Accurate forecasting of tropical cyclone(TC)tracks and intensities is essential.Although the TianXing large weather model,a six-hourly forecasting model surpassing operational forecasts,exhibits superior performance,i...Accurate forecasting of tropical cyclone(TC)tracks and intensities is essential.Although the TianXing large weather model,a six-hourly forecasting model surpassing operational forecasts,exhibits superior performance,its TC forecasts still require enhancement.Prediction errors persist due to biases in the training data and smoothing effects in data-driven methods.To address this,we introduce CycloneBCNet,a deep-learning model designed to correct TianXing’s TC forecast biases by leveraging spatial and temporal data.CycloneBCNet utilizes the SimVP(simpler yet better video prediction)framework with spatial attention to highlight cyclone core regions in forecast fields.It also incorporates TC trend information(center position,maximum wind speed,and minimum sea level pressure)via an LSTM(long short-term memory)module.These TC vectors are derived from post-processed TianXing forecasts.By fusing features from forecast fields and TC vectors,CycloneBCNet corrects biases across multiple lead times.At a 96-h lead time,the track error reduces from 162.4 to 86.4 km,the wind speed error from 17.2 to 6.69 m s^(-1),and the pressure error from 22.2 to 9.36 hPa.Interpretability analysis shows that CycloneBCNet adjusts its attention across forecast lead times.Intensity corrections prioritize inner-core dynamics,particularly the eye and eyewall,while track corrections shift from lower-level variables and the cyclone’s core to broader environmental factors and mid-to upper-level features as the forecast duration increases.These findings demonstrate that CycloneBCNet effectively captures key TC dynamics consistent with meteorological principles,including the dominance of near-surface conditions for intensity and the increasing influence of steering currents on track prediction.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
Northeast China serves as an important crop production region.Accurately forecasting summer precipitation in Northeast China(NEC-PR)has been a challenge due to its wide range of time scales influenced by varying clima...Northeast China serves as an important crop production region.Accurately forecasting summer precipitation in Northeast China(NEC-PR)has been a challenge due to its wide range of time scales influenced by varying climatic conditions.This study presents a scale separation hybrid statistical model with recurrent neural network(SS-RNN)to predict the summer monthly NEC-PR.The SS-RNN model decomposes the multiple scales of the NEC-PR into several spatiotemporal intrinsic mode functions covering annual to decadal time scales.This strategy provides a way to derive appropriate predictors and establish predictive models for the primary spatial modes of the NEC-PR at various time scales.Our results demonstrate substantial improvements by the SS-RNN model in predicting the summer monthly NEC-PR as compared with dynamic models,particularly in predicting the spatial pattern of the NEC-PR.In this paper we take August,the month of the highest NEC-PR,to assess our model skill.Independent forecasts of the August NEC-PR over the period 2021–24 achieve significant spatial anomaly correlation coefficients,reaching a maximum value of 0.83.Additional verifications by station observations show that the model hits most station anomalies,achieving a mean predictive skill score of 90.展开更多
The Northeast China Cold Vortex(NCCV)is a common cut-off low-pressure system in Northeast China,frequently causing localized heavy rainfall,strong winds,and thunderstorms during the early summer.In this study,the clea...The Northeast China Cold Vortex(NCCV)is a common cut-off low-pressure system in Northeast China,frequently causing localized heavy rainfall,strong winds,and thunderstorms during the early summer.In this study,the clear-sky radiance of 48 longwave channels from the FY-4B Geostationary Interferometric Infrared Sounder(GIIRS)is assimilated into the China Meteorological Administration mesoscale model(CMA-MESO)to evaluate its impact on NCCV development and its effects on rainfall forecasting.The results show that after assimilating the GIIRS radiance data,the warm center at 200 hPa and the cold center at 850 hPa of the NCCV are strengthened,and the dry intrusion at 850 hPa becomes more pronounced.This leads to a stronger NCCV intensity in the following 24 hours and brings the precipitation intensity and area closer to the observation,resulting in significant improvements compared to the experiments that do not assimilate GIIRS radiance data.Furthermore,it is found that the enhancement of the precipitation forecast is associated with the strengthening of cold air in the middle and lower troposphere,which intensifies the uplift of the warm,moist airflow.These results highlight the potential value of GIIRS data assimilation in enhancing early warnings and forecasts of extreme weather events influenced by the NCCV.展开更多
Precipitation nowcasting is of great importance for disaster prevention and mitigation.However,precipitation is a complex spatio-temporal phenomenon influenced by various underlying physical factors.Even slight change...Precipitation nowcasting is of great importance for disaster prevention and mitigation.However,precipitation is a complex spatio-temporal phenomenon influenced by various underlying physical factors.Even slight changes in the initial precipitation field can have a significant impact on the future precipitation patterns,making the nowcasting of short-term high-resolution precipitation a major challenge.Traditional deep learning methods often have difficulty capturing the long-term spatial dependence of precipitation and are usually at a low resolution.To address these issues,based upon the Simpler yet Better Video Prediction(SimVP)framework,we proposed a deep generative neural network that incorporates the Simple Parameter-Free Attention Module(SimAM)and Generative Adversarial Networks(GANs)for short-term high-resolution precipitation event forecasting.Through an adversarial training strategy,critical precipitation features were extracted from complex radar echo images.During the adversarial learning process,the dynamic competition between the generator and the discriminator could continuously enhance the model in prediction accuracy and resolution for short-term precipitation.Experimental results demonstrate that the proposed method could effectively forecast short-term precipitation events on various scales and showed the best overall performance among existing methods.展开更多
This study traces the development of the Shanghai Typhoon Model(SHTM)from a traditional physics-based regional model toward a data-driven,machine-learning typhoon forecasting system.After upgrading its initial and bou...This study traces the development of the Shanghai Typhoon Model(SHTM)from a traditional physics-based regional model toward a data-driven,machine-learning typhoon forecasting system.After upgrading its initial and boundary conditions,SHTM now leverages large-scale constraints from machine-learning weather prediction(MLWP)models,resulting in an ML–physics hybrid framework.During Typhoon Danas(2025),the hybrid SHTM achieves substantially lower track errors than both the advanced ECMWF Integrated Forecasting System(IFS)and leading MLWP models such as PanGu and FuXi.Furthermore,the hybrid SHTM consistently maintains mean track errors below 200 km up to a forecast lead time of 108 hours,representing a significant advancement in forecast accuracy.In addition,this study highlights the technical roadmap for transitioning from a physics-based typhoon model to a fully data-driven ML typhoon forecast system.It also emphasizes that advances in the physical modeling framework provide a critical foundation for further improving the performance of future data-driven ML typhoon models.展开更多
为进一步提高温度业务预报水平,本文采用美国国家环境预报中心环境模式中心(National Centers for Environmental Prediction-Environmental Modeling Center,NCEP-EMC)研发的基于递归贝叶斯模型过程(recursive Bayesian model process,...为进一步提高温度业务预报水平,本文采用美国国家环境预报中心环境模式中心(National Centers for Environmental Prediction-Environmental Modeling Center,NCEP-EMC)研发的基于递归贝叶斯模型过程(recursive Bayesian model process,RBMP)的多模式集合技术,开展了华东2 m温度预报试验。利用2016—2017年欧洲中期天气预报中心(European Centre for Medium-Range Weather Forecasts,ECMWF)、NCEP和加拿大气象中心(Canadian Meteorological Centre,CMC)3个具有代表性的全球集合预报系统产品,在对各模式进行偏差订正的基础上,开展了RBMP算法应用试验和评估,建立了华东地区应用方案,再利用2019年9月—2020年5月ECMWF、NCEP集合预报资料开展试运行,初步讨论了RBMP方法在冬春季节预报失败案例中的适用性。结果表明:RBMP方法能够提供更加可靠的概率预报分布并有效提高短期时效的预报技巧。其中,冬季改进最明显,集合平均的均方根误差比ECMWF订正预报和等权重多模式集合分别降低3.0%~10.5%和2.0%~5.0%,且对高温和低温事件均具有更优的分辨能力。此外,RBMP方法还能够提高大部分预报失败案例的预报准确率,为难报案例提供了有价值的不确定信息。总体而言,RBMP技术不仅保留了BMA(Bayesian model averaging)方法的优势,且能满足业务应用对资料存储和计算效率的需求,通过二阶矩调整可以有效校正集合离散度,为进一步提高短期温度预报技巧提供了一种思路。展开更多
文摘针对2023年第6号台风“卡努”影响辽宁及周边地区产生的强降水,采用TS评分(threat score)检验法和多种空间检验法,检验分析CMA_MESO、CMA_GFS和EC_IFS模式的日降水24 h、48 h和72 h预报在强度、落区形态结构和位置3方面的偏差特征。(1)TS评分检验表明,CMA_MESO、CMA_GFS和EC_IFS模式在24 h预报时效下对大雨以下量级预报的TS评分分别为0.64、0.66和0.69,随着降水阈值的增大,TS评分值降低至0.4左右。EC_IFS的TS评分最好,CMA_MESO空报率最大。(2)SAL(structure,amplitude and location)空间检验表明,3个数值模式降水整体位置预报基本一致,但降水强度预报均偏弱,EC_IFS的预报落区结构预报与实况最相似,但对暴雨以上量级范围较实况偏大。(3)MODE(method for object based diagnostic evaluation)属性综合相似度评分表明,CMA_GFS模式对于此次台风降水预报不稳定;CMA_MESO模式预报稳定,但对于暴雨量级预报效果不理想;EC_IFS模式24 h预报时效下的相似度评分最高,对于此次台风降水预报可靠性最高。空间检验法相比传统TS评分,能更精准定位模式在暴雨量级上的结构偏差,并量化雨带位置偏移。在实际业务工作中,应根据不同需求选择不同的检验方式,同时也可将不同的检验方法相结合,从不同角度分析数值模式的预报性能,有助于提高相似台风降水预报的模式适用性。
基金supported by the Meteorological Joint Funds of the National Natural Science Foundation of China(Grant No.U2142211)the National Natural Science Foundation of China(Grant Nos.42075141,42341202 and 62088101)+1 种基金the National Key Research and Development Program of China(Grant No.2020YFA0608000)the Shanghai Municipal Science and Technology Major Project(Grant No.2021SHZDZX0100).
文摘Accurate forecasting of tropical cyclone(TC)tracks and intensities is essential.Although the TianXing large weather model,a six-hourly forecasting model surpassing operational forecasts,exhibits superior performance,its TC forecasts still require enhancement.Prediction errors persist due to biases in the training data and smoothing effects in data-driven methods.To address this,we introduce CycloneBCNet,a deep-learning model designed to correct TianXing’s TC forecast biases by leveraging spatial and temporal data.CycloneBCNet utilizes the SimVP(simpler yet better video prediction)framework with spatial attention to highlight cyclone core regions in forecast fields.It also incorporates TC trend information(center position,maximum wind speed,and minimum sea level pressure)via an LSTM(long short-term memory)module.These TC vectors are derived from post-processed TianXing forecasts.By fusing features from forecast fields and TC vectors,CycloneBCNet corrects biases across multiple lead times.At a 96-h lead time,the track error reduces from 162.4 to 86.4 km,the wind speed error from 17.2 to 6.69 m s^(-1),and the pressure error from 22.2 to 9.36 hPa.Interpretability analysis shows that CycloneBCNet adjusts its attention across forecast lead times.Intensity corrections prioritize inner-core dynamics,particularly the eye and eyewall,while track corrections shift from lower-level variables and the cyclone’s core to broader environmental factors and mid-to upper-level features as the forecast duration increases.These findings demonstrate that CycloneBCNet effectively captures key TC dynamics consistent with meteorological principles,including the dominance of near-surface conditions for intensity and the increasing influence of steering currents on track prediction.
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 National Key Research and Development Program of China(Grant No.2022YFC3002803)the National Key Research and Development Program of China(Grant No.2024YFF0808402)the National Natural Science Foundation of China(Grant No.42375169)。
文摘Northeast China serves as an important crop production region.Accurately forecasting summer precipitation in Northeast China(NEC-PR)has been a challenge due to its wide range of time scales influenced by varying climatic conditions.This study presents a scale separation hybrid statistical model with recurrent neural network(SS-RNN)to predict the summer monthly NEC-PR.The SS-RNN model decomposes the multiple scales of the NEC-PR into several spatiotemporal intrinsic mode functions covering annual to decadal time scales.This strategy provides a way to derive appropriate predictors and establish predictive models for the primary spatial modes of the NEC-PR at various time scales.Our results demonstrate substantial improvements by the SS-RNN model in predicting the summer monthly NEC-PR as compared with dynamic models,particularly in predicting the spatial pattern of the NEC-PR.In this paper we take August,the month of the highest NEC-PR,to assess our model skill.Independent forecasts of the August NEC-PR over the period 2021–24 achieve significant spatial anomaly correlation coefficients,reaching a maximum value of 0.83.Additional verifications by station observations show that the model hits most station anomalies,achieving a mean predictive skill score of 90.
基金sponsored by the National Natural Science Foundation of China(Grant No.42275171)the Basic Research Operating Expenses of the Institute of Meteorological Sciences,CMA(Grant No.2023Z019)+3 种基金the National Key Research and Development Program of China(Grant No.2022YFF0801304)the China Meteorological Administration Youth Innovation Team Fund(Grant No.CMA2024QN05)a Liaoning Provincial Meteorological Bureau Project(Grant No.D202201)Shenyang Institute of Atmospheric Environment Projects(Grant Nos.2022SYIAEJY13 and 2018SYIAEZD5).
文摘The Northeast China Cold Vortex(NCCV)is a common cut-off low-pressure system in Northeast China,frequently causing localized heavy rainfall,strong winds,and thunderstorms during the early summer.In this study,the clear-sky radiance of 48 longwave channels from the FY-4B Geostationary Interferometric Infrared Sounder(GIIRS)is assimilated into the China Meteorological Administration mesoscale model(CMA-MESO)to evaluate its impact on NCCV development and its effects on rainfall forecasting.The results show that after assimilating the GIIRS radiance data,the warm center at 200 hPa and the cold center at 850 hPa of the NCCV are strengthened,and the dry intrusion at 850 hPa becomes more pronounced.This leads to a stronger NCCV intensity in the following 24 hours and brings the precipitation intensity and area closer to the observation,resulting in significant improvements compared to the experiments that do not assimilate GIIRS radiance data.Furthermore,it is found that the enhancement of the precipitation forecast is associated with the strengthening of cold air in the middle and lower troposphere,which intensifies the uplift of the warm,moist airflow.These results highlight the potential value of GIIRS data assimilation in enhancing early warnings and forecasts of extreme weather events influenced by the NCCV.
基金Supported by the National Natural Science Foundation of China(No.42306214)the Postdoctoral Innovative Talents Support Program of Shandong Province(No.SDBX2022026)+1 种基金the China Postdoctoral Science Foundation(No.2023M733533)the Special Research Assistant Project of the Chinese Academy of Sciences in 2022。
文摘Precipitation nowcasting is of great importance for disaster prevention and mitigation.However,precipitation is a complex spatio-temporal phenomenon influenced by various underlying physical factors.Even slight changes in the initial precipitation field can have a significant impact on the future precipitation patterns,making the nowcasting of short-term high-resolution precipitation a major challenge.Traditional deep learning methods often have difficulty capturing the long-term spatial dependence of precipitation and are usually at a low resolution.To address these issues,based upon the Simpler yet Better Video Prediction(SimVP)framework,we proposed a deep generative neural network that incorporates the Simple Parameter-Free Attention Module(SimAM)and Generative Adversarial Networks(GANs)for short-term high-resolution precipitation event forecasting.Through an adversarial training strategy,critical precipitation features were extracted from complex radar echo images.During the adversarial learning process,the dynamic competition between the generator and the discriminator could continuously enhance the model in prediction accuracy and resolution for short-term precipitation.Experimental results demonstrate that the proposed method could effectively forecast short-term precipitation events on various scales and showed the best overall performance among existing methods.
基金supported by the Special Project-Original Exploration(Grant No.42450163)the National Youth Science Foundation of China Project(Grant No.4240050560)the Research and Development of Key Technologies for Artificial Intelligence Regional Typhoon Forecasting Model project.
文摘This study traces the development of the Shanghai Typhoon Model(SHTM)from a traditional physics-based regional model toward a data-driven,machine-learning typhoon forecasting system.After upgrading its initial and boundary conditions,SHTM now leverages large-scale constraints from machine-learning weather prediction(MLWP)models,resulting in an ML–physics hybrid framework.During Typhoon Danas(2025),the hybrid SHTM achieves substantially lower track errors than both the advanced ECMWF Integrated Forecasting System(IFS)and leading MLWP models such as PanGu and FuXi.Furthermore,the hybrid SHTM consistently maintains mean track errors below 200 km up to a forecast lead time of 108 hours,representing a significant advancement in forecast accuracy.In addition,this study highlights the technical roadmap for transitioning from a physics-based typhoon model to a fully data-driven ML typhoon forecast system.It also emphasizes that advances in the physical modeling framework provide a critical foundation for further improving the performance of future data-driven ML typhoon models.
文摘为进一步提高温度业务预报水平,本文采用美国国家环境预报中心环境模式中心(National Centers for Environmental Prediction-Environmental Modeling Center,NCEP-EMC)研发的基于递归贝叶斯模型过程(recursive Bayesian model process,RBMP)的多模式集合技术,开展了华东2 m温度预报试验。利用2016—2017年欧洲中期天气预报中心(European Centre for Medium-Range Weather Forecasts,ECMWF)、NCEP和加拿大气象中心(Canadian Meteorological Centre,CMC)3个具有代表性的全球集合预报系统产品,在对各模式进行偏差订正的基础上,开展了RBMP算法应用试验和评估,建立了华东地区应用方案,再利用2019年9月—2020年5月ECMWF、NCEP集合预报资料开展试运行,初步讨论了RBMP方法在冬春季节预报失败案例中的适用性。结果表明:RBMP方法能够提供更加可靠的概率预报分布并有效提高短期时效的预报技巧。其中,冬季改进最明显,集合平均的均方根误差比ECMWF订正预报和等权重多模式集合分别降低3.0%~10.5%和2.0%~5.0%,且对高温和低温事件均具有更优的分辨能力。此外,RBMP方法还能够提高大部分预报失败案例的预报准确率,为难报案例提供了有价值的不确定信息。总体而言,RBMP技术不仅保留了BMA(Bayesian model averaging)方法的优势,且能满足业务应用对资料存储和计算效率的需求,通过二阶矩调整可以有效校正集合离散度,为进一步提高短期温度预报技巧提供了一种思路。
