Deep Learning Technology for Automatic Burned Area Extraction Using Satellite High Spatial Resolution Images

Kashtan, Vita; Hnatushenko, Volodymyr

doi:10.1007/978-3-031-16203-9_37

Cited by 5 publications

(3 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…before and after the event) (e.g. [38], [39], [40], [41]). The most common architectures for this task is the U-Net and simple multi-layer Convolutional Neural Networks (CNNs).…”

Section: B Methods For Burnt Area Mappingmentioning

confidence: 99%

Deep Learning for Downscaling Remote Sensing Images: Fusion and super-resolution

Sdraka

Papoutsis

Psomas

et al. 2022

IEEE Geosci. Remote Sens. Mag.

View full text Add to dashboard Cite

Over the last decade there has been an increasing frequency and intensity of wildfires across the globe, posing significant threats to human and animal lives, ecosystems, and socio-economic stability. Therefore urgent action is required to mitigate their devastating impact and safeguard Earth's natural resources. Robust Machine Learning methods combined with the abundance of high-resolution satellite imagery can provide accurate and timely mappings of the affected area in order to assess the scale of the event, identify the impacted assets and prioritize and allocate resources effectively for the proper restoration of the damaged region. In this work, we create and introduce a machine-learning ready dataset we name FLOGA (Forest wiLdfire Observations for the Greek Area). This dataset is unique as it comprises of satellite imagery acquired before and after a wildfire event, it contains information from Sentinel-2 and MODIS modalities with variable spatial and spectral resolution, and contains a large number of events where the corresponding burnt area ground truth has been annotated by domain experts. FLOGA covers the wider region of Greece, which is characterized by a Mediterranean landscape and climatic conditions. We use FLOGA to provide a thorough comparison of multiple Machine Learning and Deep Learning algorithms for the automatic extraction of burnt areas, approached as a change detection task. We also compare the results to those obtained using standard specialized spectral indices for burnt area mapping. Finally, we propose a novel Deep Learning model, namely BAM-CD. Our benchmark results demonstrate the efficacy of the proposed technique in the automatic extraction of burnt areas, outperforming all other methods in terms of accuracy and robustness. Our dataset and code are publicly available at: https://github.com/Orion-AI-Lab/FLOGA.

show abstract

“…before and after the event) (e.g. [38], [39], [40], [41]). The most common architectures for this task is the U-Net and simple multi-layer Convolutional Neural Networks (CNNs).…”

Section: B Methods For Burnt Area Mappingmentioning

confidence: 99%

Deep Learning for Downscaling Remote Sensing Images: Fusion and super-resolution

Sdraka

Papoutsis

Psomas

et al. 2022

IEEE Geosci. Remote Sens. Mag.

View full text Add to dashboard Cite

show abstract

“…However, it should be noted that under relatively stable forest vegetation conditions, the overall flammability of forests is primarily determined by weather conditions. Periods of atmospheric and soil moisture deficiency create conditions in which forest fires can easily develop (Kashtan and Hnatushenko, 2022). In times without rain for more than a month, the drought can become critical, and fires can get out of control.…”

Section: Introductionmentioning

confidence: 99%

Enhancing the Quality of CNN-Based Burned Area Detection in Satellite Imagery Through Data Augmentation

Hnatushenko,

Soldatenko

et al. 2023

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. This study aims to enhance the quality of detecting burned areas in satellite imagery using deep learning by optimizing the training dataset volume through the application of various augmentation methods. The study analyzes the impact of image flipping, rotation, and noise addition on the overall accuracy for different classes of burned areas in a forest: fire, burned, smoke and background. Results demonstrate that while single augmentation techniques such as flipping and rotation alone did not result in significant improvements, a combined approach and the addition of noise resulted in an enhancement of the classification accuracy. Moreover, the study shows that augmenting the dataset through the use of multiple augmentation methods concurrently, resulting in a fivefold increase in input data, also enhanced the recognition accuracy. The study also highlights the need for further research in developing more efficient CNN models and in experimenting with additional augmentation methods to improve the accuracy of burned area detection, which would benefit environmental protection and emergency response services.

show abstract

“…Introduction. Every year, the world witnesses the devasta tion caused by natural disasters such as forest fires [1], earth quakes, floods, and hurricanes. In addition, military conflicts [2] and armed clashes cause significant economic damage and intangible losses [3].…”

mentioning

confidence: 99%

Automated building damage detection on digital imagery using machine learning

Kashtan,

Hnatushenko

2023

Nauk. visn. nat. hirn. univ.

View full text Add to dashboard Cite

Purpose. To develop an automated method based on machine learning for accurate detection of features of a damaged building on digital imagery. Methodology. This article presents an approach that employs a combination of unsupervised machine learning techniques, specifically Principal Component Analysis (PCA), K-means clustering, and Density-Based Spatial Clustering of Applications with Noise (DBSCAN), to identify building damage resulting from military conflicts. The PCA method is utilized to identify principal vectors representing the directions of maximum variance in the data. Subsequently, the K-means method is applied to cluster the feature vector space, with the predefined number of clusters reflecting the number of principal vectors. Each cluster represents a group of similar blocks of image differences, which helps to identify significant features associated with fractures. Finally, the DBSCAN method is employed to identify areas where points with similar characteristics are located. Subsequently, a binary fracture mask is generated, with pixels exceeding the threshold being identified as fractures. Findings. The introduced methodology attains an accuracy rate of 98.13 %, surpassing the performance of conventional methods such as DBSCAN, PCA, and K-means. Furthermore, the method exhibits a recall of 82.38 %, signifying its ability to effectively detect a substantial proportion of positive examples. Precision of 58.54 % underscores the methodology’s capability to minimize false positives. The F1 Score of 70.90 % demonstrates a well-balanced performance between precision and recall. Originality. DBSCAN, PCA and K-means methods have been further developed in the context of automated detection of building destruction in aerospace images. This allows us to significantly increase the accuracy and efficiency of monitoring territories, including those affected by the consequences of military aggression. Practical value. The results obtained can be used to improve automated monitoring systems for urban development and can also serve as the basis for the development of effective strategies for the restoration and reconstruction of damaged infrastructure.

show abstract

Deep Learning Technology for Automatic Burned Area Extraction Using Satellite High Spatial Resolution Images

Cited by 5 publications

References 33 publications

Deep Learning for Downscaling Remote Sensing Images: Fusion and super-resolution

Deep Learning for Downscaling Remote Sensing Images: Fusion and super-resolution

Enhancing the Quality of CNN-Based Burned Area Detection in Satellite Imagery Through Data Augmentation

Automated building damage detection on digital imagery using machine learning

Contact Info

Product

Resources

About