Accurate prediction of tropical cyclone(TC)intensity is challenging due to the complex physical processes involved.Here,we introduce a new TC intensity prediction scheme for the western North Pacific(WNP)based on a ti...Accurate prediction of tropical cyclone(TC)intensity is challenging due to the complex physical processes involved.Here,we introduce a new TC intensity prediction scheme for the western North Pacific(WNP)based on a time-dependent theory of TC intensification,termed the energetically based dynamical system(EBDS)model,together with the use of a long short-term memory(LSTM)neural network.In time-dependent theory,TC intensity change is controlled by both the internal dynamics of the TC system and various environmental factors,expressed as environmental dynamical efficiency.The LSTM neural network is used to predict the environmental dynamical efficiency in the EBDS model trained using besttrack TC data and global reanalysis data during 1982–2017.The transfer learning and ensemble methods are used to retrain the scheme using the environmental factors predicted by the Global Forecast System(GFS)of the National Centers for Environmental Prediction during 2017–21.The predicted environmental dynamical efficiency is finally iterated into the EBDS equations to predict TC intensity.The new scheme is evaluated for TC intensity prediction using both reanalysis data and the GFS prediction data.The intensity prediction by the new scheme shows better skill than the official prediction from the China Meteorological Administration(CMA)and those by other state-of-art statistical and dynamical forecast systems,except for the 72-h forecast.Particularly at the longer lead times of 96 h and 120 h,the new scheme has smaller forecast errors,with a more than 30%improvement over the official forecasts.展开更多
Recent studies have shown that deep learning(DL)models can skillfully forecast El Niño–Southern Oscillation(ENSO)events more than 1.5 years in advance.However,concerns regarding the reliability of predictions ma...Recent studies have shown that deep learning(DL)models can skillfully forecast El Niño–Southern Oscillation(ENSO)events more than 1.5 years in advance.However,concerns regarding the reliability of predictions made by DL methods persist,including potential overfitting issues and lack of interpretability.Here,we propose ResoNet,a DL model that combines CNN(convolutional neural network)and transformer architectures.This hybrid architecture enables our model to adequately capture local sea surface temperature anomalies as well as long-range inter-basin interactions across oceans.We show that ResoNet can robustly predict ENSO at lead times of 19 months,thus outperforming existing approaches in terms of the forecast horizon.According to an explainability method applied to ResoNet predictions of El Niño and La Niña from 1-to 18-month leads,we find that it predicts the Niño-3.4 index based on multiple physically reasonable mechanisms,such as the recharge oscillator concept,seasonal footprint mechanism,and Indian Ocean capacitor effect.Moreover,we demonstrate for the first time that the asymmetry between El Niño and La Niña development can be captured by ResoNet.Our results could help to alleviate skepticism about applying DL models for ENSO prediction and encourage more attempts to discover and predict climate phenomena using AI methods.展开更多
In order to quantify the influence of external forcings on the predictability limit using observational data,the author introduced an algorithm of the conditional nonlinear local Lyapunov exponent(CNLLE)method.The eff...In order to quantify the influence of external forcings on the predictability limit using observational data,the author introduced an algorithm of the conditional nonlinear local Lyapunov exponent(CNLLE)method.The effectiveness of this algorithm is validated and compared with the nonlinear local Lyapunov exponent(NLLE)and signal-to-noise ratio methods using a coupled Lorenz model.The results show that the CNLLE method is able to capture the slow error growth constrained by external forcings,therefore,it can quantify the predictability limit induced by the external forcings.On this basis,a preliminary attempt was made to apply this method to measure the influence of ENSO on the predictability limit for both atmospheric and oceanic variable fields.The spatial distribution of the predictability limit induced by ENSO is similar to that arising from the initial conditions calculated by the NLLE method.This similarity supports ENSO as the major predictable signal for weather and climate prediction.In addition,a ratio of predictability limit(RPL)calculated by the CNLLE method to that calculated by the NLLE method was proposed.The RPL larger than 1 indicates that the external forcings can significantly benefit the long-term predictability limit.For instance,ENSO can effectively extend the predictability limit arising from the initial conditions of sea surface temperature over the tropical Indian Ocean by approximately four months,as well as the predictability limit of sea level pressure over the eastern and western Pacific Ocean.Moreover,the impact of ENSO on the geopotential height predictability limit is primarily confined to the troposphere.展开更多
The 2015/16 El Niño event ranks among the top three of the last 100 years in terms of intensity,but most dynamical models had a relatively low prediction skill for this event before the summer months.Therefore,th...The 2015/16 El Niño event ranks among the top three of the last 100 years in terms of intensity,but most dynamical models had a relatively low prediction skill for this event before the summer months.Therefore,the attribution of this particular event can help us to understand the cause of super El Niño–Southern Oscillation events and how to forecast them skillfully.The present study applies attribute methods based on a deep learning model to study the key factors related to the formation of this event.A deep learning model is trained using historical simulations from 21 CMIP6 models to predict the Niño-3.4 index.The integrated gradient method is then used to identify the key signals in the North Pacific that determine the evolution of the Niño-3.4 index.These crucial signals are then masked in the initial conditions to verify their roles in the prediction.In addition to confirming the key signals inducing the super El Niño event revealed in previous attribution studies,we identify the combined contribution of the tropical North Atlantic and the South Pacific oceans to the evolution and intensity of this event,emphasizing the crucial role of the interactions among them and the North Pacific.This approach is also applied to other El Niño events,revealing several new precursor signals.This study suggests that the deep learning method is useful in attributing the key factors inducing extreme tropical climate events.展开更多
Valuable dropsonde data were obtained from multiple field campaigns targeting tropical cyclones,namely Higos,Nangka,Saudel,and Atsani,over the western North Pacific by the Hong Kong Observatory and Taiwan Central Weat...Valuable dropsonde data were obtained from multiple field campaigns targeting tropical cyclones,namely Higos,Nangka,Saudel,and Atsani,over the western North Pacific by the Hong Kong Observatory and Taiwan Central Weather Bureau in 2020.The conditional nonlinear optimal perturbation(CNOP)method has been utilized in real-time to identify the sensitive regions for targeting observations adhering to the procedure of real-time field campaigns for the first time.The observing system experiments were conducted to evaluate the effect of dropsonde data and CNOP sensitivity on TC forecasts in terms of track and intensity,using the Weather Research and Forecasting model.It is shown that the impact of assimilating all dropsonde data on both track and intensity forecasts is case-dependent.However,assimilation using only the dropsonde data inside the sensitive regions displays unanimously positive effects on both the track and intensity forecast,either of which obtains comparable benefits to or greatly reduces deterioration of the skill when assimilating all dropsonde data.Therefore,these results encourage us to further carry out targeting observations for the forecast of tropical cyclones according to CNOP sensitivity.展开更多
运用澳大利亚大气海洋耦合预报模式(Predictive Ocean Atmosphere Model for Australia,POAMA)的输出结果,采用泰勒图与分类统计分析方法,评估了该模式对2003和2004年南海夏季风的爆发和演变进行实时预报的能力。通过对泰勒图的分析发现...运用澳大利亚大气海洋耦合预报模式(Predictive Ocean Atmosphere Model for Australia,POAMA)的输出结果,采用泰勒图与分类统计分析方法,评估了该模式对2003和2004年南海夏季风的爆发和演变进行实时预报的能力。通过对泰勒图的分析发现,随着预报初始时间越来越接近实际的季风爆发时间,模式预报南海夏季风爆发和演变的能力越来越强。当提前1—30d预报南海夏季风时,模式能够很好地预报风场、射出长波辐射OLR(Outgoing Longwave Radiation)和降水场的空间分布,其中对风场的预报最好。通过对季风爆发指数和分类统计的分析,定量分析了模式预报南海夏季风爆发的能力,结果表明该模式对南海夏季风爆发时间有一定的预报能力,其最大预报时限可以提前10—15d左右,这与目前中期预报的上限(2周)是一致的。展开更多
基金supported by the National Key R&D Program of China(Grant No.2017YFC1501604)the National Natural Science Foundation of China(Grant Nos.41875114 and 41875057).
文摘Accurate prediction of tropical cyclone(TC)intensity is challenging due to the complex physical processes involved.Here,we introduce a new TC intensity prediction scheme for the western North Pacific(WNP)based on a time-dependent theory of TC intensification,termed the energetically based dynamical system(EBDS)model,together with the use of a long short-term memory(LSTM)neural network.In time-dependent theory,TC intensity change is controlled by both the internal dynamics of the TC system and various environmental factors,expressed as environmental dynamical efficiency.The LSTM neural network is used to predict the environmental dynamical efficiency in the EBDS model trained using besttrack TC data and global reanalysis data during 1982–2017.The transfer learning and ensemble methods are used to retrain the scheme using the environmental factors predicted by the Global Forecast System(GFS)of the National Centers for Environmental Prediction during 2017–21.The predicted environmental dynamical efficiency is finally iterated into the EBDS equations to predict TC intensity.The new scheme is evaluated for TC intensity prediction using both reanalysis data and the GFS prediction data.The intensity prediction by the new scheme shows better skill than the official prediction from the China Meteorological Administration(CMA)and those by other state-of-art statistical and dynamical forecast systems,except for the 72-h forecast.Particularly at the longer lead times of 96 h and 120 h,the new scheme has smaller forecast errors,with a more than 30%improvement over the official forecasts.
基金supported by the Shanghai Artificial Intelligence Laboratory and National Natural Science Foundation of China(Grant No.42088101 and 42030605).
文摘Recent studies have shown that deep learning(DL)models can skillfully forecast El Niño–Southern Oscillation(ENSO)events more than 1.5 years in advance.However,concerns regarding the reliability of predictions made by DL methods persist,including potential overfitting issues and lack of interpretability.Here,we propose ResoNet,a DL model that combines CNN(convolutional neural network)and transformer architectures.This hybrid architecture enables our model to adequately capture local sea surface temperature anomalies as well as long-range inter-basin interactions across oceans.We show that ResoNet can robustly predict ENSO at lead times of 19 months,thus outperforming existing approaches in terms of the forecast horizon.According to an explainability method applied to ResoNet predictions of El Niño and La Niña from 1-to 18-month leads,we find that it predicts the Niño-3.4 index based on multiple physically reasonable mechanisms,such as the recharge oscillator concept,seasonal footprint mechanism,and Indian Ocean capacitor effect.Moreover,we demonstrate for the first time that the asymmetry between El Niño and La Niña development can be captured by ResoNet.Our results could help to alleviate skepticism about applying DL models for ENSO prediction and encourage more attempts to discover and predict climate phenomena using AI methods.
基金supported by the National Natural Science Foundation of China(Grant Nos.42225501 and 42105059)the National Key Scientific and Tech-nological Infrastructure project“Earth System Numerical Simula-tion Facility”(EarthLab).
文摘In order to quantify the influence of external forcings on the predictability limit using observational data,the author introduced an algorithm of the conditional nonlinear local Lyapunov exponent(CNLLE)method.The effectiveness of this algorithm is validated and compared with the nonlinear local Lyapunov exponent(NLLE)and signal-to-noise ratio methods using a coupled Lorenz model.The results show that the CNLLE method is able to capture the slow error growth constrained by external forcings,therefore,it can quantify the predictability limit induced by the external forcings.On this basis,a preliminary attempt was made to apply this method to measure the influence of ENSO on the predictability limit for both atmospheric and oceanic variable fields.The spatial distribution of the predictability limit induced by ENSO is similar to that arising from the initial conditions calculated by the NLLE method.This similarity supports ENSO as the major predictable signal for weather and climate prediction.In addition,a ratio of predictability limit(RPL)calculated by the CNLLE method to that calculated by the NLLE method was proposed.The RPL larger than 1 indicates that the external forcings can significantly benefit the long-term predictability limit.For instance,ENSO can effectively extend the predictability limit arising from the initial conditions of sea surface temperature over the tropical Indian Ocean by approximately four months,as well as the predictability limit of sea level pressure over the eastern and western Pacific Ocean.Moreover,the impact of ENSO on the geopotential height predictability limit is primarily confined to the troposphere.
基金supported by the National Key R&D Program of China(2019YFA0606703)the Youth Innovation Promotion Association of the Chinese Academy of Sciences(Grant No.Y202025).
文摘The 2015/16 El Niño event ranks among the top three of the last 100 years in terms of intensity,but most dynamical models had a relatively low prediction skill for this event before the summer months.Therefore,the attribution of this particular event can help us to understand the cause of super El Niño–Southern Oscillation events and how to forecast them skillfully.The present study applies attribute methods based on a deep learning model to study the key factors related to the formation of this event.A deep learning model is trained using historical simulations from 21 CMIP6 models to predict the Niño-3.4 index.The integrated gradient method is then used to identify the key signals in the North Pacific that determine the evolution of the Niño-3.4 index.These crucial signals are then masked in the initial conditions to verify their roles in the prediction.In addition to confirming the key signals inducing the super El Niño event revealed in previous attribution studies,we identify the combined contribution of the tropical North Atlantic and the South Pacific oceans to the evolution and intensity of this event,emphasizing the crucial role of the interactions among them and the North Pacific.This approach is also applied to other El Niño events,revealing several new precursor signals.This study suggests that the deep learning method is useful in attributing the key factors inducing extreme tropical climate events.
基金jointly sponsored by the National Nature Scientific Foundation of China(Grant.Nos.41930971 and 41775061)the National Key Research and Development Program of China(Grant No.2018YFC1506402)。
文摘Valuable dropsonde data were obtained from multiple field campaigns targeting tropical cyclones,namely Higos,Nangka,Saudel,and Atsani,over the western North Pacific by the Hong Kong Observatory and Taiwan Central Weather Bureau in 2020.The conditional nonlinear optimal perturbation(CNOP)method has been utilized in real-time to identify the sensitive regions for targeting observations adhering to the procedure of real-time field campaigns for the first time.The observing system experiments were conducted to evaluate the effect of dropsonde data and CNOP sensitivity on TC forecasts in terms of track and intensity,using the Weather Research and Forecasting model.It is shown that the impact of assimilating all dropsonde data on both track and intensity forecasts is case-dependent.However,assimilation using only the dropsonde data inside the sensitive regions displays unanimously positive effects on both the track and intensity forecast,either of which obtains comparable benefits to or greatly reduces deterioration of the skill when assimilating all dropsonde data.Therefore,these results encourage us to further carry out targeting observations for the forecast of tropical cyclones according to CNOP sensitivity.
文摘运用澳大利亚大气海洋耦合预报模式(Predictive Ocean Atmosphere Model for Australia,POAMA)的输出结果,采用泰勒图与分类统计分析方法,评估了该模式对2003和2004年南海夏季风的爆发和演变进行实时预报的能力。通过对泰勒图的分析发现,随着预报初始时间越来越接近实际的季风爆发时间,模式预报南海夏季风爆发和演变的能力越来越强。当提前1—30d预报南海夏季风时,模式能够很好地预报风场、射出长波辐射OLR(Outgoing Longwave Radiation)和降水场的空间分布,其中对风场的预报最好。通过对季风爆发指数和分类统计的分析,定量分析了模式预报南海夏季风爆发的能力,结果表明该模式对南海夏季风爆发时间有一定的预报能力,其最大预报时限可以提前10—15d左右,这与目前中期预报的上限(2周)是一致的。
