition–Optimization–Error Correction–Prediction)framework,a hybrid forecasting approach that integrates adaptive signal decomposition,machine learning,metaheuristic optimization,and error correction.The PV power signal is first decomposed using CEEMDAN to extract multi-scale temporal features.Subsequently,the hyperparameters and window sizes of the LSSVM are optimized using a Segment-based EBQPSO strategy.The main novelty of the proposed DOEP framework lies in the incorporation of Segment-based EBQPSO as a structured optimization mechanism that balances elite exploitation and population diversity during LSSVM tuning within the CEEMDAN-based forecasting pipeline.This strategy effectively mitigates convergence instability and sensitivity to initialization,which are common limitations in existing hybrid PV forecasting models.Each IMF is then predicted individually and aggregated to generate an initial forecast.In the error-correction stage,the residual error series is modeled using LSTM,and the final prediction is obtained by combining the initial forecast with the predicted error component.The proposed framework is evaluated using two PV power plant datasets with different levels of complexity.The results demonstrate that DOEP consistently outperforms benchmark models across multiple error-based and goodness-of-fit metrics,achieving MSE reductions of approximately 15%–60%on the ResPV-BDG dataset and 37%–92%on the NREL dataset.Analyses of predicted vs.observed values and residual distributions further confirm the superior calibration and robustness of the proposed approach.Although the DOEP framework entails higher computational costs than single model methods,it delivers significantly improved accuracy and stability for PV power forecasting under complex operating conditions.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
Small datasets are often challenging due to their limited sample size.This research introduces a novel solution to these problems:average linkage virtual sample generation(ALVSG).ALVSG leverages the underlying data st...Small datasets are often challenging due to their limited sample size.This research introduces a novel solution to these problems:average linkage virtual sample generation(ALVSG).ALVSG leverages the underlying data structure to create virtual samples,which can be used to augment the original dataset.The ALVSG process consists of two steps.First,an average-linkage clustering technique is applied to the dataset to create a dendrogram.The dendrogram represents the hierarchical structure of the dataset,with each merging operation regarded as a linkage.Next,the linkages are combined into an average-based dataset,which serves as a new representation of the dataset.The second step in the ALVSG process involves generating virtual samples using the average-based dataset.The research project generates a set of 100 virtual samples by uniformly distributing them within the provided boundary.These virtual samples are then added to the original dataset,creating a more extensive dataset with improved generalization performance.The efficacy of the ALVSG approach is validated through resampling experiments and t-tests conducted on two small real-world datasets.The experiments are conducted on three forecasting models:the support vector machine for regression(SVR),the deep learning model(DL),and XGBoost.The results show that the ALVSG approach outperforms the baseline methods in terms of mean square error(MSE),root mean square error(RMSE),and mean absolute error(MAE).展开更多
The Vertical Total Electron Content(VTEC)of the ionosphere is a crucial parameter for describing the distribution and dynamic changes within the ionosphere.The study utilizes Dual Hybrid Attentional UNet(DHA-UNet)mode...The Vertical Total Electron Content(VTEC)of the ionosphere is a crucial parameter for describing the distribution and dynamic changes within the ionosphere.The study utilizes Dual Hybrid Attentional UNet(DHA-UNet)model to achieve higher forecasting performance for global VTEC predictions under the condition of data acquisition delays.Initially,this study uses the first Hybrid Attentional UNet(HA-UNet)model to predict the intermediate missing data.The missing data are caused by delays in data processing,making the Global Ionosphere Map(GIM)for the current day unavailable.Subsequently,the predicted results from the first HA-UNet model are concatenated with the input data to serve as the input data for the second HA-UNet model,yielding the final prediction results.The performance of DHA-UNet model is then evaluated under varying solar and geomagnetic activity conditions.Evaluation results demonstrate that the DHA-UNet model exhibits higher forecasting accuracy and stability compared to commonly used temporal and spatiotemporal forecasting models.Compared to CODG VTEC,the DHA-UNet model achieves Mean Absolute Error(MAE)values of 2.60 TECU,3.07 TECU,3.78 TECU,and 6.45TECU during quiet,weak,moderate,and strong geomagnetic storm periods,respectively,in years of high solar activity.In years of low solar activity,the model achieves MAE values of 1.00 TECU,1.15 TECU,and 1.54 TECU during quiet,weak,and moderate geomagnetic storm periods,respectively.Even during strong geomagnetic storms,55%of the residuals from the DHA-UNet model fall within the-5.0 TECU to 5.0 TECU range,surpassing other commonly used models.Compared to the C1PG forecasting product,the DHA-UNet model shows particularly notable improvements in accuracy during the spring and winter seasons,as well as in mid-to high-latitude regions.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
Marine forecasting is critical for navigation safety and disaster prevention.However,traditional ocean numerical forecasting models are often limited by substantial errors and inadequate capture of temporal-spatial fe...Marine forecasting is critical for navigation safety and disaster prevention.However,traditional ocean numerical forecasting models are often limited by substantial errors and inadequate capture of temporal-spatial features.To address the limitations,the paper proposes a TimeXer-based numerical forecast correction model optimized by an exogenous-variable attention mechanism.The model treats target forecast values as internal variables,and incorporates historical temporal-spatial data and seven-day numerical forecast results from traditional models as external variables based on the embedding strategy of TimeXer.Using a self-attention structure,the model captures correlations between exogenous variables and target sequences,explores intrinsic multi-dimensional relationships,and subsequently corrects endogenous variables with the mined exogenous features.The model’s performance is evaluated using metrics including MSE(Mean Squared Error),MAE(Mean Absolute Error),RMSE(Root Mean Square Error),MAPE(Mean Absolute Percentage Error),MSPE(Mean Square Percentage Error),and computational time,with TimeXer and PatchTST models serving as benchmarks.Experiment results show that the proposed model achieves lower errors and higher correction accuracy for both one-day and seven-day forecasts.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
Temperate forests are vital for maintaining ecological security and regulating the global climate.Despite considerable controversy surrounding the biophysical impacts of temperate forests on mid-latitude temperatures,...Temperate forests are vital for maintaining ecological security and regulating the global climate.Despite considerable controversy surrounding the biophysical impacts of temperate forests on mid-latitude temperatures,we analyzed the effects of forest cover change on local temperature using the Weather Research and Forecasting(WRF)model from 2010 to 2020 in the Greater and Lesser Khingan Mountains(GLKM),Northeastern China,and explored the related driving factors.The conversions between forest and open lands(i.e.,cropland and grassland)were predominant.During the growing season,the conversion of cropland and grassland to forest resulted in warming(0.38±0.10 and 0.41±0.09℃,respectively)in air temperature(Ta),while the reverse conversion caused cooling(-0.31 peratur±0.08 and e-0.24±0.07℃,respectively),which was less than the changes observed in land surface tem(LST).Conversion of forest to impervious land caused warming(1.16 the±0.11℃),and opposite conversion resulted in cooling(can-0.88 t±0.17℃).These results indicate that radiative effects like albedo and net radiation drive the signifi net warming effect from afforestation on open lands within the temperate forest ecoregion.Conversely,conversion to impervious land produced the most substantial net warming impacts,driven by non-radiative effects like sensible heat,latent heat,and ground heat flux(GH).In these conversions,temperature can indirectly influence precipitation(Pre)through vapor pressure deficit(VPD),and Pre can also indirectly affect temperature via evapotranspiration(ET).This study highlights the need to thoroughly understand the impacts of afforestation in temperate forests while avoiding deforestation to regulate the climate effectively.展开更多
1.Introduction Artificial intelligence(AI)is rapidly reshaping geoscience,from Earth observation interpretation and hazard forecasting to subsurface characterisation and Earth system modelling(Kochupillai et al.,2022;...1.Introduction Artificial intelligence(AI)is rapidly reshaping geoscience,from Earth observation interpretation and hazard forecasting to subsurface characterisation and Earth system modelling(Kochupillai et al.,2022;Sun et al.,2024).These capabilities emerge at a time when geoscientific evidence is increasingly informing high-stakes decisions about climate adaptation,resource development,and disaster risk reduction(McGovern et al.,2022).展开更多
Climate model prediction has been improved by enhancing model resolution as well as the implementation of sophisticated physical parameterization and refinement of data assimilation systems[section 6.1 in Wang et al.(...Climate model prediction has been improved by enhancing model resolution as well as the implementation of sophisticated physical parameterization and refinement of data assimilation systems[section 6.1 in Wang et al.(2025)].In relation to seasonal forecasting and climate projection in the East Asian summer monsoon season,proper simulation of the seasonal migration of rain bands by models is a challenging and limiting factor[section 7.1 in Wang et al.(2025)].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
This study examines the track and intensity forecasts of two typical Bay of Bengal tropical cyclones(TC)ASANI and MOCHA.The analysis of various Numerical Weather Prediction(NWP)model forecasts[ECMWF(European Centre fo...This study examines the track and intensity forecasts of two typical Bay of Bengal tropical cyclones(TC)ASANI and MOCHA.The analysis of various Numerical Weather Prediction(NWP)model forecasts[ECMWF(European Centre for Medium range Weather Forecast),NCEP(National Centers for Environmental Prediction),NCUM(National Centre for Medium Range Weather Forecast-Unified Model),IMD(India Meteorological Department),HWRF(Hurricane Weather Research and Forecasting)],MME(Multi-model Ensemble),SCIP(Statistical Cyclone Intensity Prediction)model,and OFCL(Official)forecasts shows that intensity forecasts of ASANI and track forecasts of MOCHA were reasonably good,but there were large errors and wide variation in track forecasts of ASANI and in intensity forecasts of MOCHA.Among all model forecasts,the track forecast errors of IMD model and MME were least in general for ASANI and MOCHA respectively.Also,the landfall point forecast errors of IMD were least for ASANI,and the MME and OFCL forecast errors were least for MOCHA.No model is found to be consistently better for landfall time forecast for ASANI,and the errors of ECMWF,IMD and HWRF were least and of same order for MOCHA.The intensity forecast errors of OFCL and SCIP were least for ASANI,and the forecast errors of HWRF,IMD,NCEP,SCIP and OFCL were comparable and least for MOCHA up to 48 h forecast and HWRF errors were least thereafter in general.The ECMWF model forecast errors for intensity were found to be highest for both the TCs.The results also show that although there is significant improvement of track forecasts and limited or no improvement of intensity forecast in previous decades but challenges still persists in real time forecasting of both track and intensity due to wide variation and inconsistency of model forecasts for different TC cases.展开更多
Conducting predictability studies is essential for tracing the source of forecast errors,which not only leads to the improvement of observation and forecasting systems,but also enhances the understanding of weather an...Conducting predictability studies is essential for tracing the source of forecast errors,which not only leads to the improvement of observation and forecasting systems,but also enhances the understanding of weather and climate phenomena.In the past few decades,dynamical numerical models have been the primary tools for predictability studies,achieving significant progress.Nowadays,with the advances in artificial intelligence(AI)techniques and accumulations of vast meteorological data,modeling weather and climate events using modern data-driven approaches is becoming trendy,where FourCastNet,Pangu-Weather,and GraphCast are successful pioneers.In this perspective article,we suggest AI models should not be limited to forecasting but be expanded to predictability studies,leveraging AI's advantages of high efficiency and self-contained optimization modules.To this end,we first remark that AI models should possess high simulation capability with fine spatiotemporal resolution for two kinds of predictability studies.AI models with high simulation capabilities comparable to numerical models can be considered to provide solutions to partial differential equations in a data-driven way.Then,we highlight several specific predictability issues with well-determined nonlinear optimization formulizations,which can be well-studied using AI models,holding significant scientific value.In addition,we advocate for the incorporation of AI models into the synergistic cycle of the cognition–observation–model paradigm.Comprehensive predictability studies have the potential to transform“big data”to“big and better data”and shift the focus from“AI for forecasts”to“AI for science”,ultimately advancing the development of the atmospheric and oceanic sciences.展开更多
In this article,our nonlinear theory and technology for reducing the uncertainties of high-impact ocean‒atmosphere event predictions,with the conditional nonlinear optimal perturbation(CNOP)method as its core,are revi...In this article,our nonlinear theory and technology for reducing the uncertainties of high-impact ocean‒atmosphere event predictions,with the conditional nonlinear optimal perturbation(CNOP)method as its core,are reviewed,and the“spring predictability barrier”problem for El Nino‒Southern Oscillation events and targeted observation issues for tropical cyclone forecasts are taken as two representative examples.Nonlinear theory reveals that initial errors of particular spatial structures,environmental conditions,and nonlinear processes contribute to significant prediction errors,whereas nonlinear technology provides a pioneering approach for reducing observational and forecast errors via targeted observations through the application of the CNOP method.Follow-up research further validates the scientific rigor of the theory in revealing the nonlinear mechanism of significant prediction errors,and relevant practical field campaigns for targeted observations verify the effectiveness of the technology in reducing prediction uncertainties.The CNOP method has achieved international recognition;furthermore,its applications further extend to ensemble forecasts for weather and climate and further enrich the nonlinear technology for reducing prediction uncertainties.It is expected that this nonlinear theory and technology will play a considerably important role in reducing prediction uncertainties for high-impact weather and climate events.展开更多
Accurate prediction of water level changes in reservoirs is crucial for optimizing the operation of reservoir projects and ensuring their safety.This study proposed a method for reservoir water level prediction based ...Accurate prediction of water level changes in reservoirs is crucial for optimizing the operation of reservoir projects and ensuring their safety.This study proposed a method for reservoir water level prediction based on CEEMDAN-FE and RUN-SVM-RBFNN algorithms.By integrating the adaptive complete ensemble empirical mode decomposition with adaptive noise(CEEMDAN)method and fuzzy entropy(FE)with the new and highly efficient Runge–Kuta optimizer(RUN),adaptive parameter optimization for the support vector machine(SVM)and radial basis function neural network(RBFNN)algorithms was achieved.Regression prediction was conducted on the two reconstructed sequences using SVM and RBFNN according to their respective features.This approach improved the accuracy and stability of predictions.In terms of accuracy,the combined model outperformed single models,with the determination coefficient,root mean square error,and mean absolute error values of 0.9975,0.2418 m,and 0.1616 m,respectively.In terms of stability,the model predicted more consistently in training and testing periods,with stable overall prediction accuracy and a better adaptive ability to complex datasets.The case study demonstrated that the combined prediction model effectively addressed the environmental factors affecting reservoir water levels,leveraged the strength of each predictive method,compensated for their limitations,and clarified the impacts of environmental factors on reservoir water levels.展开更多
Accurate short-term wind power forecast technique plays a crucial role in maintaining the safety and economic efficiency of smart grids.Although numerous studies have employed various methods to forecast wind power,th...Accurate short-term wind power forecast technique plays a crucial role in maintaining the safety and economic efficiency of smart grids.Although numerous studies have employed various methods to forecast wind power,there remains a research gap in leveraging swarm intelligence algorithms to optimize the hyperparameters of the Transformer model for wind power prediction.To improve the accuracy of short-term wind power forecast,this paper proposes a hybrid short-term wind power forecast approach named STL-IAOA-iTransformer,which is based on seasonal and trend decomposition using LOESS(STL)and iTransformer model optimized by improved arithmetic optimization algorithm(IAOA).First,to fully extract the power data features,STL is used to decompose the original data into components with less redundant information.The extracted components as well as the weather data are then input into iTransformer for short-term wind power forecast.The final predicted short-term wind power curve is obtained by combining the predicted components.To improve the model accuracy,IAOA is employed to optimize the hyperparameters of iTransformer.The proposed approach is validated using real-generation data from different seasons and different power stations inNorthwest China,and ablation experiments have been conducted.Furthermore,to validate the superiority of the proposed approach under different wind characteristics,real power generation data fromsouthwestChina are utilized for experiments.Thecomparative results with the other six state-of-the-art prediction models in experiments show that the proposed model well fits the true value of generation series and achieves high prediction accuracy.展开更多
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 Key R&D Program of China [grant number 2023YFC3008004]。
文摘This study presents a comprehensive evaluation of tropical cyclone(TC)forecast performance in the western North Pacific from 2013 to 2022,based on operational forecasts issued by the China Meteorological Administration.The analysis reveals systematic improvements in both track and intensity forecasts over the decade,with distinct error characteristics observed across various forecast parameters.Track forecast errors have steadily decreased,particularly for longer lead times,while error magnitudes have increased with longer forecast lead times.Intensity forecasts show similar progressive enhancements,with maximum sustained wind speed errors decreasing by 0.26 m/s per year for 120 h forecasts.The study also identifies several key patterns in forecast performance:typhoon-grade or stronger TCs exhibit smaller track errors than week or weaker systems;intensity forecasts systematically overestimate weaker TCs while underestimating stronger systems;and spatial error distributions show greater track inaccuracies near landmasses and regional intensity biases.These findings highlight both the significant advances in TC forecasting capability achieved through improved modeling and observational systems,and the remaining challenges in predicting TC changes and landfall behavior,providing valuable benchmarks for future forecast system development.
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.
基金support from the Ministry of Science and Technology of Taiwan(Contract Nos.113-2221-E-011-130-MY2 and 113-2218-E-011-002)the support from Intelligent Manufactur-ing Innovation Center(IMIC),National Taiwan University of Science and Technology(NTUST),Taipei,Taiwan.
文摘Accurate photovoltaic(PV)power generation forecasting is essential for the efficient integration of renewable energy into power grids.However,the nonlinear and non-stationary characteristics of PV power signals,driven by fluctuating weather conditions,pose significant challenges for reliable prediction.This study proposes a DOEP(Decomposition–Optimization–Error Correction–Prediction)framework,a hybrid forecasting approach that integrates adaptive signal decomposition,machine learning,metaheuristic optimization,and error correction.The PV power signal is first decomposed using CEEMDAN to extract multi-scale temporal features.Subsequently,the hyperparameters and window sizes of the LSSVM are optimized using a Segment-based EBQPSO strategy.The main novelty of the proposed DOEP framework lies in the incorporation of Segment-based EBQPSO as a structured optimization mechanism that balances elite exploitation and population diversity during LSSVM tuning within the CEEMDAN-based forecasting pipeline.This strategy effectively mitigates convergence instability and sensitivity to initialization,which are common limitations in existing hybrid PV forecasting models.Each IMF is then predicted individually and aggregated to generate an initial forecast.In the error-correction stage,the residual error series is modeled using LSTM,and the final prediction is obtained by combining the initial forecast with the predicted error component.The proposed framework is evaluated using two PV power plant datasets with different levels of complexity.The results demonstrate that DOEP consistently outperforms benchmark models across multiple error-based and goodness-of-fit metrics,achieving MSE reductions of approximately 15%–60%on the ResPV-BDG dataset and 37%–92%on the NREL dataset.Analyses of predicted vs.observed values and residual distributions further confirm the superior calibration and robustness of the proposed approach.Although the DOEP framework entails higher computational costs than single model methods,it delivers significantly improved accuracy and stability for PV power forecasting under complex operating conditions.
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funding support from the National Science and Technology Council(NSTC),under Grant No.114-2410-H-011-026-MY3.
文摘Small datasets are often challenging due to their limited sample size.This research introduces a novel solution to these problems:average linkage virtual sample generation(ALVSG).ALVSG leverages the underlying data structure to create virtual samples,which can be used to augment the original dataset.The ALVSG process consists of two steps.First,an average-linkage clustering technique is applied to the dataset to create a dendrogram.The dendrogram represents the hierarchical structure of the dataset,with each merging operation regarded as a linkage.Next,the linkages are combined into an average-based dataset,which serves as a new representation of the dataset.The second step in the ALVSG process involves generating virtual samples using the average-based dataset.The research project generates a set of 100 virtual samples by uniformly distributing them within the provided boundary.These virtual samples are then added to the original dataset,creating a more extensive dataset with improved generalization performance.The efficacy of the ALVSG approach is validated through resampling experiments and t-tests conducted on two small real-world datasets.The experiments are conducted on three forecasting models:the support vector machine for regression(SVR),the deep learning model(DL),and XGBoost.The results show that the ALVSG approach outperforms the baseline methods in terms of mean square error(MSE),root mean square error(RMSE),and mean absolute error(MAE).
基金funded by the National Key R&D Program of China(No.2022YFB3904402)the National Natural Science Foundation of China(Nos.42474037 and U2233217)。
文摘The Vertical Total Electron Content(VTEC)of the ionosphere is a crucial parameter for describing the distribution and dynamic changes within the ionosphere.The study utilizes Dual Hybrid Attentional UNet(DHA-UNet)model to achieve higher forecasting performance for global VTEC predictions under the condition of data acquisition delays.Initially,this study uses the first Hybrid Attentional UNet(HA-UNet)model to predict the intermediate missing data.The missing data are caused by delays in data processing,making the Global Ionosphere Map(GIM)for the current day unavailable.Subsequently,the predicted results from the first HA-UNet model are concatenated with the input data to serve as the input data for the second HA-UNet model,yielding the final prediction results.The performance of DHA-UNet model is then evaluated under varying solar and geomagnetic activity conditions.Evaluation results demonstrate that the DHA-UNet model exhibits higher forecasting accuracy and stability compared to commonly used temporal and spatiotemporal forecasting models.Compared to CODG VTEC,the DHA-UNet model achieves Mean Absolute Error(MAE)values of 2.60 TECU,3.07 TECU,3.78 TECU,and 6.45TECU during quiet,weak,moderate,and strong geomagnetic storm periods,respectively,in years of high solar activity.In years of low solar activity,the model achieves MAE values of 1.00 TECU,1.15 TECU,and 1.54 TECU during quiet,weak,and moderate geomagnetic storm periods,respectively.Even during strong geomagnetic storms,55%of the residuals from the DHA-UNet model fall within the-5.0 TECU to 5.0 TECU range,surpassing other commonly used models.Compared to the C1PG forecasting product,the DHA-UNet model shows particularly notable improvements in accuracy during the spring and winter seasons,as well as in mid-to high-latitude regions.
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supported by the National Key Research and Development Program Project(2023YFC3107804)Planning Fund Project of Humanities and Social Sciences Research of the Ministry of Education(24YJA880097)the Graduate Education Reform Project in North China University of Technology(217051360025XN095-17)。
文摘Marine forecasting is critical for navigation safety and disaster prevention.However,traditional ocean numerical forecasting models are often limited by substantial errors and inadequate capture of temporal-spatial features.To address the limitations,the paper proposes a TimeXer-based numerical forecast correction model optimized by an exogenous-variable attention mechanism.The model treats target forecast values as internal variables,and incorporates historical temporal-spatial data and seven-day numerical forecast results from traditional models as external variables based on the embedding strategy of TimeXer.Using a self-attention structure,the model captures correlations between exogenous variables and target sequences,explores intrinsic multi-dimensional relationships,and subsequently corrects endogenous variables with the mined exogenous features.The model’s performance is evaluated using metrics including MSE(Mean Squared Error),MAE(Mean Absolute Error),RMSE(Root Mean Square Error),MAPE(Mean Absolute Percentage Error),MSPE(Mean Square Percentage Error),and computational time,with TimeXer and PatchTST models serving as benchmarks.Experiment results show that the proposed model achieves lower errors and higher correction accuracy for both one-day and seven-day forecasts.
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 or supported by the National Natural Science Foundation of China(Nos.32371878,32001251)the Natural Science Foundation of Jiangsu Province(No.BK20200781)+1 种基金the Youth Science and Technology Talent Lifting Project of Jiangsu Province(No.JSTJ-2024-324)the Priority Academic Program Development of Jiangsu Higher Education Institutions(PAPD)。
文摘Temperate forests are vital for maintaining ecological security and regulating the global climate.Despite considerable controversy surrounding the biophysical impacts of temperate forests on mid-latitude temperatures,we analyzed the effects of forest cover change on local temperature using the Weather Research and Forecasting(WRF)model from 2010 to 2020 in the Greater and Lesser Khingan Mountains(GLKM),Northeastern China,and explored the related driving factors.The conversions between forest and open lands(i.e.,cropland and grassland)were predominant.During the growing season,the conversion of cropland and grassland to forest resulted in warming(0.38±0.10 and 0.41±0.09℃,respectively)in air temperature(Ta),while the reverse conversion caused cooling(-0.31 peratur±0.08 and e-0.24±0.07℃,respectively),which was less than the changes observed in land surface tem(LST).Conversion of forest to impervious land caused warming(1.16 the±0.11℃),and opposite conversion resulted in cooling(can-0.88 t±0.17℃).These results indicate that radiative effects like albedo and net radiation drive the signifi net warming effect from afforestation on open lands within the temperate forest ecoregion.Conversely,conversion to impervious land produced the most substantial net warming impacts,driven by non-radiative effects like sensible heat,latent heat,and ground heat flux(GH).In these conversions,temperature can indirectly influence precipitation(Pre)through vapor pressure deficit(VPD),and Pre can also indirectly affect temperature via evapotranspiration(ET).This study highlights the need to thoroughly understand the impacts of afforestation in temperate forests while avoiding deforestation to regulate the climate effectively.
基金supported by the Natural Science Foundation of Jiangsu Province,China(Grant No.BK20240937)the Natural Science Foundation of Shandong Province(Grant No.ZR2021QE187)+2 种基金the Shandong Higher Education“Young Entrepreneurship Talents Introduction and Cultivation Program”Project(Grant No.ZXQT20221228001)the Natural Science Foundation of China(Grant No.42502273)the Science and Technology Innovation Program of Hunan Province(Grant No.2022RC4028).
文摘1.Introduction Artificial intelligence(AI)is rapidly reshaping geoscience,from Earth observation interpretation and hazard forecasting to subsurface characterisation and Earth system modelling(Kochupillai et al.,2022;Sun et al.,2024).These capabilities emerge at a time when geoscientific evidence is increasingly informing high-stakes decisions about climate adaptation,resource development,and disaster risk reduction(McGovern et al.,2022).
文摘Climate model prediction has been improved by enhancing model resolution as well as the implementation of sophisticated physical parameterization and refinement of data assimilation systems[section 6.1 in Wang et al.(2025)].In relation to seasonal forecasting and climate projection in the East Asian summer monsoon season,proper simulation of the seasonal migration of rain bands by models is a challenging and limiting factor[section 7.1 in Wang et al.(2025)].
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.
文摘This study examines the track and intensity forecasts of two typical Bay of Bengal tropical cyclones(TC)ASANI and MOCHA.The analysis of various Numerical Weather Prediction(NWP)model forecasts[ECMWF(European Centre for Medium range Weather Forecast),NCEP(National Centers for Environmental Prediction),NCUM(National Centre for Medium Range Weather Forecast-Unified Model),IMD(India Meteorological Department),HWRF(Hurricane Weather Research and Forecasting)],MME(Multi-model Ensemble),SCIP(Statistical Cyclone Intensity Prediction)model,and OFCL(Official)forecasts shows that intensity forecasts of ASANI and track forecasts of MOCHA were reasonably good,but there were large errors and wide variation in track forecasts of ASANI and in intensity forecasts of MOCHA.Among all model forecasts,the track forecast errors of IMD model and MME were least in general for ASANI and MOCHA respectively.Also,the landfall point forecast errors of IMD were least for ASANI,and the MME and OFCL forecast errors were least for MOCHA.No model is found to be consistently better for landfall time forecast for ASANI,and the errors of ECMWF,IMD and HWRF were least and of same order for MOCHA.The intensity forecast errors of OFCL and SCIP were least for ASANI,and the forecast errors of HWRF,IMD,NCEP,SCIP and OFCL were comparable and least for MOCHA up to 48 h forecast and HWRF errors were least thereafter in general.The ECMWF model forecast errors for intensity were found to be highest for both the TCs.The results also show that although there is significant improvement of track forecasts and limited or no improvement of intensity forecast in previous decades but challenges still persists in real time forecasting of both track and intensity due to wide variation and inconsistency of model forecasts for different TC cases.
基金in part supported by the National Natural Science Foundation of China(Grant Nos.42288101,42405147 and 42475054)in part by the China National Postdoctoral Program for Innovative Talents(Grant No.BX20230071)。
文摘Conducting predictability studies is essential for tracing the source of forecast errors,which not only leads to the improvement of observation and forecasting systems,but also enhances the understanding of weather and climate phenomena.In the past few decades,dynamical numerical models have been the primary tools for predictability studies,achieving significant progress.Nowadays,with the advances in artificial intelligence(AI)techniques and accumulations of vast meteorological data,modeling weather and climate events using modern data-driven approaches is becoming trendy,where FourCastNet,Pangu-Weather,and GraphCast are successful pioneers.In this perspective article,we suggest AI models should not be limited to forecasting but be expanded to predictability studies,leveraging AI's advantages of high efficiency and self-contained optimization modules.To this end,we first remark that AI models should possess high simulation capability with fine spatiotemporal resolution for two kinds of predictability studies.AI models with high simulation capabilities comparable to numerical models can be considered to provide solutions to partial differential equations in a data-driven way.Then,we highlight several specific predictability issues with well-determined nonlinear optimization formulizations,which can be well-studied using AI models,holding significant scientific value.In addition,we advocate for the incorporation of AI models into the synergistic cycle of the cognition–observation–model paradigm.Comprehensive predictability studies have the potential to transform“big data”to“big and better data”and shift the focus from“AI for forecasts”to“AI for science”,ultimately advancing the development of the atmospheric and oceanic sciences.
基金sponsored by the National Natural Science Foun-dation of China(Grant No.42330111).
文摘In this article,our nonlinear theory and technology for reducing the uncertainties of high-impact ocean‒atmosphere event predictions,with the conditional nonlinear optimal perturbation(CNOP)method as its core,are reviewed,and the“spring predictability barrier”problem for El Nino‒Southern Oscillation events and targeted observation issues for tropical cyclone forecasts are taken as two representative examples.Nonlinear theory reveals that initial errors of particular spatial structures,environmental conditions,and nonlinear processes contribute to significant prediction errors,whereas nonlinear technology provides a pioneering approach for reducing observational and forecast errors via targeted observations through the application of the CNOP method.Follow-up research further validates the scientific rigor of the theory in revealing the nonlinear mechanism of significant prediction errors,and relevant practical field campaigns for targeted observations verify the effectiveness of the technology in reducing prediction uncertainties.The CNOP method has achieved international recognition;furthermore,its applications further extend to ensemble forecasts for weather and climate and further enrich the nonlinear technology for reducing prediction uncertainties.It is expected that this nonlinear theory and technology will play a considerably important role in reducing prediction uncertainties for high-impact weather and climate events.
基金supported by the National Key R&D Program of China(Grant No.2022YFC3005401)the National Natural Science Foundation of China(Grant No.52239009)。
文摘Accurate prediction of water level changes in reservoirs is crucial for optimizing the operation of reservoir projects and ensuring their safety.This study proposed a method for reservoir water level prediction based on CEEMDAN-FE and RUN-SVM-RBFNN algorithms.By integrating the adaptive complete ensemble empirical mode decomposition with adaptive noise(CEEMDAN)method and fuzzy entropy(FE)with the new and highly efficient Runge–Kuta optimizer(RUN),adaptive parameter optimization for the support vector machine(SVM)and radial basis function neural network(RBFNN)algorithms was achieved.Regression prediction was conducted on the two reconstructed sequences using SVM and RBFNN according to their respective features.This approach improved the accuracy and stability of predictions.In terms of accuracy,the combined model outperformed single models,with the determination coefficient,root mean square error,and mean absolute error values of 0.9975,0.2418 m,and 0.1616 m,respectively.In terms of stability,the model predicted more consistently in training and testing periods,with stable overall prediction accuracy and a better adaptive ability to complex datasets.The case study demonstrated that the combined prediction model effectively addressed the environmental factors affecting reservoir water levels,leveraged the strength of each predictive method,compensated for their limitations,and clarified the impacts of environmental factors on reservoir water levels.
基金supported by Yunnan Provincial Basic Research Project(202401AT070344,202301AT070443)National Natural Science Foundation of China(62263014,52207105)+1 种基金Yunnan Lancang-Mekong International Electric Power Technology Joint Laboratory(202203AP140001)Major Science and Technology Projects in Yunnan Province(202402AG050006).
文摘Accurate short-term wind power forecast technique plays a crucial role in maintaining the safety and economic efficiency of smart grids.Although numerous studies have employed various methods to forecast wind power,there remains a research gap in leveraging swarm intelligence algorithms to optimize the hyperparameters of the Transformer model for wind power prediction.To improve the accuracy of short-term wind power forecast,this paper proposes a hybrid short-term wind power forecast approach named STL-IAOA-iTransformer,which is based on seasonal and trend decomposition using LOESS(STL)and iTransformer model optimized by improved arithmetic optimization algorithm(IAOA).First,to fully extract the power data features,STL is used to decompose the original data into components with less redundant information.The extracted components as well as the weather data are then input into iTransformer for short-term wind power forecast.The final predicted short-term wind power curve is obtained by combining the predicted components.To improve the model accuracy,IAOA is employed to optimize the hyperparameters of iTransformer.The proposed approach is validated using real-generation data from different seasons and different power stations inNorthwest China,and ablation experiments have been conducted.Furthermore,to validate the superiority of the proposed approach under different wind characteristics,real power generation data fromsouthwestChina are utilized for experiments.Thecomparative results with the other six state-of-the-art prediction models in experiments show that the proposed model well fits the true value of generation series and achieves high prediction accuracy.
