Flood Detection Using Multi-Modal and Multi-Temporal Images: A Comparative Study

Islam, Kazi Aminul; Uddin, M.S.; Kwan, Chiman; Li, Jiang

doi:10.3390/rs12152455

Cited by 30 publications

(8 citation statements)

References 38 publications

(60 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The classification is carried out on a post-event SAR acquisition. An interesting comparative study on the performance of ML and DL frameworks has been proposed in [123].…”

Section: Other Methodologies 351 Multi-sensor Data Fusionmentioning

confidence: 99%

Flood Detection with SAR: A Review of Techniques and Datasets

Amitrano,

Di Martino,

Di Simone

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

Floods are among the most severe and impacting natural disasters. Their occurrence rate and intensity have been significantly increasing worldwide in the last years due to climate change and urbanization, bringing unprecedented effects on human lives and activities. Hence, providing a prompt response to flooding events is of crucial relevance for humanitarian, social and economic reasons. Satellite remote sensing using synthetic aperture radar (SAR) offers a great deal of support in facing flood events and mitigating their effects on a global scale. As opposed to multi-spectral sensors, SAR offers important advantages, as it enables Earth’s surface imaging regardless of weather and sunlight illumination conditions. In the last decade, the increasing availability of SAR data, even at no cost, thanks to the efforts of international and national space agencies, has been deeply stimulating research activities in every Earth observation field, including flood mapping and monitoring, where advanced processing paradigms, e.g., fuzzy logic, machine learning, data fusion, have been applied, demonstrating their superiority with respect to traditional classification strategies. However, a fair assessment of the performance and reliability of flood mapping techniques is of key importance for an efficient disasters response and, hence, should be addressed carefully and on a quantitative basis trough synthetic quality metrics and high-quality reference data. To this end, the recent development of open SAR datasets specifically covering flood events with related ground-truth reference data can support thorough and objective validation as well as reproducibility of results. Notwithstanding, SAR-based flood monitoring still suffers from severe limitations, especially in vegetated and urban areas, where complex scattering mechanisms can impair an accurate extraction of water regions. All such aspects, including classification methodologies, SAR datasets, validation strategies, challenges and future perspectives for SAR-based flood mapping are described and discussed.

show abstract

“…The classification is carried out on a post-event SAR acquisition. An interesting comparative study on the performance of ML and DL frameworks has been proposed in [123].…”

Section: Other Methodologies 351 Multi-sensor Data Fusionmentioning

confidence: 99%

Flood Detection with SAR: A Review of Techniques and Datasets

Amitrano,

Di Martino,

Di Simone

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Similarly, in [10], images from both Sentinel-1 and Sentinel-2, as well as CNN models, are used to detect floods in these images, achieving an accuracy of 80%. Furthermore, [11] compares several machine learning algorithms (neural networks and SVM) with CNNs for flood detection in radar images. In [12], the performance of a multi-modal model that integrates a CNN with a transformer is compared with that of singular models, such as random forest, neural network, SVM, and CNN.…”

Section: Introductionmentioning

confidence: 99%

Vision Transformer for Flood Detection Using Satellite Images from Sentinel-1 and Sentinel-2

Chamatidis,

Istrati,

Lagaros

2024

Water

View full text Add to dashboard Cite

Floods are devastating phenomena that occur almost all around the world and are responsible for significant losses, in terms of both human lives and economic damages. When floods occur, one of the challenges that emergency response agencies face is the identification of the flooded area so that access points and safe routes can be determined quickly. This study presents a flood detection methodology that combines transfer learning with vision transformers and satellite images from open datasets. Transformers are powerful models that have been successfully applied in Natural Language Processing (NLP). A variation of this model is the vision transformer (ViT), which can be applied to image classification tasks. The methodology is applied and evaluated for two types of satellite images: Synthetic Aperture Radar (SAR) images from Sentinel-1 and Multispectral Instrument (MSI) images from Sentinel-2. By using a pre-trained vision transformer and transfer learning, the model is fine-tuned on these two datasets to train the models to determine whether the images contain floods. It is found that the proposed methodology achieves an accuracy of 84.84% on the Sentinel-1 dataset and 83.14% on the Sentinel-2 dataset, revealing its insensitivity to the image type and applicability to a wide range of available visual data for flood detection. Moreover, this study shows that the proposed approach outperforms state-of-the-art CNN models by up to 15% on the SAR images and 9% on the MSI images. Overall, it is shown that the combination of transfer learning, vision transformers, and satellite images is a promising tool for flood risk management experts and emergency response agencies.

show abstract

“…Machine learning [1,2] and deep learning [3,4] They evaluated the performance of the models using the Sentinel-1 images. Using several machine learning methods including MLP, SVM, and a deep neural network (DNN), Islam et al [10] identified flood areas in SPOT-5 and radar image sets. Tanim et al [11] evaluated the performance of supervised and unsupervised machine learning models including Random Forest, SVM, and Maximum Likelihood using Sentinel-1 satellite images.…”

Section: Introductionmentioning

confidence: 99%

Sentinel-1 Polarization Comparison for Flood Segmentation Using Deep Learning

2023

View full text Add to dashboard Cite

Flood is one of the most damaging natural hazards, and timely detection of it is very important to save human lives and assess the level of damage. The occurrence of floods in cloudy weather conditions makes the use of radar-based sensors for real-time flood mapping inevitable. In the present study, the ETCI 2021 flood event detection competition dataset, organized by the NASA Advanced Concepts and Implementation Team in collaboration with the IEEE GRSS Geoscience Informatics Technical Committee, has been used. Moreover, we have utilized the U-Net and X-Net architecture as a segmentation model to map flooded regions. This study aimed to identify the optimum polarization of the Sentinel-1 satellite for flood detection. By examining and comparing the obtained results, it was observed that the VV polarization offered better results in both models. Furthermore, U-Net had better performance than X-Net in both polarizations.

show abstract

Flood Detection Using Multi-Modal and Multi-Temporal Images: A Comparative Study

Cited by 30 publications

References 38 publications

Flood Detection with SAR: A Review of Techniques and Datasets

Flood Detection with SAR: A Review of Techniques and Datasets

Vision Transformer for Flood Detection Using Satellite Images from Sentinel-1 and Sentinel-2

Sentinel-1 Polarization Comparison for Flood Segmentation Using Deep Learning

Contact Info

Product

Resources

About