Flood Inundation Mapping Using Machine Learning for Sustainable vs. Resilient Design - UNDER REVIEW

External URL: https://edx.hydrolearn.org/courses/course-v1:NMSU+CE483+Fall2024/about

This module is intended to be exported and imported by users to aid in creating a new module. Follow these guidelines and you'll soon be on your way to an excellent module!

Flood Inundation Mapping Using Machine Learning for Sustainable vs. Resilient Design - UNDER REVIEW CIROH View Course Problem Statement In the U.S., the hydraulic collapse frequency is estimated at 0.02% per year for a total population of about 504,000 bridges. One such collapse occurred at the intersection of Bear Cabin Branch and Grafton Shop Road (Latitude 39.54491 and Longitude -76.3924) in the City of Bel Air North, MD. As a hydrologic and hydraulic engineer, you are tasked with making a decision on hydraulic design to create a more resilient and sustainable bridge in the future. The goal is to utilize a flood inundation map generated through machine learning to aid in this process. You will need to create a flood inundation map for the collapse site using machine learning techniques, and then compare and evaluate this map against existing physically based models. These flood inundation maps will be utilized in determining specific design elements for the new hydraulic bridge. Module Overview This module focuses on teaching the knowledge and technical skills related to flood inundation mapping and its impact on designing resilient and sustainable hydraulic infrastructure. It consists of the following sections: Section 1: Introduction Section 2: Machine Learning for Flood Inundation Mapping Section 3: Evaluation of Flood Inundation Mapping Section 4: Decision Making for Hydraulic Design Topics Covered Flood Hazard Data, Machine Learning for Flood Inundation Mapping, Resilient vs. Sustainable Hydraulic Design Prerequisites The student needs to have basic understanding of Hydrology , Hydraulics , and Floodplains Learning Objectives At the end of this module, students will be able to download FEMA flood hazard data, train a machine learning model for flood inundation mapping, and examine flooded areas for resilient vs. sustainable hydraulic design. This will be accomplished through activities within each section. Results from each activity will be recorded in specified results templates. The results templates for each activity can be found at the beginning of each activity. The results templates are organized such that results from one activity can easily be used in successive activities. Suggested Implementation This module was designed to be self-paced and the student should be able to complete each section following detail instructions. Course Authors Huidae Cho Dr. Huidae Cho is a Professional Engineer (PE) licensed in Maryland, Member of the American Society of Civil Engineers (M.ASCE), Certified Floodplain Manager (CFM), and Certified GIS Professional (GISP). He is an avid Open-Source advocate and enjoys scientific programming to solve computational problems. He has been part of the Geographic Resources Analysis Support System ( GRASS ) GIS development team since June 2000, is a member of the GRASS GIS Project Steering Committee, and has special interests in developing and contributing geospatial modules to the Open-Source community. He is also a senior ArcGIS developer. Email Address: hcho@nmsu.edu Fahmidah Ashraf Fahmidah Ashraf's Biography Email Address: fashraf@bradley.edu Kshitij Dahal Kshitij Dahal's Biography Email Address: kdahal3@asu.edu Target Audience The target audience of this module is senior undergraduate and/or graduate students in Civil Engineering. Tools Needed The student will need A computer with access to the Internet and A free Google Colab Account. Expected Effort The module developers estimate that this module will take between 10 to 14 hours to complete. Course Sharing and Adaptation This course is available for adaptation and customization by other instructors. A compressed copy of this course can be downloaded from the course about page in the top right hand corner by clicking the "Export Link" link. You will need a HydroLearn instructor studio account to do this. You will first need to sign up for a hydrolearn.org account, then you should register as an instructor by clicking 'studio.hydrolearn' and requesting course creation permissions. Recommended Citation Cho, H., Ashraf, F., Dahal, K. (2024). Flood Inundation Mapping Using Machine Learning for Sustainable vs. Resilient Design. HydroLearn. https://edx.hydrolearn.org/courses/course-v1:NMSU+CE483+Fall2024/about Acknowledgement Funding for this project was provided by the National Oceanic and Atmospheric Administration (NOAA), awarded to the Cooperative Institute for Research on Hydrology (CIROH) through the NOAA Cooperative Agreement with The University of Alabama, NA22NWS4320003.