Efficient 3D convolutional neural networks for Sentinel-2 land cover classification with limited ground truth data
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11310%2F25%3A10504234" target="_blank" >RIV/00216208:11310/25:10504234 - isvavai.cz</a>
Result on the web
<a href="https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=gDLXnXS3_Q" target="_blank" >https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=gDLXnXS3_Q</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1080/22797254.2025.2512531" target="_blank" >10.1080/22797254.2025.2512531</a>
Alternative languages
Result language
angličtina
Original language name
Efficient 3D convolutional neural networks for Sentinel-2 land cover classification with limited ground truth data
Original language description
This paper focuses on an innovative application of deep learning (DL) techniques, particularly 3D convolutional neural networks (CNNs), for land cover classification using multispectral Sentinel-2 (S-2) data. In this study, we evaluated the performance of window-pixel-wise 2D, 3D, and 3D Multiscale CNN architectures for land cover classification. 3D and 3D multiscale CNNs were using the spectral dimension as the third dimension for convolutions. Methodology was applied to classify large area (23,217 km2) in Czechia according to the Land use, land-use change and forestry (LULUCF) categories, a key sector in greenhouse gas inventories. The input dataset included S-2 data, along with NDVI, NDVI variance, and SRTM elevation data, all resampled to the 10 m S-2 grid and forming multi-dimensional input 5 x 5 pixel patches. The results show that a 3D CNN with 3 x 3 x 3 spatial-spectral filters and classical training achieved the best F1 score of 0.84, outperforming other proposed CNN architectures and a baseline Random Forest classifier. The study highlights the ability of 3D CNNs to integrate spatial-spectral information, making them highly effective for multispectral data analysis, even with limited (small) training ground truth datasets. This approach provides valuable information for researchers seeking to optimize DL methods for land cover classification, particularly for applications aligned with the LULUCF frameworks.
Czech name
—
Czech description
—
Classification
Type
J<sub>imp</sub> - Article in a specialist periodical, which is included in the Web of Science database
CEP classification
—
OECD FORD branch
10508 - Physical geography
Result continuities
Project
—
Continuities
S - Specificky vyzkum na vysokych skolach<br>I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace
Others
Publication year
2025
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Name of the periodical
Europen Journal of Remote Sensing
ISSN
2279-7254
e-ISSN
2279-7254
Volume of the periodical
58
Issue of the periodical within the volume
1
Country of publishing house
IT - ITALY
Number of pages
20
Pages from-to
2512531
UT code for WoS article
001502969900001
EID of the result in the Scopus database
2-s2.0-105007604034