Evaluation of SAR and Optical Data for Flood Delineation Using Supervised and Unsupervised Classification

Foroughnia, Fatemeh; Alfieri, Silvia Maria; Menenti, Massimo; Lindenbergh, Roderik

doi:10.3390/rs14153718

Cited by 16 publications

(7 citation statements)

References 76 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Optical sensors also experience difficulty detecting vegetated waters, as do radar sensors albeit to a lesser extent [ 114 – 116 ]. Most readily-available flood extents rely on algorithms suitable for mapping open waters [ 115 , 117 ] leading to flood omission where inundated vegetation is present [ 113 ]. Satellite-derived flood extents were found to underestimate flood inundation due to emergent vegetation in the central axis of the Barotse Floodplain and in the Luena Valley in previous studies [ 36 , 60 , 114 ].…”

Section: Discussionmentioning

confidence: 99%

Impacts of seasonal flooding on geographical access to maternal healthcare in the Barotse Floodplain, Zambia

Mroz,

Willis,

Thomas

et al. 2023

Int J Health Geogr

View full text Add to dashboard Cite

Background Seasonal floods pose a commonly-recognised barrier to women’s access to maternal services, resulting in increased morbidity and mortality. Despite their importance, previous GIS models of healthcare access have not adequately accounted for floods. This study developed new methodologies for incorporating flood depths, velocities, and extents produced with a flood model into network- and raster-based health access models. The methodologies were applied to the Barotse Floodplain to assess flood impact on women’s walking access to maternal services and vehicular emergency referrals for a monthly basis between October 2017 and October 2018. Methods Information on health facilities were acquired from the Ministry of Health. Population density data on women of reproductive age were obtained from the High Resolution Settlement Layer. Roads were a fusion of OpenStreetMap and data manually delineated from satellite imagery. Monthly information on floodwater depth and velocity were obtained from a flood model for 13-months. Referral driving times between delivery sites and EmOC were calculated with network analysis. Walking times to the nearest maternal services were calculated using a cost-distance algorithm. Results The changing distribution of floodwaters impacted the ability of women to reach maternal services. At the peak of the dry season (October 2017), 55%, 19%, and 24% of women had walking access within 2-hrs to their nearest delivery site, EmOC location, and maternity waiting shelter (MWS) respectively. By the flood peak, this dropped to 29%, 14%, and 16%. Complete inaccessibility became stark with 65%, 76%, and 74% unable to access any delivery site, EmOC, and MWS respectively. The percentage of women that could be referred by vehicle to EmOC from a delivery site within an hour also declined from 65% in October 2017 to 23% in March 2018. Conclusions Flooding greatly impacted health access, with impacts varying monthly as the floodwave progressed. Additional validation and application to other regions is still needed, however our first results suggest the use of a hydrodynamic model permits a more detailed representation of floodwater impact and there is great potential for generating predictive models which will be necessary to consider climate change impacts on future health access.

show abstract

Section: Discussionmentioning

confidence: 99%

Impacts of seasonal flooding on geographical access to maternal healthcare in the Barotse Floodplain, Zambia

Mroz,

Willis,

Thomas

et al. 2023

Int J Health Geogr

View full text Add to dashboard Cite

show abstract

“…This approach, with successive modifications and refinements, has been widely exploited for flooding applications [127][128][129]. Insightful comparative studies between different techniques, including ACMs, have been recently proposed in [54,130].…”

Section: Active Contour Modelsmentioning

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

“…Supervised classification utilizes prior knowledge in the classification process through the selection of training samples, with the most common classifiers being maximum likelihood, minimum distance, and artificial neural network (ANN) (Ritter and Hepner, 1990;Otukei and Blaschke, 2010;Abida et al, 2022). Unsupervised classification was developed first through different clustering methods such as K-means, interactive self-organization data analysis (ISODATA), and principal component analysis (PCA) (Abbas et al, 2016;Foroughnia et al, 2022;Macarringue et al, 2022). OBIA uses geographic objects as the fundamental units for land cover classification (Macarringue et al, 2022;Shi et al, 2022).…”

Section: Introductionmentioning

confidence: 99%

Land use classification in mine-agriculture compound area based on multi-feature random forest: a case study of Peixian

Xu,

Chen,

Zhou

et al. 2024

Front. Sustain. Food Syst.

View full text Add to dashboard Cite

IntroductionLand use classification plays a critical role in analyzing land use/cover change (LUCC). Remote sensing land use classification based on machine learning algorithm is one of the hot spots in current remote sensing technology research. The diversity of surface objects and the complexity of their distribution in mixed mining and agricultural areas have brought challenges to the classification of traditional remote sensing images, and the rich information contained in remote sensing images has not been fully utilized.MethodsA quantitative difference index was proposed quantify and select the texture features of easily confused land types, and a random forest (RF) classification method with multi-feature combination classification schemes for remote sensing images was developed, and land use information of the mine-agriculture compound area of Peixian in Xuzhou, China was extracted.ResultsThe quantitative difference index proved effective in reducing the dimensionality of feature parameters and resulted in a reduction of the optimal feature scheme dimension from 57 to 22. Among the four classification methods based on the optimal feature classification scheme, the RF algorithm emerged as the most efficient with a classification accuracy of 92.38% and a Kappa coefficient of 0.90, which outperformed the support vector machine (SVM), classification and regression tree (CART), and neural network (NN) algorithm.ConclusionThe findings indicate that the quantitative differential index is a novel and effective approach for discerning distinct texture features among various land types. It plays a crucial role in the selection and optimization of texture features in multispectral remote sensing imagery. Random forest (RF) classification method, leveraging a multi-feature combination, provides a fresh method support for the precise classification of intricate ground objects within the mine-agriculture compound area.

show abstract

Evaluation of SAR and Optical Data for Flood Delineation Using Supervised and Unsupervised Classification

Cited by 16 publications

References 76 publications

Impacts of seasonal flooding on geographical access to maternal healthcare in the Barotse Floodplain, Zambia

Impacts of seasonal flooding on geographical access to maternal healthcare in the Barotse Floodplain, Zambia

Flood Detection with SAR: A Review of Techniques and Datasets

Land use classification in mine-agriculture compound area based on multi-feature random forest: a case study of Peixian

Contact Info

Product

Resources

About