scholarly journals Machine-learning and HEC-RAS integrated models for flood inundation mapping in Baro River Basin, Ethiopia

2021 ◽  
Author(s):  
Habtamu Tamiru ◽  
Meseret Wagari
Keyword(s):  
Machine Learning ◽  
River Basin ◽  
Water Body ◽  
Hydrological Model ◽  
Daily Rainfall ◽  
Landsat 8 ◽  
Flood Inundation ◽  
Inundation Mapping ◽  
Flood Inundation Mapping ◽  
Daily Discharge

AbstractThis study presents an integrated machine-learning and HEC-RAS models for flood inundation mapping in Baro River Basin, Ethiopia. ANN and HEC-RAS models were integrated as a predictive hydrological and hydraulic model to generate runoff and the extent of flood, respectively. Daily rainfall and temperature data of 7-years (1999–2005), daily discharge (1999–2005) and 30 m × 30 m gridded Topographical Wetness Index (TWI) were used to train a predictive ANN hydrological model in RStudio. The predictive performance of the developed ANN hydrological model was evaluated in RStudio using Nash–Sutcliffe Efficiency (NSE) values of 0.86 and 0.88 during the training period (1999–2005) and testing period (2006–2008), respectively, with the corresponding observed daily discharge. The validated ANN predictive hydrological model was linked with HEC-RAS to generate the flood extent along the river course. The HEC-RAS model result was calibrated and validated using the water body delineated using Normal Difference Water Index (NDWI) from LANDSAT 8 imagery based on historical flood events of 2005 and 2008. It was found that about 96% of an agreement was made between the flood-prone areas generated in HEC-RAS and the water body delineated using NDWI. Therefore, it is logical to conclude that the integration of a machine-learning approach with the HEC-RAS model has improved the spatiotemporal uncertainties in traditional flood forecasting methods. This integrated model is powerful tool for flood inundation mapping to warn residents of this basin.

scholarly journals Machine learning and HEC-RAS integrated models for flood inundation mapping in Baro River Basin, Ethiopia

2021 ◽  
Author(s):  
Habtamu Tamiru
Keyword(s):  
Machine Learning ◽  
River Basin ◽  
Daily Rainfall ◽  
Simulation Models ◽  
Spatial And Temporal Variability ◽  
Flood Inundation ◽  
Rainfall Runoff ◽  
Ann Model ◽  
Inundation Mapping ◽  
Flood Inundation Mapping

This paper presents the integrated machine learning and HEC-RAS models for flood inundation mapping in Baro River Basin, Ethiopia. A predictive rainfall-runoff and spatially distributed river simulation models were developed using Artificial Neural Networks (ANNs) and HEC-RAS respectively. Daily rainfall and temperature data of 7-yrs and Topographical Wetness Index (TWI) with a spatial resolution of 50 x 50m were used to train the ANN in R studio. The integration of the spatial and temporal variability in this paper improved the accuracy of the predictive models integrated with ANN and HEC-RAS. The predictive ANN model was tested with the observed daily discharge of the same temporal resolution and the rainfall-runoff result obtained from the tested ANN model was used as input for the HEC-RAS. The flood event of 2005 was used to verify the accuracy of flood generated in the HEC-RAS model by implementing the Normal Difference Water Index (NDWI). The comparison was made between the flood inundation map generated by HEC-RAS and flood events of different periods based on coverage percentage areas and a good agreement was reached with 96 % overlapped areas. The performance of ANN and HEC-RAS models were evaluated with 0.86 and 0.88 values at the training and testing period respectively. Finally, it was concluded that the integration of a machine learning approach with the HEC-RAS model in developing a flood inundation mapping is an appropriate tool to warn residents in this river basin.

scholarly journals High-Resolution Inundation Mapping for Heterogeneous Land Covers with Synthetic Aperture Radar and Terrain Data

2020 ◽  
Vol 12 (6) ◽  
pp. 900 ◽  
Author(s):  
Fernando Aristizabal ◽  
Jasmeet Judge ◽  
Alejandro Monsivais-Huertero
Keyword(s):  
Machine Learning ◽  
Synthetic Aperture Radar ◽  
Predictive Value ◽  
Synthetic Aperture ◽  
Flood Inundation ◽  
Dense Vegetation ◽  
Inundation Mapping ◽  
Flood Inundation Mapping ◽  
Land Covers ◽  
Aperture Radar

Floods are one of the most wide-spread, frequent, and devastating natural disasters that continue to increase in frequency and intensity. Remote sensing, specifically synthetic aperture radar (SAR), has been widely used to detect surface water inundation to provide retrospective and near-real time (NRT) information due to its high-spatial resolution, self-illumination, and low atmospheric attenuation. However, the efficacy of flood inundation mapping with SAR is susceptible to reflections and scattering from a variety of factors including dense vegetation and urban areas. In this study, the topographic dataset Height Above Nearest Drainage (HAND) was investigated as a potential supplement to Sentinel-1A C-Band SAR along with supervised machine learning to improve the detection of inundation in heterogeneous areas. Three machine learning classifiers were trained on two sets of features dual-polarized SAR only and dual-polarized SAR along with HAND to map inundated areas. Three study sites along the Neuse River in North Carolina, USA during the record flood of Hurricane Matthew in October 2016 were selected. The binary classification analysis (inundated as positive vs. non-inundated as negative) revealed significant improvements when incorporating HAND in several metrics including classification accuracy (ACC) (+36.0%), critical success index (CSI) (+39.95%), true positive rate (TPR) (+42.02%), and negative predictive value (NPV) (+17.26%). A marginal change of +0.15% was seen for positive predictive value (PPV), but true negative rate (TNR) fell −14.4%. By incorporating HAND, a significant number of areas with high SAR backscatter but low HAND values were detected as inundated which increased true positives. This in turn also increased the false positives detected but to a lesser extent as evident in the metrics. This study demonstrates that HAND could be considered a valuable feature to enhance SAR flood inundation mapping especially in areas with heterogeneous land covers with dense vegetation that interfere with SAR.

scholarly journals Flood Inundation Mapping along the Lower Reach of Kelani River Basin under the Impact of Climatic Change

2012 ◽  
Vol 45 (2) ◽  
pp. 23 ◽  
Author(s):  
M. M. G. T. De Silva ◽  
S. B. Weerakoon ◽  
Srikantha Herath ◽  
U. R. Ratnayake ◽  
Sarith Mahanama
Keyword(s):  
Climatic Change ◽  
River Basin ◽  
Flood Inundation ◽  
Lower Reach ◽  
Inundation Mapping ◽  
Flood Inundation Mapping ◽  
Kelani River ◽  
The Impact

Flood Inundation Mapping of the Hitachi Region in the Kuji River Basin, Japan, During the October 11–13, 2019 Extreme Rain Event

2020 ◽  
Vol 15 (6) ◽  
pp. 712-725 ◽  
Author(s):  
Shakti P. C. ◽  
◽  
Kohin Hirano ◽  
Satoshi Iizuka
Keyword(s):  
River Basin ◽  
Hydrological Modeling ◽  
Rapid Development ◽  
Mitigation Strategies ◽  
Flood Mapping ◽  
Rain Event ◽  
Flood Inundation ◽  
Advantages And Disadvantages ◽  
Inundation Mapping ◽  
Flood Inundation Mapping

The frequency of severe flood events has been increasing recently in Japan. One of the latest events occurred in October 2019 and caused extensive damage in several river basins, especially in the central and northern regions of the country. In this study, we selected the Hitachi region (Hitachi-Omiya and Hitachi-Ota) within the Kuji River Basin which underwent considerable flooding due to the failure of embankments at two locations in the region. Maximum-possible flood inundation maps were generated using survey-based data and hydrological modeling for the Hitachi region. These maps incorporated the flood scenarios (embankment failures). All the generated products were compared with the reference flood mapping, i.e., Sentinel-1 data and Geospatial Information Authority of Japan (GSI) data for that region. It was observed that generated flood inundation mapping product based on the survey-data yielded results similar to those obtained with GSI data for the Hitachi region. Although each flood mapping product has advantages and disadvantages, they can be a good reference for the proper management and mitigation of flood disaster in the future. The rapid development of flood inundation mapping products that consider varying flood scenarios is an important part of flood mitigation strategies.

scholarly journals High-Resolution Inundation Mapping for Heterogeneous Land Covers with Synthetic Aperture Radar and Terrain Data

2019 ◽  
Author(s):  
Fernando Aristizabal ◽  
Jasmeet Judge ◽  
Alejandro Monsivais-Huertero
Keyword(s):  
Machine Learning ◽  
Synthetic Aperture Radar ◽  
Predictive Value ◽  
Synthetic Aperture ◽  
Flood Inundation ◽  
Dense Vegetation ◽  
Inundation Mapping ◽  
Flood Inundation Mapping ◽  
Land Covers ◽  
Aperture Radar

Floods are one of the most wide-spread, frequent, and devastating natural disasters that continue to increase in frequency and intensity. Remote sensing, specifically synthetic aperture radar (SAR), has been widely used to detect surface water inundation to provide retrospective and near-real time (NRT) information due to its high-spatial resolution, self-illumination, and low atmospheric attenuation. However, the efficacy of flood inundation mapping with SAR is susceptible to reflections and scattering from a variety of factors including dense vegetation and urban areas. In this study, the topographic dataset height above nearest drainage (HAND) was investigated as a potential supplement to Sentinel-1A C-Band SAR along with supervised machine learning to improve the detection of inundation in heterogeneous areas. Three machine learning classifiers were trained on two sets of features SAR only (VV & VH) and VV, VH & HAND to map inundated areas. Three study sites along the Neuse River in North Carolina, USA during the record flood of Hurricane Matthew in October 2016 were selected. The binary classification analysis (inundated as positive vs. non-inundated as negative) revealed significant improvements when incorporating HAND in several metrics including classification accuracy (ACC) (+37.1%), true positive rate (TPR) (+51.2%), and negative predictive value (NPV) (+23.7%), A marginal improvement of +1.4% was seen for positive predictive value (PPV), but true negative rate (TNR) fell -15.1%. By incorporating HAND, a significant number of areas with high SAR backscatter but low HAND values were detected as inundated which increased true positives. This in turn also increased the false positives detected but to a lesser extent as evident in the metrics. This study demonstrates that HAND could be considered a valuable feature to enhance SAR flood inundation mapping especially in areas with heterogeneous land covers with dense vegetation that interfere with SAR.

Sign in / Sign up

Export Citation Format

Share Document