Technical gazette, Vol. 27 No. 3, 2020.
Original scientific paper
https://doi.org/10.17559/TV-20190903094335
Radar-based Hail-producing Storm Detection Using Positive Unlabeled Classification
Junzhi Shi
orcid.org/0000-0001-8701-981X
; School of Electrical and Information Engineering, Tianjin University, Tianjin, 300072, China
Ping Wang
; School of Electrical and Information Engineering, Tianjin University, Tianjin, 300072, China
Di Wang
; School of Electrical and Information Engineering, Tianjin University, Tianjin, 300072, China
Huizhen Jia
; Tianjin Bureau of Meteorology, Tianjin 300074, China
Abstract
Machine learning methods have been widely used in many fields of weather forecasting. However, some severe weather, such as hailstorm, is difficult to be completely and accurately recorded. These inaccurate data sets will affect the performance of machine-learning-based forecasting models. In this paper, a weather-radar-based hail-producing storm detection method is proposed. This method utilizes the bagging class-weighted support vector machine to learn from partly labeled hail case data and the other unlabeled data, with features extracted from radar and sounding data. The real case data from three radars of North China are used for evaluation. Results suggest that the proposed method could improve both the forecast accuracy and the forecast lead time comparing with the commonly used radar parameter methods. Besides, the proposed method works better than the method with the supervised learning model in any situation, especially when the number of positive samples contaminated in the unlabeled set is large.
Keywords
hailstorm; machine learning; positive unlabeled learning; weather forecasting; weather radar
Hrčak ID:
239105
URI
Publication date:
14.6.2020.
Visits: 2.099 *