Comparison of Satellite and Geomorphic Indices for Flooded Areas Detection in a Mediterranean River Basin

Totaro, Vincenzo; Peschechera, Giuseppe; Gioia, Andrea; Iacobellis, Vito; Fratino, Umberto

doi:10.1007/978-3-030-24305-0_14

Cited by 6 publications

(4 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A identificação das fontes de incertezas e sua quantificação torna-se um aspecto importante para a seleção do método ou modelo mais adequado para a redução da subestimação ou superestimação no mapeamento das inundações (Teng et al, 2017). Um dos índices usados para avaliar as incertezas espacialmente distribuídas é a medida de entropia de Shannon (E), derivada da teoria da informação (Shannon, 1948): onde, 𝑝𝑝𝑝𝑝 é a probabilidade associada a classe 𝑝𝑝 e n é o número de classes.…”

Section: Medida De Incerteza Da Classificaçãounclassified

“…No entanto, os índices espectrais têm como principal limitação a determinação de um valor de limiar ideal para subdividir de forma efetiva alvos aquáticos e não aquáticos para o mapeamento da água superficial, principalmente em áreas inundadas (Jones, 2015;Silveira & Guasselli, 2019;Totaro et al, 2019;Kordelas et al, 2019). Em relação às classificações supervisionadas baseadas em estatística, estas podem ser complexas justamente devido à esta mistura ou similaridade espectral dos alvos não aquáticos com a água, necessitando a criação de muitas subclasses de mapeamento (Koko et al, 2021).…”

Section: Introductionunclassified

See 1 more Smart Citation

Integração Da Incerteza Na Amostragem E Classificação Random Forest Utilizando Bandas E Índices Espectrais Para O Mapeamento De Inundação

et al. 2023

View full text Add to dashboard Cite

Classificações tradicionais apresentam limitações para o mapeamento de inundações devido à mistura da resposta espectral da água com alvos adjacentes não aquáticos ou resposta espectral similar de alvos não aquáticos com a água. Além disso, em geral, as classificações são avaliadas apenas em termos de acurácia global sem considerar as incertezas no processo de classificação. Assim, neste estudo objetivou-se integrar a incerteza na classificação Random Forest (RF) para o mapeamento de inundações auxiliando o processo de amostragem. A classificação utilizou 21 variáveis representadas por bandas e índices espectrais do sensor Operational Land Imager do satélite Landsat-8. A amostragem foi realizada inicialmente com a seleção de pontos a partir da interpretação visual da imagem de satélite e posteriormente coletando amostras com alta entropia de Shannon no mapa de incerteza. As variáveis com maior importância para a classificação foram selecionadas utilizando o algoritmo Recursive Feature Elimination (RFE). Os resultados mostram que a classificação RF final usando amostras coletadas com base no mapa de incerteza e o conjunto de variáveis selecionadas pelo RFE apresentou 98,0% de exatidão e redução das incertezas do mapeamento da água superficial em relação à classificação RF com todas as variáveis e sem considerar a amostragem baseada na incerteza. Palavras-chave: Mapeamento de inundação. Classificador Random Forest. Bandas e índices espectrais. Seleção de variáveis. Entropia de Shannon.

show abstract

Section: Medida De Incerteza Da Classificaçãounclassified

Section: Introductionunclassified

Integração Da Incerteza Na Amostragem E Classificação Random Forest Utilizando Bandas E Índices Espectrais Para O Mapeamento De Inundação

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Then, merging of the multi-source and multi-temporal RS data and combining this with other methodologies become necessary in order to improve the quantity and quality of the extracted information. (2) In addition to the hydro-geomorphological analysis, the application of an integrated approach has been amply demonstrated in many research on flood mapping [40][41][42] (Figure 2). The coupling of optical and SAR satellite images has proven to be helpful to observe the spatial evolution of flood event (Left Panel in Figure 2); the integration of multi-frequency, multi-polarization, and multi-temporal SAR data was successfully used to derive a flood map in areas characterized by various vegetation cover types (Right Panel in Figure 2); and the combined application of the hydro-geomorphological parameter-the sediment connectivity index-and the RS data enhanced the exploration of the processes' connection in flood dynamics (Below Panel in Figure 2).…”

Section: Introductionmentioning

confidence: 99%

New Perspectives of Earth Surface Remote Detection for Hydro-Geomorphological Monitoring of Rivers

2022

View full text Add to dashboard Cite

In the current scenery of climate change and its relatively increasing visible effects seen over the world, the monitoring of geomorphological processes and flood dynamics becomes more and more necessary for disaster risk reduction. During recent decades, the advantages offered by remote sensing for Earth surface observations have been widely exploited, producing images, digital elevation models (DEM), maps, and other tools useful for hydro-geomorphological parameters detection, flood extent monitoring, and forecasting. However, today, advanced technologies and integrated methodologies do not yet enable one to completely provide near-real-time (NRT) and very-high-resolution (VHR) observations of a river, which is needed for risk evaluation and correct operational strategy identification. This work presents an advanced remote detection analysis system (ARDAS) based on the combination of multiple technologies, such as Unmanned Aerial Vehicle (UAV) systems, Structure from Motion (SfM) techniques, and cloud computing environment. The system allows to obtain VHR products, such as ortho-photomosaics and DEM, for deep observation of the river conditions, morphological modifications, and evolution trend. The test of ARDAS in the Basento river catchment area (Basilicata, South Italy) showed that the innovative system (i) proves to be advantageous in river monitoring due to its high accuracy, quickness, and data flexibility; (ii) could represent a NRT solution for timely support of flood hazard assessments; and (iii) can be further developed by integrating other technologies for direct application in land planning and safeguard activities by contributing to the value chain of the new space economy and sustainable development.

show abstract

“…Different approaches can be used for the management and mitigation of hydraulic risk, for example by making use of theoretical tools in the framework of derived flood frequency distributions [ 9 , 10 ] or in the context of conceptual models [ 11 ]. In addition, useful support for flood management is provided by satellite data, which use is widespread in the environmental field, both for the evaluation of hydrological parameters [ 12 – 16 ] and for flood risk assessment [ 17 – 20 ]. Recent advances in the definition of high-resolution Digital Elevation Models (DEM) were carried out exploiting the use of Unmanned Aerial Vehicle (UAV) (e.g., [ 21 ]).…”

Section: Introductionmentioning

confidence: 99%

Coupled Use of Hydrologic-Hydraulic Model and Geomorphological Descriptors for Flood-Prone Areas Evaluation: A Case Study of Lama Lamasinata

Lioi

Gioia

Totaro

et al. 2020

Computational Science and Its Applications – ICCSA 2020

Self Cite

View full text Add to dashboard Cite

The delineation of flood risk maps is a fundamental step in planning urban areas management. This evaluation can be carried out by hydraulic/hydrological modelling that allows obtaining water depths and related flooded areas. In this way, it is possible to mitigate and contain the catastrophic effects of floods, which become more frequent in the last decades. These events result in losses of both human lives and assets. In addition, the growing availability of high-resolution topographic data (i.e. Digital Terrain Models - DTM), due to new technologies for measuring surface elevation, gave a strong impulse to the development of new techniques capable of providing rapid and reliable identification of flood susceptibility. In this study, two methodologies for mapping flood-prone areas in karst ephemeral streams in Puglia region (Southern Italy) are compared, highlighting how DTM-based technologies are a precious source of information in data-poor environments. Results are in perfect agreement with previous studies on similar areas, showing the marked influences of topography in defining flood-prone areas. These researches can also be useful in investigating a wider gamma of hydrological-related aspects, in particular with respect to the social behavior of communities.

show abstract

Comparison of Satellite and Geomorphic Indices for Flooded Areas Detection in a Mediterranean River Basin

Cited by 6 publications

References 44 publications

Integração Da Incerteza Na Amostragem E Classificação Random Forest Utilizando Bandas E Índices Espectrais Para O Mapeamento De Inundação

Integração Da Incerteza Na Amostragem E Classificação Random Forest Utilizando Bandas E Índices Espectrais Para O Mapeamento De Inundação

New Perspectives of Earth Surface Remote Detection for Hydro-Geomorphological Monitoring of Rivers

Coupled Use of Hydrologic-Hydraulic Model and Geomorphological Descriptors for Flood-Prone Areas Evaluation: A Case Study of Lama Lamasinata

Contact Info

Product

Resources

About