Loading…

Loading grant details…

Completed STANDARD GRANT National Science Foundation (US)

CIVIC-PG Track A: Machine Learning Approaches to Improve Resilience of Water Utilities to Extreme Weather Events

$750K USD

Funder National Science Foundation (US)
Recipient Organization Johns Hopkins University
Country United States
Start Date Oct 01, 2024
End Date Mar 31, 2025
Duration 181 days
Number of Grantees 4
Roles Principal Investigator; Former Principal Investigator; Former Co-Principal Investigator; Co-Principal Investigator
Data Source National Science Foundation (US)
Grant ID 2431342
Grant Description

The objective of this Civic Innovation Challenge (CIVIC) project is to support research on design and implementation of a machine learning (ML)-based system, called WAUTO (Water operations AUTOmation), to optimize wastewater treatment plant operations during extreme weather events. Working with the Little Patuxent Wastewater Reclamation Plant (LPWRP), researchers from the Johns Hopkins University Applied Physics Laboratory (APL) and the Whiting School of Engineering (WSE) aim to enhance LPWRP’s resilience to extreme weather.

Climate change is resulting in more frequent floods with higher water levels than what current models predict. In Howard County, MD, two floods, each expected to occur only every 1,000-years, took place within two years. The challenges faced by LPWRP are common nationwide.

Smaller facilities, usually serving economically disadvantaged and marginalized communities, are especially vulnerable to flooding events. The WAUTO intends to enable continued system operation essential to public health and prosperity throughout the disaster. A wide range of stakeholders are engaged, including engineers, plant managers, and government officials.

Success of this project could pave the way for the deployment of cutting-edge ML-based solutions for protecting critical infrastructures of national importance.

In this project, the researchers build a high accuracy model to predict the inflow and plant capacity as well as a model of plant equipment. Using features such as the water table / river levels and weather for the first model, and schematics/documentation and subject matter expertise for the second, the team trains a Reinforcement Learning (RL) agent to optimize plant operations by taking actions such as adjusting water flow rates and equalizing tank levels, based on predictions from the models as well real-time observations.

For the Stage 2 Pilot, WAUTO will deployed at LPWRP through a phased approach as confidence in its performance improves. This civic-academic team consists of professionals from LPWRP, the Howard County Department of Public Works (DPW), researchers from APL and WSE, experts in geology and weather, and members from the broader community.

This project is in response to the Civic Innovation Challenge program’s Track A. Climate and Environmental Instability - Building Resilient Communities through Co-Design, Adaption, and Mitigation and is a collaboration between NSF, the Department of Homeland Security, and the Department of Energy.

This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

All Grantees

Johns Hopkins University

Advertisement
Discover thousands of grant opportunities
Advertisement
Browse Grants on GrantFunds
Interested in applying for this grant?

Complete our application form to express your interest and we'll guide you through the process.

Apply for This Grant