With the development of space exploration and space environment measurements,the numerous observations of solar,solar wind,and near Earth space environment have been obtained in last 20 years.The accumulation of multi...With the development of space exploration and space environment measurements,the numerous observations of solar,solar wind,and near Earth space environment have been obtained in last 20 years.The accumulation of multiple data makes it possible to better use machine learning technique,which has achieved unforeseen results in industrial applications in last decades,for developing new approaches and models in space weather investigation and prediction.In this paper,the efforts on the forecasting methods for space weather indices,events,and parameters using machine learning are briefly introduced based on the study works in recent years.These investigations indicate that machine learning,especially deep learning technique can be used in automatic characteristic identification,solar eruption prediction,space weather forecasting for solar and geomagnetic indices,and modeling of space environment parameters.展开更多
In space weather forecasting, forecast verification is necessary so that the forecast quality can be assessed. This paper provides an example of how to choose and devise verification methods and techniques according t...In space weather forecasting, forecast verification is necessary so that the forecast quality can be assessed. This paper provides an example of how to choose and devise verification methods and techniques according to different space weather forecast products. Solar proton events(SPEs) are hazardous space weather events, and forecasting them is one of the major tasks of the Space Environment Prediction Center(SEPC) at the National Space Science Center of the Chinese Academy of Sciences. Through analyzing SPE occurrence characteristics, SPE forecast properties, and verification requirements at SEPC, verification methods for SPE probability forecasts are identified, and verification results obtained. Overall, SPE probability forecasts at SEPC exhibit good accuracy, reliability, and discrimination. Compared with climatology and persistence forecasts, the SPE forecasts are more accurate. However, the forecasts for SPE onset days are substantially underestimated and need to be considerably improved.展开更多
基金Supported by National Natural Science Foundation of China(41574181)。
文摘With the development of space exploration and space environment measurements,the numerous observations of solar,solar wind,and near Earth space environment have been obtained in last 20 years.The accumulation of multiple data makes it possible to better use machine learning technique,which has achieved unforeseen results in industrial applications in last decades,for developing new approaches and models in space weather investigation and prediction.In this paper,the efforts on the forecasting methods for space weather indices,events,and parameters using machine learning are briefly introduced based on the study works in recent years.These investigations indicate that machine learning,especially deep learning technique can be used in automatic characteristic identification,solar eruption prediction,space weather forecasting for solar and geomagnetic indices,and modeling of space environment parameters.
基金supported by the National Basic Program of China (Grant No. 2012CB825600)
文摘In space weather forecasting, forecast verification is necessary so that the forecast quality can be assessed. This paper provides an example of how to choose and devise verification methods and techniques according to different space weather forecast products. Solar proton events(SPEs) are hazardous space weather events, and forecasting them is one of the major tasks of the Space Environment Prediction Center(SEPC) at the National Space Science Center of the Chinese Academy of Sciences. Through analyzing SPE occurrence characteristics, SPE forecast properties, and verification requirements at SEPC, verification methods for SPE probability forecasts are identified, and verification results obtained. Overall, SPE probability forecasts at SEPC exhibit good accuracy, reliability, and discrimination. Compared with climatology and persistence forecasts, the SPE forecasts are more accurate. However, the forecasts for SPE onset days are substantially underestimated and need to be considerably improved.
