A Method of Forecasting Thunderstorms and Gale Weather Based on Multisource Convolution Neural Network
The local thunderstorms and gale weather occurring frequently has brought huge losses to the agriculture and transportation industries. This paper presents a method of forecasting the local thunderstorms and gale weather, in which a multisource convolution neural network is constructed to extract th...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8781906/ |
| _version_ | 1818562769357635584 |
|---|---|
| author | Yanping Jiang Jinliang Yao Zheng Qian |
| author_facet | Yanping Jiang Jinliang Yao Zheng Qian |
| author_sort | Yanping Jiang |
| collection | DOAJ |
| description | The local thunderstorms and gale weather occurring frequently has brought huge losses to the agriculture and transportation industries. This paper presents a method of forecasting the local thunderstorms and gale weather, in which a multisource convolution neural network is constructed to extract the features of weather-related data with multiple types from Doppler radar. To improve the discriminative power of features, Center-Loss and Softmax were jointly used as loss function in the training, and then the features obtained are combined with SVM for classification. Furthermore, a comparative experiment of multisource convolution neural network based on CNN-4, ResNet30, ResNet50, and VGG16 is designed, in which the ResNet30 achieves the highest accuracy. The experimental results show that the multisource convolution neural network avoids the limitation of using one type of data and improves the accuracy of forecasting local thunderstorms and gale. |
| first_indexed | 2024-12-14T01:08:06Z |
| format | Article |
| id | doaj.art-576fb848042f4dd1ac9cd72303c7b480 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-14T01:08:06Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-576fb848042f4dd1ac9cd72303c7b4802022-12-21T23:22:52ZengIEEEIEEE Access2169-35362019-01-01710769510769810.1109/ACCESS.2019.29320278781906A Method of Forecasting Thunderstorms and Gale Weather Based on Multisource Convolution Neural NetworkYanping Jiang0https://orcid.org/0000-0001-7233-1157Jinliang Yao1Zheng Qian2School of Computer Science, Hangzhou Dianzi University, Xiasha Higher Education Zone, Hangzhou, ChinaSchool of Computer Science, Hangzhou Dianzi University, Xiasha Higher Education Zone, Hangzhou, ChinaNingbo Meteorological Service Center, Ningbo, ChinaThe local thunderstorms and gale weather occurring frequently has brought huge losses to the agriculture and transportation industries. This paper presents a method of forecasting the local thunderstorms and gale weather, in which a multisource convolution neural network is constructed to extract the features of weather-related data with multiple types from Doppler radar. To improve the discriminative power of features, Center-Loss and Softmax were jointly used as loss function in the training, and then the features obtained are combined with SVM for classification. Furthermore, a comparative experiment of multisource convolution neural network based on CNN-4, ResNet30, ResNet50, and VGG16 is designed, in which the ResNet30 achieves the highest accuracy. The experimental results show that the multisource convolution neural network avoids the limitation of using one type of data and improves the accuracy of forecasting local thunderstorms and gale.https://ieeexplore.ieee.org/document/8781906/Feature extractionDoppler radarforecastingcenter_loss |
| spellingShingle | Yanping Jiang Jinliang Yao Zheng Qian A Method of Forecasting Thunderstorms and Gale Weather Based on Multisource Convolution Neural Network IEEE Access Feature extraction Doppler radar forecasting center_loss |
| title | A Method of Forecasting Thunderstorms and Gale Weather Based on Multisource Convolution Neural Network |
| title_full | A Method of Forecasting Thunderstorms and Gale Weather Based on Multisource Convolution Neural Network |
| title_fullStr | A Method of Forecasting Thunderstorms and Gale Weather Based on Multisource Convolution Neural Network |
| title_full_unstemmed | A Method of Forecasting Thunderstorms and Gale Weather Based on Multisource Convolution Neural Network |
| title_short | A Method of Forecasting Thunderstorms and Gale Weather Based on Multisource Convolution Neural Network |
| title_sort | method of forecasting thunderstorms and gale weather based on multisource convolution neural network |
| topic | Feature extraction Doppler radar forecasting center_loss |
| url | https://ieeexplore.ieee.org/document/8781906/ |
| work_keys_str_mv | AT yanpingjiang amethodofforecastingthunderstormsandgaleweatherbasedonmultisourceconvolutionneuralnetwork AT jinliangyao amethodofforecastingthunderstormsandgaleweatherbasedonmultisourceconvolutionneuralnetwork AT zhengqian amethodofforecastingthunderstormsandgaleweatherbasedonmultisourceconvolutionneuralnetwork AT yanpingjiang methodofforecastingthunderstormsandgaleweatherbasedonmultisourceconvolutionneuralnetwork AT jinliangyao methodofforecastingthunderstormsandgaleweatherbasedonmultisourceconvolutionneuralnetwork AT zhengqian methodofforecastingthunderstormsandgaleweatherbasedonmultisourceconvolutionneuralnetwork |