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
Accurate short-term forecast of offshore wind fields is still challenging for numerical weather prediction models.Based on three years of 48-hour forecast data from the European Centre for Medium-Range Weather Forecas...Accurate short-term forecast of offshore wind fields is still challenging for numerical weather prediction models.Based on three years of 48-hour forecast data from the European Centre for Medium-Range Weather Forecasts Integrated Forecasting System global model(ECMWF-IFS)over 14 offshore weather stations along the coast of Shandong Province,this study introduces a multi-task learning(MTL)model(TabNet-MTL),which significantly improves the forecast bias of near-surface wind direction and speed simultaneously.TabNet-MTL adopts the feature engineering method,utilizes mean square error as the loss function,and employs the 5-fold cross validation method to ensure the generalization ability of the trained model.It demonstrates superior skills in wind field correction across different forecast lead times over all stations compared to its single-task version(TabNet-STL)and three other popular single-task learning models(Random Forest,LightGBM,and XGBoost).Results show that it significantly reduces root mean square error of the ECMWF-IFS wind speed forecast from 2.20 to 1.25 m s−1,and increases the forecast accuracy of wind direction from 50%to 65%.As an explainable deep learning model,the weather stations and long-term temporal statistics of near-surface wind speed are identified as the most influential variables for TabNet-MTL in constructing its feature engineering.展开更多
Post-processing correction is an effective way to improve the model forecasting result. Especially, the machine learning methods have played increasingly important roles in recent years. Taking the meteorological obse...Post-processing correction is an effective way to improve the model forecasting result. Especially, the machine learning methods have played increasingly important roles in recent years. Taking the meteorological observational data in a period of two years as the reference, the maximum and minimum temperature predictions of Shenyang station from the European Center for Medium-Range Weather Forecasts (ECMWF) and national intelligent grid forecasts are objectively corrected by using wavelet analysis, sliding training and other technologies. The evaluation results show that the sliding training time window of the maximum temperature is smaller than that of the minimum temperature, and their difference is the largest in August, with a difference of 2.6 days. The objective correction product of maximum temperature shows a good performance in spring, while that of minimum temperature performs well throughout the whole year, with an accuracy improvement of 97% to 186%. The correction effect in the central plains is better than in the regions with complex terrain. As for the national intelligent grid forecasts, the objective correction products have shown positive skills in predicting the maximum temperatures in spring (the skill-score reaches 0.59) and in predicting the minimum temperature at most times of the year (the skill-score reaches 0.68).展开更多
This paper presents a new multiple linear regression（MLR） approach to updating the hourly, extrapolated precipitation forecasts generated by the INCA（Integrated Nowcasting through Comprehensive Analysis） system fo...This paper presents a new multiple linear regression（MLR） approach to updating the hourly, extrapolated precipitation forecasts generated by the INCA（Integrated Nowcasting through Comprehensive Analysis） system for the Eastern Alps.The generalized form of the model approximates the updated precipitation forecast as a linear response to combinations of predictors selected through a backward elimination algorithm from a pool of predictors. The predictors comprise the raw output of the extrapolated precipitation forecast, the latest radar observations, the convective analysis, and the precipitation analysis. For every MLR model, bias and distribution correction procedures are designed to further correct the systematic regression errors. Applications of the MLR models to a verification dataset containing two months of qualified samples,and to one-month gridded data, are performed and evaluated. Generally, MLR yields slight, but definite, improvements in the intensity accuracy of forecasts during the late evening to morning period, and significantly improves the forecasts for large thresholds. The structure-amplitude-location scores, used to evaluate the performance of the MLR approach,based on its simulation of morphological features, indicate that MLR typically reduces the overestimation of amplitudes and generates similar horizontal structures in precipitation patterns and slightly degraded location forecasts, when compared with the extrapolated nowcasting.展开更多
Severe precipitation ranks among the most impactful meteorological disasters,exerting profound social and economic consequences.Forecasting heavy rainfall on an hourly scale,driven by complex multi-scale thermodynamic...Severe precipitation ranks among the most impactful meteorological disasters,exerting profound social and economic consequences.Forecasting heavy rainfall on an hourly scale,driven by complex multi-scale thermodynamic processes,remains a formidable challenge in numerical weather prediction(NWP).This study introduces a deeplearning-based fusion rain network(FRNet)designed to improve intense rainfall forecasting by effectively integrating the strengths of multi-scale model rain features.The model's performance in 3-h rainfall forecasts within a 24-h lead time over North China was comprehensively validated.Statistical assessments,based on independent tests conducted for 2021 and 2022,demonstrated FRNet's robust generalization capability.The results of the evaluations reveal that the deep learning model significantly enhances forecast accuracy across various precipitation thresholds—ranging from light to torrential rain—across all lead times within the 24-h period,when compared with the original model forecasts and the traditional multi-model similarity ensemble correction method.Notably,improvements become more pronounced with increasing precipitation intensity.Case studies of typical intense rainfall events have illustrated that FRNet effectively synthesizes the strengths of global models in predicting rainband location and movement,as well as mesoscale numerical models in forecasting intensity and fine-scale structures.This integration results in a more comprehensive and precise adjustment of precipitation forecasts,offering superior guidance for intense rainfall events compared to any single numerical model.Structure–amplitude–location(SAL)verification shows that FRNet significantly adjusts the structure and location of heavy precipitation but shows overestimation at the same time.Ablation experiments confirm that the performance gains of FRNet are primarily driven by the inclusion of high-resolution global and mesoscale model forecasts,complemented by geographic and temporal information.This study underscores the potential of deep learning techniques to integrate more multi-scale physical and observational features from different sources,paving the way for future advancements in intense rainfall forecasting.展开更多
This paper presents a new correction method, "instant correction method(ICM)", to improve the accuracy of numerical prediction products(NPP) and provide weather variables at grid cells. The ICM makes use of ...This paper presents a new correction method, "instant correction method(ICM)", to improve the accuracy of numerical prediction products(NPP) and provide weather variables at grid cells. The ICM makes use of the continuity in time of the forecast errors at different forecast times to improve the accuracy of large scale NPP. To apply the ICM in China, an ensemble correction scheme is designed to correct the T213 NPP(the most popular NPP in China) through different statistical methods. The corrected T213 NPP(ICM T213 NPP) are evaluated by four popular indices: Correlation coefficient, climate anomalies correlation coefficient, root-mean-square-errors(RMSE), and confidence intervals(CI). The results show that the ICM T213 NPP are more accurate than the original T213 NPP in both the training period(2003–2008) and the validation period(2009–2010). Applications in China over the past three years indicate that the ICM is simple, fast, and reliable. Because of its low computing cost, end users in need of more accurate short-range weather forecasts around China can benefit greatly from the method.展开更多
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the National Key Research and Development Plan of China[Grant No.2023YFB3002400]the Shanghai 2021 Natural Science Foundation[Grant Nos.21ZR1420400 and 21ZR1419800]+1 种基金the Shanghai 2023 Natural Science Foundation[Grant No.23ZR1463000]the Shandong Provincial Meteorological Bureau Scientific Research Project[Grant No.2023SDBD05].
文摘Accurate short-term forecast of offshore wind fields is still challenging for numerical weather prediction models.Based on three years of 48-hour forecast data from the European Centre for Medium-Range Weather Forecasts Integrated Forecasting System global model(ECMWF-IFS)over 14 offshore weather stations along the coast of Shandong Province,this study introduces a multi-task learning(MTL)model(TabNet-MTL),which significantly improves the forecast bias of near-surface wind direction and speed simultaneously.TabNet-MTL adopts the feature engineering method,utilizes mean square error as the loss function,and employs the 5-fold cross validation method to ensure the generalization ability of the trained model.It demonstrates superior skills in wind field correction across different forecast lead times over all stations compared to its single-task version(TabNet-STL)and three other popular single-task learning models(Random Forest,LightGBM,and XGBoost).Results show that it significantly reduces root mean square error of the ECMWF-IFS wind speed forecast from 2.20 to 1.25 m s−1,and increases the forecast accuracy of wind direction from 50%to 65%.As an explainable deep learning model,the weather stations and long-term temporal statistics of near-surface wind speed are identified as the most influential variables for TabNet-MTL in constructing its feature engineering.
文摘Post-processing correction is an effective way to improve the model forecasting result. Especially, the machine learning methods have played increasingly important roles in recent years. Taking the meteorological observational data in a period of two years as the reference, the maximum and minimum temperature predictions of Shenyang station from the European Center for Medium-Range Weather Forecasts (ECMWF) and national intelligent grid forecasts are objectively corrected by using wavelet analysis, sliding training and other technologies. The evaluation results show that the sliding training time window of the maximum temperature is smaller than that of the minimum temperature, and their difference is the largest in August, with a difference of 2.6 days. The objective correction product of maximum temperature shows a good performance in spring, while that of minimum temperature performs well throughout the whole year, with an accuracy improvement of 97% to 186%. The correction effect in the central plains is better than in the regions with complex terrain. As for the national intelligent grid forecasts, the objective correction products have shown positive skills in predicting the maximum temperatures in spring (the skill-score reaches 0.59) and in predicting the minimum temperature at most times of the year (the skill-score reaches 0.68).
基金supported by Beijing Science & Technology Commission (Grant No. Z151100002115012)
文摘This paper presents a new multiple linear regression（MLR） approach to updating the hourly, extrapolated precipitation forecasts generated by the INCA（Integrated Nowcasting through Comprehensive Analysis） system for the Eastern Alps.The generalized form of the model approximates the updated precipitation forecast as a linear response to combinations of predictors selected through a backward elimination algorithm from a pool of predictors. The predictors comprise the raw output of the extrapolated precipitation forecast, the latest radar observations, the convective analysis, and the precipitation analysis. For every MLR model, bias and distribution correction procedures are designed to further correct the systematic regression errors. Applications of the MLR models to a verification dataset containing two months of qualified samples,and to one-month gridded data, are performed and evaluated. Generally, MLR yields slight, but definite, improvements in the intensity accuracy of forecasts during the late evening to morning period, and significantly improves the forecasts for large thresholds. The structure-amplitude-location scores, used to evaluate the performance of the MLR approach,based on its simulation of morphological features, indicate that MLR typically reduces the overestimation of amplitudes and generates similar horizontal structures in precipitation patterns and slightly degraded location forecasts, when compared with the extrapolated nowcasting.
基金Supported by the National Natural Science Foundation of China(U2142214,42030611,and 42275013)Key Research and Development Program of Hebei Province of China(23375401D)Key Research Program of the China Meteorological Administration Training Centre(2024CMATCZDIAN13)。
文摘Severe precipitation ranks among the most impactful meteorological disasters,exerting profound social and economic consequences.Forecasting heavy rainfall on an hourly scale,driven by complex multi-scale thermodynamic processes,remains a formidable challenge in numerical weather prediction(NWP).This study introduces a deeplearning-based fusion rain network(FRNet)designed to improve intense rainfall forecasting by effectively integrating the strengths of multi-scale model rain features.The model's performance in 3-h rainfall forecasts within a 24-h lead time over North China was comprehensively validated.Statistical assessments,based on independent tests conducted for 2021 and 2022,demonstrated FRNet's robust generalization capability.The results of the evaluations reveal that the deep learning model significantly enhances forecast accuracy across various precipitation thresholds—ranging from light to torrential rain—across all lead times within the 24-h period,when compared with the original model forecasts and the traditional multi-model similarity ensemble correction method.Notably,improvements become more pronounced with increasing precipitation intensity.Case studies of typical intense rainfall events have illustrated that FRNet effectively synthesizes the strengths of global models in predicting rainband location and movement,as well as mesoscale numerical models in forecasting intensity and fine-scale structures.This integration results in a more comprehensive and precise adjustment of precipitation forecasts,offering superior guidance for intense rainfall events compared to any single numerical model.Structure–amplitude–location(SAL)verification shows that FRNet significantly adjusts the structure and location of heavy precipitation but shows overestimation at the same time.Ablation experiments confirm that the performance gains of FRNet are primarily driven by the inclusion of high-resolution global and mesoscale model forecasts,complemented by geographic and temporal information.This study underscores the potential of deep learning techniques to integrate more multi-scale physical and observational features from different sources,paving the way for future advancements in intense rainfall forecasting.
基金partially supported by the National Natural Science Foundation of China(Grant No.91125010)
文摘This paper presents a new correction method, "instant correction method(ICM)", to improve the accuracy of numerical prediction products(NPP) and provide weather variables at grid cells. The ICM makes use of the continuity in time of the forecast errors at different forecast times to improve the accuracy of large scale NPP. To apply the ICM in China, an ensemble correction scheme is designed to correct the T213 NPP(the most popular NPP in China) through different statistical methods. The corrected T213 NPP(ICM T213 NPP) are evaluated by four popular indices: Correlation coefficient, climate anomalies correlation coefficient, root-mean-square-errors(RMSE), and confidence intervals(CI). The results show that the ICM T213 NPP are more accurate than the original T213 NPP in both the training period(2003–2008) and the validation period(2009–2010). Applications in China over the past three years indicate that the ICM is simple, fast, and reliable. Because of its low computing cost, end users in need of more accurate short-range weather forecasts around China can benefit greatly from the method.
