Large-scale dynamic flood monitoring in an arid-zone floodplain using SAR data and hybrid machine-learning models

Panahi, Mahdi; Rahmati, Omid; Kalantari, Zahra; Darabi, Hamid; Rezaie, Fatemeh; Moghaddam, Davoud Davoudi; Ferreira, Carla; Foody, Giles M.; Aliramaee, Ramyar; Bateni, Sayed M.; Lee, Chang-Wook; Lee, Saro

doi:10.1016/j.jhydrol.2022.128001

Cited by 22 publications

(8 citation statements)

References 122 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Implementation of machine learning plugins ready for final user can be found also in SIG environments, like QGIS, ArcGIS, ENVI and MATLAB. Similarly, in Panahi et al (2022), the SVM classifier was called hybrid machine-learning after a series of metaheuristic optimization procedures were employed in a coupled way to improve the original method. In those cases, the hybrid combination performs better than the standalone SVM, with accuracy reaching up to 91%.…”

Section: Machine Learning Methodsmentioning

confidence: 99%

Flood extent delineation using Sentinel-1 data as information source: systematic review of processing methods

Liz

Ribas

2022

Rev. Bras. Geog. Fis.

View full text Add to dashboard Cite

Delineating the flood extent using SAR data has been an unexceptional activity since the launch of the first sensors. The methodologies applied to image classification vary in complexity and accuracy and, for Sentinel-1, the technical procedures must be adapted considering their polarization, band, temporal resolution, and other factors. Considering these aspects, this article aimed to realize a systematic literature review discussing the most frequent methodologies applied to flood mapping classification employing Sentinel-1 data; describe the preferred methods by areas of expertise; and, inform about their accuracy level. Results indicate that thresholding is the most common methodologies used to flood delineation whatsoever is the researcher area of work. Excellent accuracy levels (reaching 99%) can be obtained using thresholding as the major method, with refinement provided by additional procedures to correct limitations and misclassification. The Sentinel-1data is a good source of information to realize classification in flooded areas but has its limitations in small areas. The choice of methodology for processing SAR data is subjective and requires specific knowledge in the remote sensing field from who executes a hydrological study.

show abstract

Section: Machine Learning Methodsmentioning

confidence: 99%

Flood extent delineation using Sentinel-1 data as information source: systematic review of processing methods

Liz

Ribas

2022

Rev. Bras. Geog. Fis.

View full text Add to dashboard Cite

show abstract

“…Panahi et al, uses SAR satellite images extracted data for flood prediction [22]. Support vector machine (SVM) based machine algorithm was applied for the prediction with meta heuristic features.…”

Section: Related Workmentioning

confidence: 99%

IoT-Enabled Flood Monitoring System for Enhanced Dam Surveillance and Risk Mitigation

R.S,

et al. 2024

Int. Res. J. multidiscip. Technovation

View full text Add to dashboard Cite

According to the Indian scenario, the majority of reservoirs for holding water are operated independently, which is problematic when there are crises (abnormal inflow, cloudy conditions), which causes the surrounding communities and agricultural areas to be submerged those aquifers. Due to the vast geographic region and depth, it is challenging to manually measure the essential reservoir life metrics. Therefore, this research work suggests a cutting-edge system of reservoir management that includes sensors that are appropriate for measuring variables such as pressure, water level, outflow velocity, inflow velocity, tilt, vibration, etc. The Arduino Uno integrates all of the sensors, and Microsoft Power BI receives the data in real time, where each parameter is shown in an appropriate format for visualization. In case of an emergency water level rise, the alarm is set off. The procedure begins with the collection of data from sensors and concludes with the presentation of that data on a dashboard in a control room situated in a distant place that links to a website where the relevant information can be seen by visitors.

show abstract

“…To this end, the authors exploited different techniques obtaining the best precision metric from SVM. This technique was also exploited in [91] as a part of a hybrid approach including metaheuristic optimization procedures like the grey wolf optimization, the differential evolution and the imperialist competitive algorithm. A variant of SVM, known as reference vector machine [92], has been adopted in [93] to map floods in Aqqala, Iran.…”

Section: Machine Learningmentioning

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

Large-scale dynamic flood monitoring in an arid-zone floodplain using SAR data and hybrid machine-learning models

Cited by 22 publications

References 122 publications

Flood extent delineation using Sentinel-1 data as information source: systematic review of processing methods

Flood extent delineation using Sentinel-1 data as information source: systematic review of processing methods

IoT-Enabled Flood Monitoring System for Enhanced Dam Surveillance and Risk Mitigation

Flood Detection with SAR: A Review of Techniques and Datasets

Contact Info

Product

Resources

About