A Convection Nowcasting Method Based on Machine Learning

Aifang Su,Yungang Chen,Liman Cui,Han Li

doi:10.1155/2020/5124274

Abstract

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.

Highlights

Convection nowcasting refers to the short-term forecasting of the convective weather system and the catastrophic convective weather they may produce, up to 0–6 hours beyond the current observation time
Convection nowcasting based on radar data mainly involves thunderstorm identification, tracking, and automated extrapolation techniques [1], e.g., the centroid tracking method [2,3,4], the tracking radar echo by correlation method [5,6,7], and the optical flow method [8,9,10,11,12,13]
Our experimental results demonstrated that the global optical flow field generated by pyramid delaminating technique can better reflect the movements of radar echoes, including nonlinear motions such as rotation, convergence, and divergence of local radar elements

Summary

A Convection Nowcasting Method Based on Machine Learning

Received 24 June 2019; Revised 6 November 2019; Accepted 20 December 2019; Published 27 January 2020. A convection nowcasting method based on machine learning was proposed. The generated optical flow field information of each pixel and the RedGreen-Blue (RGB) image information were input into the Convolutional Long Short-Term Memory (ConvLSTM) algorithm for training purposes. E 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. Based on learning through the above features, this algorithm can forecast the generation and dissipation trends of convective cells to some extent. e addition of the optical flow information can more accurately simulate nonlinear trends such as the rotation, or merging, or separation of radar echoes. e trajectories of radar echoes obtained through nowcasting are closer to their actual movements, which prolongs the valid forecasting period and improves forecast accuracy

Introduction

Data and Methodology

Results

Case Analysis

Conclusions

Disclosure