Building a Real-Time Predictive Flood Model for Improving Early Warning Systems in Ellicott City, Maryland

As flood events in the United States grow in frequency and intensity, the uses of applied remote sensing analyses are increasingly necessary for effective flood monitoring and warning systems. The NASA DEVELOP Ellicott City Disasters III project investigated the use of machine learning for applications in flood risk detection to support the improvement of early warning systems in Ellicott City, Maryland. To strengthen the efforts of the Howard County Office of Emergency Management (OEM) in building a more robust flood monitoring system, this term built on the predictive capability of the long-short term memory (LSTM) model created by the second term of this DEVELOP project to create a Sequentially Trained Real-time EstimAted Model (STREAM). Enhancements to the model included the integration of both real-time and predicted weather products from the National Weather Service to increase predictive capacity. These weather products were supplemented by stream gauge data from the OEM as well as real-time radar products. The resultant flood risk model was trained to evaluate input variables and predict stage height in Ellicott City in real time. The model, upgraded to predict stage height up to 8 hours in advance, was incorporated into an online dashboard in a user-friendly interface. The project demonstrated the potential for integration of open data and NASA Earth observations into a flood risk forecasting tool capable of informing real-time decision-making.

Location

Maryland - Goddard

Term

Summer 2020

Partner(s)

Howard County Government, Office of Emergency Management
Howard County Government, Stormwater Management Division
NOAA, National Weather Service, Baltimore-Washington Weather Forecast Office

NASA Earth Observations

GOES-16 ABI

Team

Erika Munshi (Project Lead)
Ryan Hammock
Eli Orland
Alina Schulz

Advisor(s)

Dr. John Bolten (NASA Goddard Space Flight Center)
Brian Cleary (Howard County Storm Water Management Division)
Dr. Sujay Kumar (NASA Goddard Space Flight Center)
Perry Oddo (Science Systems & Applications, NASA Goddard Space Flight Center)