Classified Early Warning and Forecast of Severe Convective Weather Based on LightGBM Algorithm

Xinwei Liu,Bolong Duan,Wubin Huang,Haixia Duan,Runxia Guo

doi:10.4236/acs.2021.112017

Abstract

Severe convective weather can lead to a variety of disasters, but they are still difficult to be pre-warned and forecasted in the meteorological operation. This study generates a model based on the light gradient boosting machine (LightGBM) algorithm using C-band radar echo products and ground observations, to identify and classify three major types of severe convective weather (i.e., hail, short-term heavy rain (STHR), convective gust (CG)). The model evaluations show the LightGBM model performs well in the training set (2011-2017) and the testing set (2018) with the overall false identification ratio (FIR) of only 4.9% and 7.0%, respectively. Furthermore, the average probability of detection (POD), critical success index (CSI) and false alarm ratio (FAR) for the three types of severe convective weather in two sample sets are over 85%, 65% and lower than 30%, respectively. The LightGBM model and the storm cell identification and tracking (SCIT) product are then used to forecast the severe convective weather 15 - 60 minutes in advance. The average POD, CSI and FAR for the forecasts of the three types of severe convective weather are 57.4%, 54.7% and 38.4%, respectively, which are significantly higher than those of the manual work. Among the three types of severe convective weather, the STHR has the highest POD and CSI and the lowest FAR, while the skill scores for the hail and CG are similar. Therefore, the LightGBM model constructed in this paper is able to identify, classify and forecast the three major types of severe convective weather automatically with relatively high accuracy, and has a broad application prospect in the future automatic meteorological operation.

Highlights

Severe convective weather usually refers to kinds of disastrous weather generated by deep moist convections, such as hail, gale, tornado and heavy precipitation [1]
The feature engineering in the LightGBM modeling will find the characteristics of independent variable that can best reflect the essence of the dependent variables to classify samples, and allocate the weights of the independent variables in the calculation according to their importance [30]
This study constructs a LightGBM model based on the C-band radar-echo data to identify, classify and forecast three major types of severe convective weather

Summary

Introduction

Severe convective weather usually refers to kinds of disastrous weather generated by deep moist convections, such as hail, gale, tornado and heavy precipitation [1]. There is no unified criterion for the definition of severe convective weather, the severe convective weather defined by the Central Meteorological Observatory of China Meteorological Administration refers to the event with any or several following weather conditions: hail with a diameter of 5 mm or above on the ground, tornado at any level on land, convective wind gust (CG) of more than 17 m∙s−1 and short-term heavy rainfall (STHR) of 20 mm∙h−1 or above [2]. Since the severe convective weather has strong destructiveness and often brings great harm to industry, agriculture and people’s safety, its nowcasting and early warning play a great important role in the meteorological disaster prevention and mitigation. It is urgent to improve the forecast and early warning skills of severe convective weather in China and enhance the services of disaster prevention and mitigation

Methods

Results

Discussion

Conclusion