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
The variations in the wave energy and the amplitude along the energy dispersion paths of the barotropic Rossby waves in zonally symmetric basic flow are studied by solving the wave energy equation,which expresses that...The variations in the wave energy and the amplitude along the energy dispersion paths of the barotropic Rossby waves in zonally symmetric basic flow are studied by solving the wave energy equation,which expresses that the wave energy variability is determined by the divergence of the group velocity and the energy budget from the basic flow.The results suggest that both the wave energy and the amplitude of a leading wave increase significantly in the propagating region that is located south of the jet axis and enclosed by a southern critical line and a northern turning latitude.The leading wave gains the barotropic energy from the basic flow by eddy activities.The amplitude continuously climbs up a peak at the turning latitude due to increasing wave energy and enlarging horizontal scale(shrinking total wavenumber).Both the wave energy and the amplitude eventually decrease when the trailing wave continuously approaches southward to the critical line.The trailing wave decays and its energy is continuously absorbed by the basic flow.Furthermore,both the wave energy and the amplitude oscillate with a limited range in the propagating region that is located near the jet axis and enclosed by two turning latitudes.Both the leading and trailing waves neither develop nor decay significantly.The jet works as a waveguide to allow the waves to propagate a long distance.展开更多
In recent years,with the increase in the price of cryptocurrencies,the number of malicious cryptomining software has increased significantly.With their powerful spreading ability,cryptomining malware can unknowingly o...In recent years,with the increase in the price of cryptocurrencies,the number of malicious cryptomining software has increased significantly.With their powerful spreading ability,cryptomining malware can unknowingly occupy our resources,harm our interests,and damage more legitimate assets.However,although current traditional rule-based malware detection methods have a low false alarm rate,they have a relatively low detection rate when faced with a large volume of emerging malware.Even though common machine learning-based or deep learning-based methods have certain ability to learn and detect unknown malware,the characteristics they learn are single and independent,and cannot be learned adaptively.Aiming at the above problems,we propose a deep learning model with multi-input of multi-modal features,which can simultaneously accept digital features and image features on different dimensions.The model in turn includes parallel learning of three sub-models and ensemble learning of another specific sub-model.The four sub-models can be processed in parallel on different devices and can be further applied to edge computing environments.The model can adaptively learn multi-modal features and output prediction results.The detection rate of our model is as high as 97.01%and the false alarm rate is only 0.63%.The experimental results prove the advantage and effectiveness of the proposed method.展开更多
Variations in wave energy and amplitude for Rossby waves are investigated by solving the wave energy equation for the quasigeostrophic barotropic potential vorticity model.The results suggest that compared with rays i...Variations in wave energy and amplitude for Rossby waves are investigated by solving the wave energy equation for the quasigeostrophic barotropic potential vorticity model.The results suggest that compared with rays in the nondivergent barotropic model,rays in the divergent model can have enhanced meridional and zonal propagation,accompanied by a more dramatic variability in both wave energy and amplitude,which is caused by introducing the divergence effect of the free surface in the quasigeostrophic model.For rays propagating in a region enclosed by a turning latitude and a critical latitude,the wave energy approaches the maximum value inside the region,while the amplitude approaches the maximum at the turning latitude.Waves can develop when both the wave energy and amplitude increase.For rays propagating in a region enclosed by two turning latitudes,the wave energy approaches the minimum value at one turning latitude and the maximum value at the other latitude,while the total wavenumber approaches the maximum value inside the region.The resulting amplitude increases if the total wavenumber decreases or the wave energy increases more significantly and decreases if the total wavenumber increases or the wave energy decreases more significantly.The matched roles of the energy from the basic flow and the divergence of the group velocity contribute to the slightly oscillating wave energy,which causes a slightly oscillating amplitude as well as the slightly oscillating total wavenumber.展开更多
In this paper, we propose a deep spatio-temporal forecasting model (DeepSTF) for multi-site weather prediction post-processing by using both temporal andspatial information. In our proposed framework, the spatio-temp...In this paper, we propose a deep spatio-temporal forecasting model (DeepSTF) for multi-site weather prediction post-processing by using both temporal andspatial information. In our proposed framework, the spatio-temporal information ismodeled by a CNN (convolutional neural network) module and an encoder-decoderstructure with the attention mechanism. The novelty of our work lies in that our modeltakes full account of temporal and spatial characteristics and obtain forecasts of multiple meteorological stations simultaneously by using the same framework. We applythe DeepSTF model to short-term weather prediction at 226 meteorological stations inBeijing. It significantly improves the short-term forecasts compared to other widelyused benchmark models including the Model Output Statistics method. In order toevaluate the uncertainty of the model parameters, we estimate the confidence intervals by bootstrapping. The results show that the prediction accuracy of the DeepSTFmodel has strong stability. Finally, we evaluate the impact of seasonal changes and topographical differences on the accuracy of the model predictions. The results indicatethat our proposed model has high prediction accuracy.展开更多
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This study was jointly funded by the National Natural Science Foundation of China(Grant Nos.41505042 and 41805041)the National Program on Global Change and Air−Sea Interaction(Grant No.GASI-IPOVAI-03)+1 种基金the National Basic Research Program of China(Grant Nos.2015CB953601 and 2014CB953903)the Fundamental Research Funds for the Central Universities.
文摘The variations in the wave energy and the amplitude along the energy dispersion paths of the barotropic Rossby waves in zonally symmetric basic flow are studied by solving the wave energy equation,which expresses that the wave energy variability is determined by the divergence of the group velocity and the energy budget from the basic flow.The results suggest that both the wave energy and the amplitude of a leading wave increase significantly in the propagating region that is located south of the jet axis and enclosed by a southern critical line and a northern turning latitude.The leading wave gains the barotropic energy from the basic flow by eddy activities.The amplitude continuously climbs up a peak at the turning latitude due to increasing wave energy and enlarging horizontal scale(shrinking total wavenumber).Both the wave energy and the amplitude eventually decrease when the trailing wave continuously approaches southward to the critical line.The trailing wave decays and its energy is continuously absorbed by the basic flow.Furthermore,both the wave energy and the amplitude oscillate with a limited range in the propagating region that is located near the jet axis and enclosed by two turning latitudes.Both the leading and trailing waves neither develop nor decay significantly.The jet works as a waveguide to allow the waves to propagate a long distance.
基金supported by the Key Research and Development Program of Shandong Province(Soft Science Project)(2020RKB01364).
文摘In recent years,with the increase in the price of cryptocurrencies,the number of malicious cryptomining software has increased significantly.With their powerful spreading ability,cryptomining malware can unknowingly occupy our resources,harm our interests,and damage more legitimate assets.However,although current traditional rule-based malware detection methods have a low false alarm rate,they have a relatively low detection rate when faced with a large volume of emerging malware.Even though common machine learning-based or deep learning-based methods have certain ability to learn and detect unknown malware,the characteristics they learn are single and independent,and cannot be learned adaptively.Aiming at the above problems,we propose a deep learning model with multi-input of multi-modal features,which can simultaneously accept digital features and image features on different dimensions.The model in turn includes parallel learning of three sub-models and ensemble learning of another specific sub-model.The four sub-models can be processed in parallel on different devices and can be further applied to edge computing environments.The model can adaptively learn multi-modal features and output prediction results.The detection rate of our model is as high as 97.01%and the false alarm rate is only 0.63%.The experimental results prove the advantage and effectiveness of the proposed method.
基金This study was jointly funded by the National Natural Science Foundation of China(Grant Nos.41805041 and 41505042)the National Program on Global Change and Air-Sea Interaction(GASI-IPOVAI-03)+1 种基金the National Basis Research Program of China(2015CB953601 and 2014CB953903)the Fundamental Research Funds for the Central Universities.
文摘Variations in wave energy and amplitude for Rossby waves are investigated by solving the wave energy equation for the quasigeostrophic barotropic potential vorticity model.The results suggest that compared with rays in the nondivergent barotropic model,rays in the divergent model can have enhanced meridional and zonal propagation,accompanied by a more dramatic variability in both wave energy and amplitude,which is caused by introducing the divergence effect of the free surface in the quasigeostrophic model.For rays propagating in a region enclosed by a turning latitude and a critical latitude,the wave energy approaches the maximum value inside the region,while the amplitude approaches the maximum at the turning latitude.Waves can develop when both the wave energy and amplitude increase.For rays propagating in a region enclosed by two turning latitudes,the wave energy approaches the minimum value at one turning latitude and the maximum value at the other latitude,while the total wavenumber approaches the maximum value inside the region.The resulting amplitude increases if the total wavenumber decreases or the wave energy increases more significantly and decreases if the total wavenumber increases or the wave energy decreases more significantly.The matched roles of the energy from the basic flow and the divergence of the group velocity contribute to the slightly oscillating wave energy,which causes a slightly oscillating amplitude as well as the slightly oscillating total wavenumber.
基金This work is supported by the National Key Research and Development Program of China(Grant Nos.2017YFC0209804 and 2018YFF0300104)Beijing Academy of Artificial Intelligence(BAAI)+1 种基金the National Natural Science Foundation of China(Grant No.11421101)the Open Research Fund of Shenzhen Research Institute of Big Data(Grant No.2019ORF01001).
文摘In this paper, we propose a deep spatio-temporal forecasting model (DeepSTF) for multi-site weather prediction post-processing by using both temporal andspatial information. In our proposed framework, the spatio-temporal information ismodeled by a CNN (convolutional neural network) module and an encoder-decoderstructure with the attention mechanism. The novelty of our work lies in that our modeltakes full account of temporal and spatial characteristics and obtain forecasts of multiple meteorological stations simultaneously by using the same framework. We applythe DeepSTF model to short-term weather prediction at 226 meteorological stations inBeijing. It significantly improves the short-term forecasts compared to other widelyused benchmark models including the Model Output Statistics method. In order toevaluate the uncertainty of the model parameters, we estimate the confidence intervals by bootstrapping. The results show that the prediction accuracy of the DeepSTFmodel has strong stability. Finally, we evaluate the impact of seasonal changes and topographical differences on the accuracy of the model predictions. The results indicatethat our proposed model has high prediction accuracy.
