A Convection Nowcasting Method Based on Machine Learning
In this study, a convection nowcasting method based on machine learning was proposed. First, the historical data were back-calculated using the pyramid optical flow method. Next, the generated optical flow field information of each pixel and the Red-Green-Blue (RGB) image information were input into...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2020-01-01
|
| Series: | Advances in Meteorology |
| Online Access: | http://dx.doi.org/10.1155/2020/5124274 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832547179335516160 |
|---|---|
| author | Aifang Su Han Li Liman Cui Yungang Chen |
| author_facet | Aifang Su Han Li Liman Cui Yungang Chen |
| author_sort | Aifang Su |
| collection | DOAJ |
| description | In this study, a convection nowcasting method based on machine learning was proposed. First, the historical data were back-calculated using the pyramid optical flow method. Next, the generated optical flow field information of each pixel and the Red-Green-Blue (RGB) image information were input into the Convolutional Long Short-Term Memory (ConvLSTM) algorithm for training purposes. During the extrapolation process, dynamic characteristics such as the rotation, convergence, and divergence in the optical flow field were also used as predictors to form an optimal nowcasting model. The test analysis demonstrated that the algorithm combined the image feature extraction ability of the convolutional neural network (CNN) and the sequential learning ability of the long short-term memory network (LSTM) model to establish an end-to-end deep learning network, which could deeply extract high-order features of radar echoes such as structural texture, spatial correlation, and temporal evolution compared with the traditional algorithm. Based on learning through the above features, this algorithm can forecast the generation and dissipation trends of convective cells to some extent. The addition of the optical flow information can more accurately simulate nonlinear trends such as the rotation, or merging, or separation of radar echoes. The trajectories of radar echoes obtained through nowcasting are closer to their actual movements, which prolongs the valid forecasting period and improves forecast accuracy. |
| format | Article |
| id | doaj-art-cb289d651551493dbd3bbced2f25d39d |
| institution | Kabale University |
| issn | 1687-9309 1687-9317 |
| language | English |
| publishDate | 2020-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Advances in Meteorology |
| spelling | doaj-art-cb289d651551493dbd3bbced2f25d39d2025-02-03T06:45:47ZengWileyAdvances in Meteorology1687-93091687-93172020-01-01202010.1155/2020/51242745124274A Convection Nowcasting Method Based on Machine LearningAifang Su0Han Li1Liman Cui2Yungang Chen3Key Laboratory of Agrometeorological Safeguard Application Technique, CMA, Zhengzhou 450003, ChinaKey Laboratory of Agrometeorological Safeguard Application Technique, CMA, Zhengzhou 450003, ChinaKey Laboratory of Agrometeorological Safeguard Application Technique, CMA, Zhengzhou 450003, ChinaBeijing Presky Technology Co., Ltd., Beijing 100195, ChinaIn this study, a convection nowcasting method based on machine learning was proposed. First, the historical data were back-calculated using the pyramid optical flow method. Next, the generated optical flow field information of each pixel and the Red-Green-Blue (RGB) image information were input into the Convolutional Long Short-Term Memory (ConvLSTM) algorithm for training purposes. During the extrapolation process, dynamic characteristics such as the rotation, convergence, and divergence in the optical flow field were also used as predictors to form an optimal nowcasting model. The test analysis demonstrated that the algorithm combined the image feature extraction ability of the convolutional neural network (CNN) and the sequential learning ability of the long short-term memory network (LSTM) model to establish an end-to-end deep learning network, which could deeply extract high-order features of radar echoes such as structural texture, spatial correlation, and temporal evolution compared with the traditional algorithm. Based on learning through the above features, this algorithm can forecast the generation and dissipation trends of convective cells to some extent. The addition of the optical flow information can more accurately simulate nonlinear trends such as the rotation, or merging, or separation of radar echoes. The trajectories of radar echoes obtained through nowcasting are closer to their actual movements, which prolongs the valid forecasting period and improves forecast accuracy.http://dx.doi.org/10.1155/2020/5124274 |
| spellingShingle | Aifang Su Han Li Liman Cui Yungang Chen A Convection Nowcasting Method Based on Machine Learning Advances in Meteorology |
| title | A Convection Nowcasting Method Based on Machine Learning |
| title_full | A Convection Nowcasting Method Based on Machine Learning |
| title_fullStr | A Convection Nowcasting Method Based on Machine Learning |
| title_full_unstemmed | A Convection Nowcasting Method Based on Machine Learning |
| title_short | A Convection Nowcasting Method Based on Machine Learning |
| title_sort | convection nowcasting method based on machine learning |
| url | http://dx.doi.org/10.1155/2020/5124274 |
| work_keys_str_mv | AT aifangsu aconvectionnowcastingmethodbasedonmachinelearning AT hanli aconvectionnowcastingmethodbasedonmachinelearning AT limancui aconvectionnowcastingmethodbasedonmachinelearning AT yungangchen aconvectionnowcastingmethodbasedonmachinelearning AT aifangsu convectionnowcastingmethodbasedonmachinelearning AT hanli convectionnowcastingmethodbasedonmachinelearning AT limancui convectionnowcastingmethodbasedonmachinelearning AT yungangchen convectionnowcastingmethodbasedonmachinelearning |