It is fundamental and useful to investigate how deep learning forecasting models(DLMs)perform compared to operational oceanography forecast systems(OFSs).However,few studies have intercompared their performances using...It is fundamental and useful to investigate how deep learning forecasting models(DLMs)perform compared to operational oceanography forecast systems(OFSs).However,few studies have intercompared their performances using an identical reference.In this study,three physically reasonable DLMs are implemented for the forecasting of the sea surface temperature(SST),sea level anomaly(SLA),and sea surface velocity in the South China Sea.The DLMs are validated against both the testing dataset and the“OceanPredict”Class 4 dataset.Results show that the DLMs'RMSEs against the latter increase by 44%,245%,302%,and 109%for SST,SLA,current speed,and direction,respectively,compared to those against the former.Therefore,different references have significant influences on the validation,and it is necessary to use an identical and independent reference to intercompare the DLMs and OFSs.Against the Class 4 dataset,the DLMs present significantly better performance for SLA than the OFSs,and slightly better performances for other variables.The error patterns of the DLMs and OFSs show a high degree of similarity,which is reasonable from the viewpoint of predictability,facilitating further applications of the DLMs.For extreme events,the DLMs and OFSs both present large but similar forecast errors for SLA and current speed,while the DLMs are likely to give larger errors for SST and current direction.This study provides an evaluation of the forecast skills of commonly used DLMs and provides an example to objectively intercompare different DLMs.展开更多
1.A key support for the 2022 Winter Olympics The XXIV Olympic Winter Games are scheduled to take place from 4 to 22 February 2022,followed by the Paralympic Games from 4 to 13 March,in Beijing and towns in the neighbo...1.A key support for the 2022 Winter Olympics The XXIV Olympic Winter Games are scheduled to take place from 4 to 22 February 2022,followed by the Paralympic Games from 4 to 13 March,in Beijing and towns in the neighboring Hebei Province,China.Weather plays an extremely important role in the outcome of the games(Chen et al.,2018).It can not only cause a difference between a medal or not,but affect the safety of athletes.Success of the Winter Olympics will greatly depend on weather conditions at the outdoor competition venues,dealing with many weather elements including the snow surface temperature,apparent temperature,gust wind speed,snow,visibility,etc.To ensure that the scheduled games go smoothly,it is imperative to have hourly or even every 10-minutely forecasts as well as updated weather-related risk assessments at the venues for the next 240 hours.So far,the Beijing/Hebei Meteorological Observatory has already started intelligent weather forecasting at 3-km resolution based on the results of numerical weather prediction(NWP)models.However,these experiments have suggested that the current forecasting techniques are incapable of capturing the complex mountain weather variations around some venues.The forecasting capability of NWP is constrained partly by limited knowledge of the local weather mechanisms.展开更多
We propose a novel machine learning approach to reconstruct meshless surface wind speed fields,i.e.,to reconstruct the surface wind speed at any location,based on meteorological background fields and geographical info...We propose a novel machine learning approach to reconstruct meshless surface wind speed fields,i.e.,to reconstruct the surface wind speed at any location,based on meteorological background fields and geographical information.The random forest method is selected to develop the machine learning data reconstruction model(MLDRM-RF)for wind speeds over Beijing from 2015-19.We use temporal,geospatial attribute and meteorological background field features as inputs.The wind speed field can be reconstructed at any station in the region not used in the training process to cross-validate model performance.The evaluation considers the spatial distribution of and seasonal variations in the root mean squared error(RMSE)of the reconstructed wind speed field across Beijing.The average RMSE is 1.09 m s^(−1),considerably smaller than the result(1.29 m s^(−1))obtained with inverse distance weighting(IDW)interpolation.Finally,we extract the important feature permutations by the method of mean decrease in impurity(MDI)and discuss the reasonableness of the model prediction results.MLDRM-RF is a reasonable approach with excellent potential for the improved reconstruction of historical surface wind speed fields with arbitrary grid resolutions.Such a model is needed in many wind applications,such as wind energy and aviation safety assessments.展开更多
基金supported by the National Natural Science Foundation of China(Grant Nos.42375062 and 42275158)the National Key Scientific and Technological Infrastructure project“Earth System Science Numerical Simulator Facility”(EarthLab)the Natural Science Foundation of Gansu Province(Grant No.22JR5RF1080)。
文摘It is fundamental and useful to investigate how deep learning forecasting models(DLMs)perform compared to operational oceanography forecast systems(OFSs).However,few studies have intercompared their performances using an identical reference.In this study,three physically reasonable DLMs are implemented for the forecasting of the sea surface temperature(SST),sea level anomaly(SLA),and sea surface velocity in the South China Sea.The DLMs are validated against both the testing dataset and the“OceanPredict”Class 4 dataset.Results show that the DLMs'RMSEs against the latter increase by 44%,245%,302%,and 109%for SST,SLA,current speed,and direction,respectively,compared to those against the former.Therefore,different references have significant influences on the validation,and it is necessary to use an identical and independent reference to intercompare the DLMs and OFSs.Against the Class 4 dataset,the DLMs present significantly better performance for SLA than the OFSs,and slightly better performances for other variables.The error patterns of the DLMs and OFSs show a high degree of similarity,which is reasonable from the viewpoint of predictability,facilitating further applications of the DLMs.For extreme events,the DLMs and OFSs both present large but similar forecast errors for SLA and current speed,while the DLMs are likely to give larger errors for SST and current direction.This study provides an evaluation of the forecast skills of commonly used DLMs and provides an example to objectively intercompare different DLMs.
基金supported by the National Key Research and Development Program of China(Grant No.2018YFF0300104)Beijing Academy of Artificial Intelligence,and the Open Research Fund of the Shenzhen Research Institute of Big Data(Grant No.2019ORF01001).
文摘1.A key support for the 2022 Winter Olympics The XXIV Olympic Winter Games are scheduled to take place from 4 to 22 February 2022,followed by the Paralympic Games from 4 to 13 March,in Beijing and towns in the neighboring Hebei Province,China.Weather plays an extremely important role in the outcome of the games(Chen et al.,2018).It can not only cause a difference between a medal or not,but affect the safety of athletes.Success of the Winter Olympics will greatly depend on weather conditions at the outdoor competition venues,dealing with many weather elements including the snow surface temperature,apparent temperature,gust wind speed,snow,visibility,etc.To ensure that the scheduled games go smoothly,it is imperative to have hourly or even every 10-minutely forecasts as well as updated weather-related risk assessments at the venues for the next 240 hours.So far,the Beijing/Hebei Meteorological Observatory has already started intelligent weather forecasting at 3-km resolution based on the results of numerical weather prediction(NWP)models.However,these experiments have suggested that the current forecasting techniques are incapable of capturing the complex mountain weather variations around some venues.The forecasting capability of NWP is constrained partly by limited knowledge of the local weather mechanisms.
基金supported by the Strategic Priority Research Program of the Chinese Academy of Sciences(Grant No.XDA19030402)the Key Special Projects for International Cooperation in Science and Technology Innovation between Governments(Grant No.2017YFE0133600the Beijing Municipal Natural Science Foundation Youth Project 8214066:Application Research of Beijing Road Visibility Prediction Based on Machine Learning Methods.
文摘We propose a novel machine learning approach to reconstruct meshless surface wind speed fields,i.e.,to reconstruct the surface wind speed at any location,based on meteorological background fields and geographical information.The random forest method is selected to develop the machine learning data reconstruction model(MLDRM-RF)for wind speeds over Beijing from 2015-19.We use temporal,geospatial attribute and meteorological background field features as inputs.The wind speed field can be reconstructed at any station in the region not used in the training process to cross-validate model performance.The evaluation considers the spatial distribution of and seasonal variations in the root mean squared error(RMSE)of the reconstructed wind speed field across Beijing.The average RMSE is 1.09 m s^(−1),considerably smaller than the result(1.29 m s^(−1))obtained with inverse distance weighting(IDW)interpolation.Finally,we extract the important feature permutations by the method of mean decrease in impurity(MDI)and discuss the reasonableness of the model prediction results.MLDRM-RF is a reasonable approach with excellent potential for the improved reconstruction of historical surface wind speed fields with arbitrary grid resolutions.Such a model is needed in many wind applications,such as wind energy and aviation safety assessments.
