Integrated machine learning and GIS-based bathtub models to assess the future flood risk in the Kapuas River Delta, Indonesia. Issue 1 (25th November 2022)

• Record Type: Journal Article
• Authors: Sampurno, Joko; Ardianto, Randy; Hanert, Emmanuel
• Is Part Of: Journal of hydroinformatics. Volume 25:Issue 1(2023)
• Page Start: 113
• Page End: 125
• Publication Date: 2022-11-25
• Subjects: climate change -- GIS -- data-scarce delta -- flood risk -- machine learning; Hydrology -- Data processing -- Periodicals; Geographic information systems -- Periodicals; Geographic information systems; Hydrology -- Data processing; Electronic journals; Periodicals; 551.480285
• DOI: 10.2166/hydro.2022.106
• Languages: English
• ISSNs: 1464-7141

Abstract

Abstract: As more and more people live near the sea, future flood risk must be properly assessed for sustainable urban planning and coastal protection. However, this is rarely the case in developing countries where there is a lack of both in-situ data collection and forecasting tools. Here, we consider the case of the Kapuas River Delta (KRD), a data-scarce delta on the west coast of Borneo Island, Indonesia. We assessed future flood risk under three climate change scenarios (RCP2.6, RCP4.5, and RCP8.5). We combined the multiple linear regression and the GIS-based bathtub inundation models to assess the future flood risk. The former model was implemented to model the river's water-level dynamics in the KRD, particularly in Pontianak, under the influence of rainfall changes, surface wind changes, and sea-level rise. The later model created flood maps with inundated areas under a 100-year flood scenario, representing Pontianak's current and future flood extent. We found that about 6.4%–11.9% more buildings and about 6.8%–12.7% more roads will be impacted by a 100-year flood in 2100. Our assessment guides the local water manager in preparing adequate flood mitigation strategies. HIGHLIGHTS: The proposed scheme successfully tackled the issues of data scarcity and low computational resources. The approach is appropriate for local water managers in developing countries. The proposed method combined the simple machine learning and GIS-based bathtub inundation models. The scheme is successfully implemented in the Kapuas River Delta. The assessment is beneficial for flood mitigation strategies.