V. D. Bloshchinskiy, L. S. Kramareva, Yu. A. Shamilova
{"title":"Cloud Cover Detection Using a Neural Network Based on MSU-GS Instrument Data of Arktika-M No. 1 Satellite","authors":"V. D. Bloshchinskiy, L. S. Kramareva, Yu. A. Shamilova","doi":"10.1134/S102485602470043X","DOIUrl":null,"url":null,"abstract":"<p>Cloud detection in satellite imagery is one the most important problems of satellite meteorology. The accuracy of cloud detection significantly determines the quality of other hydrometeorological products. The paper presents an algorithm for detecting clouds in satellite images, which is based on a convolutional neural network with a modified U-Net architecture. Multispectral satellite imagery from the MSU-GS instrument operating onboard Arktika-M No 1 satellite are used as input data. The algorithm accuracy was estimated through machine learning metrics and comparison with reference masks compiled via manual decryption of the satellite images by an experienced image interpreter. In addition, the results are compared with similar products based on data of SEVIRI and VIIRS instruments. The accuracy of a cloud mask obtained following the suggested algorithm is 92% compared to a reference mask for sun-illuminated areas and 89% for dark areas.</p>","PeriodicalId":46751,"journal":{"name":"Atmospheric and Oceanic Optics","volume":null,"pages":null},"PeriodicalIF":0.9000,"publicationDate":"2024-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Atmospheric and Oceanic Optics","FirstCategoryId":"1085","ListUrlMain":"https://link.springer.com/article/10.1134/S102485602470043X","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"OPTICS","Score":null,"Total":0}
引用次数: 0
Abstract
Cloud detection in satellite imagery is one the most important problems of satellite meteorology. The accuracy of cloud detection significantly determines the quality of other hydrometeorological products. The paper presents an algorithm for detecting clouds in satellite images, which is based on a convolutional neural network with a modified U-Net architecture. Multispectral satellite imagery from the MSU-GS instrument operating onboard Arktika-M No 1 satellite are used as input data. The algorithm accuracy was estimated through machine learning metrics and comparison with reference masks compiled via manual decryption of the satellite images by an experienced image interpreter. In addition, the results are compared with similar products based on data of SEVIRI and VIIRS instruments. The accuracy of a cloud mask obtained following the suggested algorithm is 92% compared to a reference mask for sun-illuminated areas and 89% for dark areas.
期刊介绍：
Atmospheric and Oceanic Optics is an international peer reviewed journal that presents experimental and theoretical articles relevant to a wide range of problems of atmospheric and oceanic optics, ecology, and climate. The journal coverage includes: scattering and transfer of optical waves, spectroscopy of atmospheric gases, turbulent and nonlinear optical phenomena, adaptive optics, remote (ground-based, airborne, and spaceborne) sensing of the atmosphere and the surface, methods for solving of inverse problems, new equipment for optical investigations, development of computer programs and databases for optical studies. Thematic issues are devoted to the studies of atmospheric ozone, adaptive, nonlinear, and coherent optics, regional climate and environmental monitoring, and other subjects.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
