{"title":"A Method for Object-oriented Detection of Deep Convection from Geostationary Satellite Imagery Using Machine Learning","authors":"A. E. Shishov","doi":"10.3103/s1068373924040071","DOIUrl":null,"url":null,"abstract":"<h3 data-test=\"abstract-sub-heading\">Abstract</h3><p>Due to high spatial and temporal resolution, geostationary meteorological satellite imagery is a valuable source of information on the development of deep convective clouds and related severe weather events. Some methods for automatic deep convection detection from satellite data provide a satisfactory probability of detection for independent datasets, but are characterized by a high false alarm rate. The paper gives a description of an algorithm for automatic detection of deep convective clouds with satellite imagery using gradient boosting, logistic regression, and artificial neural network models. The results of validation of the proposed method using dependent and independent data of ground-based observations for the period 2013–2020 are presented. A low false alarm rate and high probability of detection suggest that the algorithm can be used in the operational mode.</p>","PeriodicalId":49581,"journal":{"name":"Russian Meteorology and Hydrology","volume":"70 1","pages":""},"PeriodicalIF":0.6000,"publicationDate":"2024-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Russian Meteorology and Hydrology","FirstCategoryId":"89","ListUrlMain":"https://doi.org/10.3103/s1068373924040071","RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"METEOROLOGY & ATMOSPHERIC SCIENCES","Score":null,"Total":0}
引用次数: 0
Abstract
Due to high spatial and temporal resolution, geostationary meteorological satellite imagery is a valuable source of information on the development of deep convective clouds and related severe weather events. Some methods for automatic deep convection detection from satellite data provide a satisfactory probability of detection for independent datasets, but are characterized by a high false alarm rate. The paper gives a description of an algorithm for automatic detection of deep convective clouds with satellite imagery using gradient boosting, logistic regression, and artificial neural network models. The results of validation of the proposed method using dependent and independent data of ground-based observations for the period 2013–2020 are presented. A low false alarm rate and high probability of detection suggest that the algorithm can be used in the operational mode.
期刊介绍：
Russian Meteorology and Hydrology is a peer reviewed journal that covers topical issues of hydrometeorological science and practice: methods of forecasting weather and hydrological phenomena, climate monitoring issues, environmental pollution, space hydrometeorology, agrometeorology.
京公网安备 11010802042870号
京ICP备2023020795号-1
分享
求助内容：
应助结果提醒方式：
扫码关注我们
