Neural Network-Based Analysis of Forest Fire Aftermath in Class-Imbalanced Remote Sensing Earth Image Classification

Today's agricultural sector is characterized by an important role of accurate mapping and monitoring of agriculture with the help of satellite imagery, which allows to optimize the use of resources, to plan crop areas and to forecast productivity. Classification of satellite images with unbalan...

Full description

Saved in:
Bibliographic Details
Main Authors: V. Hnatushenko, D. Soldatenko
Format: Article
Language:English
Published: Copernicus Publications 2024-11-01
Series:The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Online Access:https://isprs-archives.copernicus.org/articles/XLVIII-3-2024/223/2024/isprs-archives-XLVIII-3-2024-223-2024.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850199247643738112
author V. Hnatushenko
V. Hnatushenko
V. Hnatushenko
D. Soldatenko
author_facet V. Hnatushenko
V. Hnatushenko
V. Hnatushenko
D. Soldatenko
author_sort V. Hnatushenko
collection DOAJ
description Today's agricultural sector is characterized by an important role of accurate mapping and monitoring of agriculture with the help of satellite imagery, which allows to optimize the use of resources, to plan crop areas and to forecast productivity. Classification of satellite images with unbalanced sample distribution is a critical problem in this regard. Traditional machine learning algorithms in particular have limitations in dealing with sample imbalance. In this paper, we proposed convolution neural networks for semantic segmentation, where sample imbalance is considered based on a particular loss function coupled with data augmentation. To illustrate our method, we use Sentinel-2 remote sensing (RS) images covering a number of regions in Ukraine, and then we create an image dataset of the region and for training and testing make data augmentation. The models with different architectural features were investigated.<br />The results demonstrate that the proposed CNN has a higher classification accuracy than the ones discussed in the paper: the classification accuracy on the test dataset reached 96.7% with intersection-over-union values of up to 89.7%. This opens the way for further research in the direction of refining algorithms for classify satellite data with an imbalanced class structure.
format Article
id doaj-art-2f0e0189bfbc40579cf97018ab76407e
institution OA Journals
issn 1682-1750
2194-9034
language English
publishDate 2024-11-01
publisher Copernicus Publications
record_format Article
series The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
spelling doaj-art-2f0e0189bfbc40579cf97018ab76407e2025-08-20T02:12:41ZengCopernicus PublicationsThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences1682-17502194-90342024-11-01XLVIII-3-202422322910.5194/isprs-archives-XLVIII-3-2024-223-2024Neural Network-Based Analysis of Forest Fire Aftermath in Class-Imbalanced Remote Sensing Earth Image ClassificationV. Hnatushenko0V. Hnatushenko1V. Hnatushenko2D. Soldatenko3Dept. Information Technologies and Systems, Ukrainian State University of Science and Technologies, Dnipro, UkraineInstitute of Photogrammetry and GeoInformation, Leibniz Universität Hannover, GermanyDept. Information Technologies and Computer Engineering, Dnipro University of Technology, Dnipro, UkraineDept. Information Technologies and Systems, Ukrainian State University of Science and Technologies, Dnipro, UkraineToday's agricultural sector is characterized by an important role of accurate mapping and monitoring of agriculture with the help of satellite imagery, which allows to optimize the use of resources, to plan crop areas and to forecast productivity. Classification of satellite images with unbalanced sample distribution is a critical problem in this regard. Traditional machine learning algorithms in particular have limitations in dealing with sample imbalance. In this paper, we proposed convolution neural networks for semantic segmentation, where sample imbalance is considered based on a particular loss function coupled with data augmentation. To illustrate our method, we use Sentinel-2 remote sensing (RS) images covering a number of regions in Ukraine, and then we create an image dataset of the region and for training and testing make data augmentation. The models with different architectural features were investigated.<br />The results demonstrate that the proposed CNN has a higher classification accuracy than the ones discussed in the paper: the classification accuracy on the test dataset reached 96.7% with intersection-over-union values of up to 89.7%. This opens the way for further research in the direction of refining algorithms for classify satellite data with an imbalanced class structure.https://isprs-archives.copernicus.org/articles/XLVIII-3-2024/223/2024/isprs-archives-XLVIII-3-2024-223-2024.pdf
spellingShingle V. Hnatushenko
V. Hnatushenko
V. Hnatushenko
D. Soldatenko
Neural Network-Based Analysis of Forest Fire Aftermath in Class-Imbalanced Remote Sensing Earth Image Classification
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
title Neural Network-Based Analysis of Forest Fire Aftermath in Class-Imbalanced Remote Sensing Earth Image Classification
title_full Neural Network-Based Analysis of Forest Fire Aftermath in Class-Imbalanced Remote Sensing Earth Image Classification
title_fullStr Neural Network-Based Analysis of Forest Fire Aftermath in Class-Imbalanced Remote Sensing Earth Image Classification
title_full_unstemmed Neural Network-Based Analysis of Forest Fire Aftermath in Class-Imbalanced Remote Sensing Earth Image Classification
title_short Neural Network-Based Analysis of Forest Fire Aftermath in Class-Imbalanced Remote Sensing Earth Image Classification
title_sort neural network based analysis of forest fire aftermath in class imbalanced remote sensing earth image classification
url https://isprs-archives.copernicus.org/articles/XLVIII-3-2024/223/2024/isprs-archives-XLVIII-3-2024-223-2024.pdf
work_keys_str_mv AT vhnatushenko neuralnetworkbasedanalysisofforestfireaftermathinclassimbalancedremotesensingearthimageclassification
AT vhnatushenko neuralnetworkbasedanalysisofforestfireaftermathinclassimbalancedremotesensingearthimageclassification
AT vhnatushenko neuralnetworkbasedanalysisofforestfireaftermathinclassimbalancedremotesensingearthimageclassification
AT dsoldatenko neuralnetworkbasedanalysisofforestfireaftermathinclassimbalancedremotesensingearthimageclassification