Sentinel-2 data classifications for the Baikal natural area

Yurii V. Avramenko; Anastasia K. Popova; Roman K. Fedorov

doi:10.1117/12.2603482

15 December 2021 Sentinel-2 data classifications for the Baikal natural area

Yurii V. Avramenko, Anastasia K. Popova, Roman K. Fedorov

Proceedings Volume 11916, 27th International Symposium on Atmospheric and Ocean Optics, Atmospheric Physics; 119168Q (2021) https://doi.org/10.1117/12.2603482
Event: 27th International Symposium on Atmospheric and Ocean Optics, Atmospheric Physics, 2021, Moscow, Russian Federation

Abstract

The territory of the Baikal Natural Territory (BNT) is quite large and inaccessible in some places. Therefore, remote sensing is the only source of regular data for research of the spatial-temporal land cover dynamics of the BNT. Regular processing and classification of land cover is required to monitor BNT. Satellite image classification is a common method of information extraction related to the structure and changes in land cover. In this work we used Sentinel-2 multispectral images for classifying land cover of the BNT. There are many methods to analyze and classify remote sensing data. The article discusses algorithms for the land cover classification: the vegetation index NDVI, machine learning based on Random Forest algorithm and the convolutional neural network xResNet50. The results of all methods are tested for compliance with the verification dataset for BNT.

Citation Download Citation

Yurii V. Avramenko, Anastasia K. Popova, and Roman K. Fedorov "Sentinel-2 data classifications for the Baikal natural area", Proc. SPIE 11916, 27th International Symposium on Atmospheric and Ocean Optics, Atmospheric Physics, 119168Q (15 December 2021); https://doi.org/10.1117/12.2603482

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available