Artificial Intelligence in Geospatial Analysis for Flood Vulnerability Assessment: A Case of Dire Dawa Watershed, Awash Basin, Ethiopia

Abstract

This study presents the novelty artificial intelligence in geospatial analysis for flood vulnerability assessment in Dire Dawa, Ethiopia. Flood-causing factors such as rainfall, slope, LULC, elevation NDVI, TWI, SAVI, K-factor, R-factor, river distance, geomorphology, road distance, SPI, and population density were used to train the ANN model. The weights were generated in the ANN model and prioritized. Initial values were randomly assigned to the NN and trained with the feedforward processes. Ground-truthing points collected from the historical flood events of 2006 were used as targeting data during the training. A rough flood hazard map generated in feedforward was compared with the actual data, and the errors were propagated back into the NN with the backpropagation technique, and this step was repeated until a good agreement was made between the result of the GIS-ANN and the historical flood events. The results were overlapped with ground-truthing points at 88.46% and 89.15% agreement during training and validation periods. Therefore, the application of the GIS-ANN for the assessment of flood vulnerable zones for this city and its catchment was successful. The result of this study can also be further considered along with the city and its catchment for practical flood management.

Potential flood-prone area identification and mapping using GIS-based multi-criteria decision-making and analytical hierarchy process in Dega Damot district, northwestern Ethiopia

“…In recent years, the integrated use of geospatial technologies (GIS and remote sensing) with other models/methods has become the most popular method to examine flood hazards. Multi-criteria decision analysis (MCDA) using analytical hierarchy process (AHP) (Ajibade et al 2021;Allafta and Opp 2021;Aydin and Birincioğlu 2022;Das and Gupta 2021;Karymbalis et al 2021;Wubalem et al 2021), frequency ratio (FR) (Ali et al 2020;Tehrany et al 2017;Wubalem et al 2021;Yariyan et al 2020), hydrologic engineering centers river analysis system (HEC-RAS) (Demir and Kisi 2016), fuzzy logic (Ajibade et al 2021;Kanani-Sadat et al 2019), logistic regression (LR) (Ali et al 2020;Tehrany et al 2017;Wubalem et al 2021), artificial neural networks (ANN) (Tamiru and Dinka, 2021), fuzzy weights-of-evidence (fuzzy-WofE) (Hong et al 2018a, b;Tehrany et al 2017), support vector machine (SVM) (Son et al 2021), random forest (RF) (Farhadi and Najafzadeh, 2021;Son et al 2021;Wang et al 2015;Zhao et al 2018), two-dimensional flood routing model (FLO-2D) (Erena et al 2018), and adaptive neuro-fuzzy inference system (ANFIS) (Hong et al 2018a, b;Razavi-Termeh et al 2018) integrated with geospatial technologies (GIS and remote sensing) are the indispensable methods developed and employed by previous researchers for flood hazard area identification and mapping. Ali et al (2020) employed the integration of GIS, multicriteria decision-making (MCDM) approach, bivariate statistics (frequency ratio and statistical index), and logistic regression to identify flood-prone areas of the Topľa river basin in Slovakia.…”

Geospatial Analysis of Flood Vulnerability Levels Based on Physical Characteristics and Resilience Capacity of Peri-Urban Settlements in Nigeria

“…According to Sarkar and Mondal (2020), the aftermath of a flood event can be perceived in socio-economic activities, while the extent of such aftermaths is historically increasing globally (Moreno et al, 2020). Flood events can impact various entities both in urban and rural areas, while the extent of the impacts tends to be very high in urban areas (Tamiru & Dinka, 2021). According to global natural disaster reports, over 2.4 billion individuals have, one way or other, suffered the consequences of flood events.…”

“…According to global natural disaster reports, over 2.4 billion individuals have, one way or other, suffered the consequences of flood events. About 165,020 mortalities have been linked to the event between 2019 and 2020, as approximated by the United Nations (Tamiru & Dinka, 2021). Furthermore, floods have caused approximately $280 billion in economic damage in Africa over the past two decades.…”

“…Over the years, GIS and RS technologies have played a significant role in flood risk management at various levels of society, including the coastal areas (Gedam & Dagalo, 2020;Tamiru & Dinka, 2021). Flood risk management entails activi-O.…”

“…The present study focuses on the physical vulnerability using various physical-environmental domains such as land use, drainage, and elevation. GIS techniques can spatially process different physical-environmental parameters in flood risk assessment (Danumah et al, 2016;Meena & Gupta, 2017;Njoku et al, 2018;Rimba et al, 2017;Deepak et al, 2020;Tamiru & Dinka, 2021).…”