hrcak mascot   Srce   HID

Izvorni znanstveni članak
https://doi.org/10.17559/TV-20190903094335

Radar-based Hail-producing Storm Detection Using Positive Unlabeled Classification

Junzhi Shi   ORCID icon 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

Puni tekst: engleski, pdf (2 MB) str. 941-950 preuzimanja: 98* citiraj
APA 6th Edition
Shi, J., Wang, P., Wang, D. i Jia, H. (2020). Radar-based Hail-producing Storm Detection Using Positive Unlabeled Classification. Tehnički vjesnik, 27 (3), 941-950. https://doi.org/10.17559/TV-20190903094335
MLA 8th Edition
Shi, Junzhi, et al. "Radar-based Hail-producing Storm Detection Using Positive Unlabeled Classification." Tehnički vjesnik, vol. 27, br. 3, 2020, str. 941-950. https://doi.org/10.17559/TV-20190903094335. Citirano 30.10.2020.
Chicago 17th Edition
Shi, Junzhi, Ping Wang, Di Wang i Huizhen Jia. "Radar-based Hail-producing Storm Detection Using Positive Unlabeled Classification." Tehnički vjesnik 27, br. 3 (2020): 941-950. https://doi.org/10.17559/TV-20190903094335
Harvard
Shi, J., et al. (2020). 'Radar-based Hail-producing Storm Detection Using Positive Unlabeled Classification', Tehnički vjesnik, 27(3), str. 941-950. https://doi.org/10.17559/TV-20190903094335
Vancouver
Shi J, Wang P, Wang D, Jia H. Radar-based Hail-producing Storm Detection Using Positive Unlabeled Classification. Tehnički vjesnik [Internet]. 2020 [pristupljeno 30.10.2020.];27(3):941-950. https://doi.org/10.17559/TV-20190903094335
IEEE
J. Shi, P. Wang, D. Wang i H. Jia, "Radar-based Hail-producing Storm Detection Using Positive Unlabeled Classification", Tehnički vjesnik, vol.27, br. 3, str. 941-950, 2020. [Online]. https://doi.org/10.17559/TV-20190903094335

Sažetak
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.

Ključne riječi
hailstorm; machine learning; positive unlabeled learning; weather forecasting; weather radar

Hrčak ID: 239105

URI
https://hrcak.srce.hr/239105

Posjeta: 188 *