复杂地形风电场流动具有强烈的非定常现象和多尺度特征,其准确模拟是风资源精细化评估的难点。为兼顾宏观中尺度大气环流和微观非定常流动细节,该文结合中尺度气象研究与预报(weather research and forecasting,WRF)模式和微尺度计算流...复杂地形风电场流动具有强烈的非定常现象和多尺度特征,其准确模拟是风资源精细化评估的难点。为兼顾宏观中尺度大气环流和微观非定常流动细节,该文结合中尺度气象研究与预报(weather research and forecasting,WRF)模式和微尺度计算流体动力学(computational fluid dynamics,CFD)技术,构建一套WRF-CFD模式耦合的复杂地形风电场非定常仿真方法。以国际经典案例Askervein山和Bolund岛为验证对象,研究复杂地形流场中平均风速和湍流强度的分布特征,并简要分析复杂地形中风力机布置策略。结果表明,基于WRF-CFD模式的数值模拟结果与实验观测值有较好的一致性,且优于中尺度数值模拟结果,在选取的特征点位置,风速绝对误差均在2 m/s以内。结果可为风力机的设计、布局、载荷评估及风电场运行控制提供一定参考。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
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
Deep learning-based methods have become alternatives to traditional numerical weather prediction systems,offering faster computation and the ability to utilize large historical datasets.However,the application of deep...Deep learning-based methods have become alternatives to traditional numerical weather prediction systems,offering faster computation and the ability to utilize large historical datasets.However,the application of deep learning to medium-range regional weather forecasting with limited data remains a significant challenge.In this work,three key solutions are proposed:(1)motivated by the need to improve model performance in data-scarce regional forecasting scenarios,the authors innovatively apply semantic segmentation models,to better capture spatiotemporal features and improve prediction accuracy;(2)recognizing the challenge of overfitting and the inability of traditional noise-based data augmentation methods to effectively enhance model robustness,a novel learnable Gaussian noise mechanism is introduced that allows the model to adaptively optimize perturbations for different locations,ensuring more effective learning;and(3)to address the issue of error accumulation in autoregressive prediction,as well as the challenge of learning difficulty and the lack of intermediate data utilization in one-shot prediction,the authors propose a cascade prediction approach that effectively resolves these problems while significantly improving model forecasting performance.The method achieves a competitive result in The East China Regional AI Medium Range Weather Forecasting Competition.Ablation experiments further validate the effectiveness of each component,highlighting their contributions to enhancing prediction performance.展开更多
Sustainable energy systems will entail a change in the carbon intensity projections,which should be carried out in a proper manner to facilitate the smooth running of the grid and reduce greenhouse emissions.The prese...Sustainable energy systems will entail a change in the carbon intensity projections,which should be carried out in a proper manner to facilitate the smooth running of the grid and reduce greenhouse emissions.The present article outlines the TransCarbonNet,a novel hybrid deep learning framework with self-attention characteristics added to the bidirectional Long Short-Term Memory(Bi-LSTM)network to forecast the carbon intensity of the grid several days.The proposed temporal fusion model not only learns the local temporal interactions but also the long-term patterns of the carbon emission data;hence,it is able to give suitable forecasts over a period of seven days.TransCarbonNet takes advantage of a multi-head self-attention element to identify significant temporal connections,which means the Bi-LSTM element calculates sequential dependencies in both directions.Massive tests on two actual data sets indicate much improved results in comparison with the existing results,with mean relative errors of 15.3 percent and 12.7 percent,respectively.The framework has given explicable weights of attention that reveal critical periods that influence carbon intensity alterations,and informed decisions on the management of carbon sustainability.The effectiveness of the proposed solution has been validated in numerous cases of operations,and TransCarbonNet is established to be an effective tool when it comes to carbon-friendly optimization of the grid.展开更多
Predicting the behavior of renewable energy systems requires models capable of generating accurate forecasts from limited historical data,a challenge that becomes especially pronounced when commissioning new facil-iti...Predicting the behavior of renewable energy systems requires models capable of generating accurate forecasts from limited historical data,a challenge that becomes especially pronounced when commissioning new facil-ities where operational records are scarce.This review aims to synthesize recent progress in data-efficient deep learning approaches for addressing such“cold-start”forecasting problems.It primarily covers three interrelated domains—solar photovoltaic(PV),wind power,and electrical load forecasting—where data scarcity and operational variability are most critical,while also including representative studies on hydropower and carbon emission prediction to provide a broader systems perspective.To this end,we examined trends from over 150 predominantly peer-reviewed studies published between 2019 and mid-2025,highlighting advances in zero-shot and few-shot meta-learning frameworks that enable rapid model adaptation with minimal labeled data.Moreover,transfer learning approaches combined with spatiotemporal graph neural networks have been employed to transfer knowledge from existing energy assets to new,data-sparse environments,effectively capturing hidden dependencies among geographic features,meteorological dynamics,and grid structures.Synthetic data generation has further proven valuable for expanding training samples and mitigating overfitting in cold-start scenarios.In addition,large language models and explainable artificial intelligence(XAI)—notably conversational XAI systems—have been used to interpret and communicate complex model behaviors in accessible terms,fostering operator trust from the earliest deployment stages.By consolidating methodological advances,unresolved challenges,and open-source resources,this review provides a coherent overview of deep learning strategies that can shorten the data-sparse ramp-up period of new energy infrastructures and accelerate the transition toward resilient,low-carbon electricity grids.展开更多
作为天气系统的主要组成部分,三维云仿真在军事、航空等领域都起着重要作用.目前主流的边界体积层次结构(Bounding Volume Hierarchy,BVH)在处理形状不均匀且体积较大的云时存在渲染效率低下的问题,为此提出一种基于优化BVH算法的云产...作为天气系统的主要组成部分,三维云仿真在军事、航空等领域都起着重要作用.目前主流的边界体积层次结构(Bounding Volume Hierarchy,BVH)在处理形状不均匀且体积较大的云时存在渲染效率低下的问题,为此提出一种基于优化BVH算法的云产品渲染方法.将WRF(Weather Research and Forecasting,天气研究与预报)模型网格点中的数据作为云基元,利用Z-order Hilbert曲线对其进行空间排序,结合云基元密度优化BVH算法,提高计算效率.提出ONS(Overlapping Node Sets,重叠节点结构)降低数据存取耗时.优化BVH算法能够减少不必要的光线和三角形面之间的相交测试次数,并解决边界体无效重叠问题.仿真实验显示,SAH(Surface Area Heuristic,表面积启发式)成本较同类最优算法可提升15.6%,EPO(Effective Partial Overlap,有效重叠部分)可提升10%,构建时间减少100%以上,在任意云场景中优化BVH算法的计算效率较同类算法都有显著提高,表明其能实现WRF云产品的快速渲染.展开更多
为提升低空风切变预报精度,本文综合运用欧洲中期天气预报中心第五代再分析资料[European Centre for Medium-Range Weather Forecasts(ECMWF)fifth-generation reanalysis data,ERA5]和美国国家环境预报中心(National Centers for Envi...为提升低空风切变预报精度,本文综合运用欧洲中期天气预报中心第五代再分析资料[European Centre for Medium-Range Weather Forecasts(ECMWF)fifth-generation reanalysis data,ERA5]和美国国家环境预报中心(National Centers for Environmental Prediction,NCEP)的FNL全球再分析资料(Final Operational Global Analysis)、先进星载热发射和反射辐射仪全球数字高程模型以及兰州中川机场的实况观测资料,采用中尺度数值天气预报模式(Weather Research and Forecasting Model,WRF)、WRF结合计算流体动力学(Computational Fluid Dynamics,CFD)方法、长短期神经网络(Long Short-Term Memory,LSTM)方法,对2021年4月15-16日兰州中川机场的两次风切变过程进行模拟分析。结果表明:(1)在小于1 km的网格中使用大涡模拟,WRF模式在单个站点风速模拟任务中表现更好,但在近地面水平风场风速模拟效果上,不如WRF模式结合计算流体力学模型方案;(2)对于飞机降落过程中遭遇的两次低空风切变的模拟,WRF-LES和WRF-CFD两种模式都可以模拟出第一次低空风切变,而第二次受传入模式的WRF风速数据值较小的影响,两种模式风速差都没有达到阈值,需要在后续工作中进一步验证;(3)低风速条件(6 m·s^(-1))下,基于LSTM的单变量风速预测模型平均绝对误差基本维持在0.59 m·s^(-1),能较好地把握不同地形与环流背景条件下风速变化的非线性关系,虽然受到WRF误差和观测要素不全的限制,多变量风速预测能在保证平均绝对百分比误差小于6.60%的情况下,以更高的计算效率和泛化能力实现风速预测。本文不仅验证了WRF-CFD和WRF-LES耦合方案在风场和低空风切变预报中的差异,还探讨了基于LSTM的风速预测的可行性和准确性,期望为提高风场模拟精度,缩短精细风场模拟时间提供新的视角和方法。展开更多
A new method for driving a One-Dimensional Stratiform Cold （1DSC） cloud model with Weather Research and Fore casting （WRF） model outputs was developed by conducting numerical experiments for a typical large-scale ...A new method for driving a One-Dimensional Stratiform Cold （1DSC） cloud model with Weather Research and Fore casting （WRF） model outputs was developed by conducting numerical experiments for a typical large-scale stratiform rainfall event that took place on 4-5 July 2004 in Changchun, China. Sensitivity test results suggested that, with hydrometeor pro files extracted from the WRF outputs as the initial input, and with continuous updating of soundings and vertical velocities （including downdraft） derived from the WRF model, the new WRF-driven 1DSC modeling system （WRF-1DSC） was able to successfully reproduce both the generation and dissipation processes of the precipitation event. The simulated rainfall intensity showed a time-lag behind that observed, which could have been caused by simulation errors of soundings, vertical velocities and hydrometeor profiles in the WRF output. Taking into consideration the simulated and observed movement path of the precipitation system, a nearby grid point was found to possess more accurate environmental fields in terms of their similarity to those observed in Changchun Station. Using profiles from this nearby grid point, WRF-1DSC was able to repro duce a realistic precipitation pattern. This study demonstrates that 1D cloud-seeding models do indeed have the potential to predict realistic precipitation patterns when properly driven by accurate atmospheric profiles derived from a regional short range forecasting system, This opens a novel and important approach to developing an ensemble-based rain enhancement prediction and operation system under a probabilistic framework concept.展开更多
This paper evaluates the skills of physical Parameterization schemes in simulating extreme rainfall events over Dar es Salaam Region, Tanzania using the Weather Research and Forecasting (WRF) model. The model skill is...This paper evaluates the skills of physical Parameterization schemes in simulating extreme rainfall events over Dar es Salaam Region, Tanzania using the Weather Research and Forecasting (WRF) model. The model skill is determined during the 21 December 2011 flooding event. Ten sensitivity experiments have been conducted using Cumulus, Convective and Planetary boundary layer schemes to find the best combination and optimize the WRF model for the study area for heavy rainfall events. Model simulation results were verified against observed data using standard statistical tests. The model simulations show encouraging and better statistical results with the combination of Kain-Fritsch cumulus parameterization scheme, Lin microphysics scheme and Asymmetric Convection Model 2 (ACM2) planetary boundary scheme than any other combinations of physical parameterization schemes over Dar es Salaam region.展开更多
This paper investigates the accuracy of weather research and forecasting by improving coding for solar radiation forecasting for location in Dili Timor Leste. Weather Research and Forecasting (WRF) model version 3.9.1...This paper investigates the accuracy of weather research and forecasting by improving coding for solar radiation forecasting for location in Dili Timor Leste. Weather Research and Forecasting (WRF) model version 3.9.1 is used in this study for improvement purposes. The shortwave coding of WRF is used to improve in order to decrease error simulation. The importance of improving WRF coding at a specific region will reduce the bias and root mean square root when comparing to the observed data. This study uses high resolution based on the WRF modeling to stabilize the performance of forecasting. The decrease in error performance will be expected to enhance the value of renewable energy. The results show the root mean square error of the WRF default is 233 W/m<sup>2</sup> higher compared to 205 W/m<sup>2</sup> from the WRF improvement model. In addition, the Mean Bias Error (MBE) of the WRF default is obtained value 0.06 higher than 0.03 from the WRF improvement in rainy days. Meanwhile, on sunny days, the performance Root Mean Square Error (RMSE) of WRF default is 327 W/m<sup>2</sup> higher than 223 W/m<sup>2</sup> from the WRF improvement. The MBE of WRF improvement obtained 0.13 lower compared to 0.21 of WRF default coding. Finally, this study concludes that improving the shortwave code under the WRF model can decrease the error performance of the WRF simulation for local weather forecasting</span></span><span style="font-family:Verdana;">.展开更多
A study of a combination of Weather Research and Forecasting (WRF) model and Long Short Term Memory (LSTM) network for location in Dili Timor Leste is introduced in this paper. One calendar year’s results of solar ra...A study of a combination of Weather Research and Forecasting (WRF) model and Long Short Term Memory (LSTM) network for location in Dili Timor Leste is introduced in this paper. One calendar year’s results of solar radiation from January to December 2014 are used as input data to estimate future forecasting of solar radiation using the LSTM network for three months period. The WRF model version 3.9.1 is used to simulate one year’s solar radiation in horizontal resolution low scale for nesting domain 1</span><span style="font-family:""> </span><span style="font-family:Verdana;">×</span><span style="font-family:""> </span><span style="font-family:Verdana;">1 km. It is done by applying 6-hourly interval 1</span><span style="font-family:Verdana;">º</span><span style="font-family:""> </span><span style="font-family:""><span style="font-family:Verdana;">×</span><span style="font-family:Verdana;"> 1</span></span><span style="font-family:Verdana;">º</span><span style="font-family:""><span style="font-family:Verdana;"> NCEP FNL analysis data used as Global Forecast System (GFS). LSTM network is applied for forecasting in numerous learning problems for solar radiation forecasting. LSTM network uses two-layer LSTM architecture of 512 hidden neurons coupled with a dense output layer with linear as the model activation to predict with time steps are configured to 50 and the number of features is 1. The maximum epoch is set to 325 with batch size 300 and the validation split is 0.09. The results demonstrate that the combination of these two methods can successfully predict solar radiation where four error metrics of mean bias error (MBE), root mean square error (RMSE), normalized MBE (nMBE), and normalized RMSE (nRMSE) perform small error distribution and percentage in three months prediction where the error percentage is obtained below the 20% for nMBE and nRMSE. Meanwhile, the error distribution of RMSE is obtained below 200 W/m</span><sup><span style="font-family:Verdana;">2</span></sup><span style="font-family:Verdana;"> and maximum bias error is 0.07. Finally, the values of MBE, RMSE, nMBE, and nRMSE conclude that the good performance of the combination of two methods in this study can be applied to simulate any other weather variable for local necessary.展开更多
文摘复杂地形风电场流动具有强烈的非定常现象和多尺度特征,其准确模拟是风资源精细化评估的难点。为兼顾宏观中尺度大气环流和微观非定常流动细节,该文结合中尺度气象研究与预报(weather research and forecasting,WRF)模式和微尺度计算流体动力学(computational fluid dynamics,CFD)技术,构建一套WRF-CFD模式耦合的复杂地形风电场非定常仿真方法。以国际经典案例Askervein山和Bolund岛为验证对象,研究复杂地形流场中平均风速和湍流强度的分布特征,并简要分析复杂地形中风力机布置策略。结果表明,基于WRF-CFD模式的数值模拟结果与实验观测值有较好的一致性,且优于中尺度数值模拟结果,在选取的特征点位置,风速绝对误差均在2 m/s以内。结果可为风力机的设计、布局、载荷评估及风电场运行控制提供一定参考。
基金Science and Technology Development Program of the“Taihu Light”(K20231023)CMA Numerical Weather Prediction R&D Project(TCYF2024QH007)+1 种基金“Qing Lan”Project of Jiangsu Province for C.H.LUWuxi University Research Start-up Fund for Introduced Talents(2023r037)。
文摘Since the initiation of the subseasonal-to-seasonal prediction project by the World Meteorological Organization,the accuracy of model forecasts has improved notably.However,substantial discrepancies have been observed among forecast results produced by different ensemble members when applied to South China.To enhance the accuracy of sub-seasonal forecasts in this region,it is essential to develop new methods that can effectively leverage multiple predictive models.This study introduces a weighted ensemble forecasting method based on online learning to improve forecast accuracy.We utilized ensemble forecasts from three models:the Integrated Forecasting System model from the European Centre for Medium-Range Weather Forecasts,the Climate Forecast System Version 2 model from the National Centers for Environmental Prediction,and the Beijing Climate Center-Climate Prediction System version 3 model from the China Meteorological Administration.The ensemble weights are trained using an online learning approach.The results indicate that the forecasts obtained through online learning outperform those of the original dynamical models.Compared to the simple ensemble results of the three models,the weighted ensemble model showed a stronger capability to capture temperature and precipitation patterns in South China.Therefore,this method has the potential to improve the accuracy of sub-seasonal forecasts in this region.
基金supported by the National Natural Science Foundation of China(No.52171284)。
文摘Wind speed is a crucial parameter affecting wind energy utilization.However,its volatility leads to time-varying power output.Herein,a novel Seq2Seq model integrating deep learning,data denoising,and a shape-aware loss function is proposed for accurate multistep wind speed forecasting.In this model,the wind speed data is first denoised using the maximal overlap discrete wavelet transform.Next,an encoder-decoder network based on a temporal convolutional network,bidirectional gated recurrent unit,and multihead self-attention is employed for forecasting.Additionally,to enhance the ability of the model to identify temporal dynamics,a shape-aware loss function,ITILDE-Q,is employed in the model.To verify the effectiveness of the proposed model,a comparative experiment and an ablation experiment were conducted using three datasets of measured wind speeds.Three error metrics and a similarity metric were adopted for comprehensive evaluation.The experimental results showed that the proposed model consistently outperforms benchmark models in all tested forecasting scenarios,with particularly pronounced differences in performance over longer forecast horizons.Furthermore,the synergistic interaction of the three key components contributes to the extraordinary performance of the proposed model.
基金supported by the Academic Research Projects of Beijing Union University(ZK20202204)the National Natural Science Foundation of China(12250005,12073040,12273059,11973056,12003051,11573037,12073041,11427901,11572005,11611530679 and 12473052)+1 种基金the Strategic Priority Research Program of the China Academy of Sciences(XDB0560000,XDA15052200,XDB09040200,XDA15010700,XDB0560301,and XDA15320102)the Chinese Meridian Project(CMP).
文摘The solar cycle(SC),a phenomenon caused by the quasi-periodic regular activities in the Sun,occurs approximately every 11 years.Intense solar activity can disrupt the Earth’s ionosphere,affecting communication and navigation systems.Consequently,accurately predicting the intensity of the SC holds great significance,but predicting the SC involves a long-term time series,and many existing time series forecasting methods have fallen short in terms of accuracy and efficiency.The Time-series Dense Encoder model is a deep learning solution tailored for long time series prediction.Based on a multi-layer perceptron structure,it outperforms the best previously existing models in accuracy,while being efficiently trainable on general datasets.We propose a method based on this model for SC forecasting.Using a trained model,we predict the test set from SC 19 to SC 25 with an average mean absolute percentage error of 32.02,root mean square error of 30.3,mean absolute error of 23.32,and R^(2)(coefficient of determination)of 0.76,outperforming other deep learning models in terms of accuracy and training efficiency on sunspot number datasets.Subsequently,we use it to predict the peaks of SC 25 and SC 26.For SC 25,the peak time has ended,but a stronger peak is predicted for SC 26,of 199.3,within a range of 170.8-221.9,projected to occur during April 2034.
文摘Accurate short-term electricity price forecasts are essential for market participants to optimize bidding strategies,hedge risk and plan generation schedules.By leveraging advanced data analytics and machine learning methods,accurate and reliable price forecasts can be achieved.This study forecasts day-ahead prices in Türkiye’s electricity market using eXtreme Gradient Boosting(XGBoost).We benchmark XGBoost against four alternatives—Support Vector Machines(SVM),Long Short-Term Memory(LSTM),Random Forest(RF),and Gradient Boosting(GBM)—using 8760 hourly observations from 2023 provided by Energy Exchange Istanbul(EXIST).All models were trained on an identical chronological 80/20 train–test split,with hyperparameters tuned via 5-fold cross-validation on the training set.XGBoost achieved the best performance(Mean Absolute Error(MAE)=144.8 TRY/MWh,Root Mean Square Error(RMSE)=201.8 TRY/MWh,coefficient of determination(R^(2))=0.923)while training in 94 s.To enhance interpretability and identify key drivers,we employed Shapley Additive Explanations(SHAP),which highlighted a strong association between higher prices and increased natural-gas-based generation.The results provide a clear performance benchmark and practical guidance for selecting forecasting approaches in day-ahead electricity markets.
基金supported by the National Natural Science Foundation of China[grant number 62376217]the Young Elite Scientists Sponsorship Program by CAST[grant number 2023QNRC001]the Joint Research Project for Meteorological Capacity Improvement[grant number 24NLTSZ003]。
文摘Deep learning-based methods have become alternatives to traditional numerical weather prediction systems,offering faster computation and the ability to utilize large historical datasets.However,the application of deep learning to medium-range regional weather forecasting with limited data remains a significant challenge.In this work,three key solutions are proposed:(1)motivated by the need to improve model performance in data-scarce regional forecasting scenarios,the authors innovatively apply semantic segmentation models,to better capture spatiotemporal features and improve prediction accuracy;(2)recognizing the challenge of overfitting and the inability of traditional noise-based data augmentation methods to effectively enhance model robustness,a novel learnable Gaussian noise mechanism is introduced that allows the model to adaptively optimize perturbations for different locations,ensuring more effective learning;and(3)to address the issue of error accumulation in autoregressive prediction,as well as the challenge of learning difficulty and the lack of intermediate data utilization in one-shot prediction,the authors propose a cascade prediction approach that effectively resolves these problems while significantly improving model forecasting performance.The method achieves a competitive result in The East China Regional AI Medium Range Weather Forecasting Competition.Ablation experiments further validate the effectiveness of each component,highlighting their contributions to enhancing prediction performance.
基金funded by the Deanship of Scientific Research and Libraries at Princess Nourah bint Abdulrahman University,through the“Nafea”Program,Grant No.(NP-45-082).
文摘Sustainable energy systems will entail a change in the carbon intensity projections,which should be carried out in a proper manner to facilitate the smooth running of the grid and reduce greenhouse emissions.The present article outlines the TransCarbonNet,a novel hybrid deep learning framework with self-attention characteristics added to the bidirectional Long Short-Term Memory(Bi-LSTM)network to forecast the carbon intensity of the grid several days.The proposed temporal fusion model not only learns the local temporal interactions but also the long-term patterns of the carbon emission data;hence,it is able to give suitable forecasts over a period of seven days.TransCarbonNet takes advantage of a multi-head self-attention element to identify significant temporal connections,which means the Bi-LSTM element calculates sequential dependencies in both directions.Massive tests on two actual data sets indicate much improved results in comparison with the existing results,with mean relative errors of 15.3 percent and 12.7 percent,respectively.The framework has given explicable weights of attention that reveal critical periods that influence carbon intensity alterations,and informed decisions on the management of carbon sustainability.The effectiveness of the proposed solution has been validated in numerous cases of operations,and TransCarbonNet is established to be an effective tool when it comes to carbon-friendly optimization of the grid.
文摘Predicting the behavior of renewable energy systems requires models capable of generating accurate forecasts from limited historical data,a challenge that becomes especially pronounced when commissioning new facil-ities where operational records are scarce.This review aims to synthesize recent progress in data-efficient deep learning approaches for addressing such“cold-start”forecasting problems.It primarily covers three interrelated domains—solar photovoltaic(PV),wind power,and electrical load forecasting—where data scarcity and operational variability are most critical,while also including representative studies on hydropower and carbon emission prediction to provide a broader systems perspective.To this end,we examined trends from over 150 predominantly peer-reviewed studies published between 2019 and mid-2025,highlighting advances in zero-shot and few-shot meta-learning frameworks that enable rapid model adaptation with minimal labeled data.Moreover,transfer learning approaches combined with spatiotemporal graph neural networks have been employed to transfer knowledge from existing energy assets to new,data-sparse environments,effectively capturing hidden dependencies among geographic features,meteorological dynamics,and grid structures.Synthetic data generation has further proven valuable for expanding training samples and mitigating overfitting in cold-start scenarios.In addition,large language models and explainable artificial intelligence(XAI)—notably conversational XAI systems—have been used to interpret and communicate complex model behaviors in accessible terms,fostering operator trust from the earliest deployment stages.By consolidating methodological advances,unresolved challenges,and open-source resources,this review provides a coherent overview of deep learning strategies that can shorten the data-sparse ramp-up period of new energy infrastructures and accelerate the transition toward resilient,low-carbon electricity grids.
文摘作为天气系统的主要组成部分,三维云仿真在军事、航空等领域都起着重要作用.目前主流的边界体积层次结构(Bounding Volume Hierarchy,BVH)在处理形状不均匀且体积较大的云时存在渲染效率低下的问题,为此提出一种基于优化BVH算法的云产品渲染方法.将WRF(Weather Research and Forecasting,天气研究与预报)模型网格点中的数据作为云基元,利用Z-order Hilbert曲线对其进行空间排序,结合云基元密度优化BVH算法,提高计算效率.提出ONS(Overlapping Node Sets,重叠节点结构)降低数据存取耗时.优化BVH算法能够减少不必要的光线和三角形面之间的相交测试次数,并解决边界体无效重叠问题.仿真实验显示,SAH(Surface Area Heuristic,表面积启发式)成本较同类最优算法可提升15.6%,EPO(Effective Partial Overlap,有效重叠部分)可提升10%,构建时间减少100%以上,在任意云场景中优化BVH算法的计算效率较同类算法都有显著提高,表明其能实现WRF云产品的快速渲染.
文摘为提升低空风切变预报精度,本文综合运用欧洲中期天气预报中心第五代再分析资料[European Centre for Medium-Range Weather Forecasts(ECMWF)fifth-generation reanalysis data,ERA5]和美国国家环境预报中心(National Centers for Environmental Prediction,NCEP)的FNL全球再分析资料(Final Operational Global Analysis)、先进星载热发射和反射辐射仪全球数字高程模型以及兰州中川机场的实况观测资料,采用中尺度数值天气预报模式(Weather Research and Forecasting Model,WRF)、WRF结合计算流体动力学(Computational Fluid Dynamics,CFD)方法、长短期神经网络(Long Short-Term Memory,LSTM)方法,对2021年4月15-16日兰州中川机场的两次风切变过程进行模拟分析。结果表明:(1)在小于1 km的网格中使用大涡模拟,WRF模式在单个站点风速模拟任务中表现更好,但在近地面水平风场风速模拟效果上,不如WRF模式结合计算流体力学模型方案;(2)对于飞机降落过程中遭遇的两次低空风切变的模拟,WRF-LES和WRF-CFD两种模式都可以模拟出第一次低空风切变,而第二次受传入模式的WRF风速数据值较小的影响,两种模式风速差都没有达到阈值,需要在后续工作中进一步验证;(3)低风速条件(6 m·s^(-1))下,基于LSTM的单变量风速预测模型平均绝对误差基本维持在0.59 m·s^(-1),能较好地把握不同地形与环流背景条件下风速变化的非线性关系,虽然受到WRF误差和观测要素不全的限制,多变量风速预测能在保证平均绝对百分比误差小于6.60%的情况下,以更高的计算效率和泛化能力实现风速预测。本文不仅验证了WRF-CFD和WRF-LES耦合方案在风场和低空风切变预报中的差异,还探讨了基于LSTM的风速预测的可行性和准确性,期望为提高风场模拟精度,缩短精细风场模拟时间提供新的视角和方法。
基金jointly supported by the Main Direction Program of Knowledge Innovation of the Chinese Academy of Sciences(Grant No.KZCX2EW203)the National Key Basic Research Program of China(Grant No.2013CB430105)the National Department of Public Benefit Research Foundation(Grant No.GYHY201006031)
文摘A new method for driving a One-Dimensional Stratiform Cold （1DSC） cloud model with Weather Research and Fore casting （WRF） model outputs was developed by conducting numerical experiments for a typical large-scale stratiform rainfall event that took place on 4-5 July 2004 in Changchun, China. Sensitivity test results suggested that, with hydrometeor pro files extracted from the WRF outputs as the initial input, and with continuous updating of soundings and vertical velocities （including downdraft） derived from the WRF model, the new WRF-driven 1DSC modeling system （WRF-1DSC） was able to successfully reproduce both the generation and dissipation processes of the precipitation event. The simulated rainfall intensity showed a time-lag behind that observed, which could have been caused by simulation errors of soundings, vertical velocities and hydrometeor profiles in the WRF output. Taking into consideration the simulated and observed movement path of the precipitation system, a nearby grid point was found to possess more accurate environmental fields in terms of their similarity to those observed in Changchun Station. Using profiles from this nearby grid point, WRF-1DSC was able to repro duce a realistic precipitation pattern. This study demonstrates that 1D cloud-seeding models do indeed have the potential to predict realistic precipitation patterns when properly driven by accurate atmospheric profiles derived from a regional short range forecasting system, This opens a novel and important approach to developing an ensemble-based rain enhancement prediction and operation system under a probabilistic framework concept.
文摘This paper evaluates the skills of physical Parameterization schemes in simulating extreme rainfall events over Dar es Salaam Region, Tanzania using the Weather Research and Forecasting (WRF) model. The model skill is determined during the 21 December 2011 flooding event. Ten sensitivity experiments have been conducted using Cumulus, Convective and Planetary boundary layer schemes to find the best combination and optimize the WRF model for the study area for heavy rainfall events. Model simulation results were verified against observed data using standard statistical tests. The model simulations show encouraging and better statistical results with the combination of Kain-Fritsch cumulus parameterization scheme, Lin microphysics scheme and Asymmetric Convection Model 2 (ACM2) planetary boundary scheme than any other combinations of physical parameterization schemes over Dar es Salaam region.
文摘This paper investigates the accuracy of weather research and forecasting by improving coding for solar radiation forecasting for location in Dili Timor Leste. Weather Research and Forecasting (WRF) model version 3.9.1 is used in this study for improvement purposes. The shortwave coding of WRF is used to improve in order to decrease error simulation. The importance of improving WRF coding at a specific region will reduce the bias and root mean square root when comparing to the observed data. This study uses high resolution based on the WRF modeling to stabilize the performance of forecasting. The decrease in error performance will be expected to enhance the value of renewable energy. The results show the root mean square error of the WRF default is 233 W/m<sup>2</sup> higher compared to 205 W/m<sup>2</sup> from the WRF improvement model. In addition, the Mean Bias Error (MBE) of the WRF default is obtained value 0.06 higher than 0.03 from the WRF improvement in rainy days. Meanwhile, on sunny days, the performance Root Mean Square Error (RMSE) of WRF default is 327 W/m<sup>2</sup> higher than 223 W/m<sup>2</sup> from the WRF improvement. The MBE of WRF improvement obtained 0.13 lower compared to 0.21 of WRF default coding. Finally, this study concludes that improving the shortwave code under the WRF model can decrease the error performance of the WRF simulation for local weather forecasting</span></span><span style="font-family:Verdana;">.
文摘A study of a combination of Weather Research and Forecasting (WRF) model and Long Short Term Memory (LSTM) network for location in Dili Timor Leste is introduced in this paper. One calendar year’s results of solar radiation from January to December 2014 are used as input data to estimate future forecasting of solar radiation using the LSTM network for three months period. The WRF model version 3.9.1 is used to simulate one year’s solar radiation in horizontal resolution low scale for nesting domain 1</span><span style="font-family:""> </span><span style="font-family:Verdana;">×</span><span style="font-family:""> </span><span style="font-family:Verdana;">1 km. It is done by applying 6-hourly interval 1</span><span style="font-family:Verdana;">º</span><span style="font-family:""> </span><span style="font-family:""><span style="font-family:Verdana;">×</span><span style="font-family:Verdana;"> 1</span></span><span style="font-family:Verdana;">º</span><span style="font-family:""><span style="font-family:Verdana;"> NCEP FNL analysis data used as Global Forecast System (GFS). LSTM network is applied for forecasting in numerous learning problems for solar radiation forecasting. LSTM network uses two-layer LSTM architecture of 512 hidden neurons coupled with a dense output layer with linear as the model activation to predict with time steps are configured to 50 and the number of features is 1. The maximum epoch is set to 325 with batch size 300 and the validation split is 0.09. The results demonstrate that the combination of these two methods can successfully predict solar radiation where four error metrics of mean bias error (MBE), root mean square error (RMSE), normalized MBE (nMBE), and normalized RMSE (nRMSE) perform small error distribution and percentage in three months prediction where the error percentage is obtained below the 20% for nMBE and nRMSE. Meanwhile, the error distribution of RMSE is obtained below 200 W/m</span><sup><span style="font-family:Verdana;">2</span></sup><span style="font-family:Verdana;"> and maximum bias error is 0.07. Finally, the values of MBE, RMSE, nMBE, and nRMSE conclude that the good performance of the combination of two methods in this study can be applied to simulate any other weather variable for local necessary.
