Detail Abstract

Developing Operational Web Application for Flood Inundation Forecasting for Lower Mekong River Basin

MeetingVIWC2026
TopicOS2: Remote Sensing of water and inundation
AuthorSon K. Do | Chi-Hung Chang | Hyongki LEE | Tien L.T. DU
OrganizationDepartment of Civil and Environmental Engineering, University of Houston, Houston, TX, USA | Department of Civil and Environmental Engineering, University of Houston, Houston, TX, USA | Department of Civil and Environmental Engineering, University of Houston, Houston, TX, USA | Department of Civil and Environmental Engineering, University of Houston, Houston, TX, USA
DOI2022.1672422188

Abstract

Floods are among the world’s most costly and deadly natural disasters. For relief planning, support rescue, and damage recovery decisions during flood events, inundation mapping is extremely vital. Yet, there is no rapid operational inundation forecasting system that can help decision-makers proactively mitigate flood damages in Lower Mekong River Basin. Here, we integrated the so-called Forecasting Inundation Extents using Rotated empirical orthogonal function analysis (FIER) framework with an altimetry-based operational Mekong River level forecasting system to produce accurate inundation extent forecasts for the region. To inform and assist end-users we built an operational web application that generates inundation forecasts with up to 18-day lead times in about 20 seconds on a daily basis with a promising skill (> 70% of critical success index). We use an open-source platform called Streamlit which gained popularity recently among data scientists and engineers to build and host web applications using only Python without intense front-end design knowledge. We also utilize Google Earth Engine and Floodwater Depth Estimation Tool (FwDET) to generate flood depth estimation maps. The wesb application FIER-Mekong can be accessed at https://skd862-fier-mekong-demo-vlobm9.streamlitapp.com/).

Keywords: monitoring, remote sensing, flood forecasting, web-application