SBIR Phase II: A Decision Support Platform for Urban Watershed Management and Water Infrastructure Planning

Award ID: 2423488

The broader/commercial impact of this Small Business Innovation Research (SBIR) Phase II project addresses the critical financing and complex operational challenges in managing water infrastructure by developing an open and extensible Artificial Intelligence (AI) platform that also enables enhanced interoperability and maintainability. The proposed solution aims to enhance operational decision-making and facilitate innovative financing for essential water infrastructure by integrating models that also forecast the socio-economic impact of infrastructure actions alongside process-based and watershed models. It aims to enhance infrastructure resilience, supporting sustainable urban growth and improving quality of life in urban areas. It also is designed to promote social equity through more equitable distribution of water resources and improved access for underserved communities thereby supporting NSF's mission of providing technological leadership with broader societal impact. Furthermore, the successful commercialization of this platform could generate significant economic benefits, including job creation and tax revenues. The key technical innovation of this project lies in the development of an open AI software platform for water and wastewater utilities, which utilizes a multi-agent orchestration module to improve the accessibility and maintainability of digital and model-based tools. Model integration driven by an innovative emulation approach, where a deep learning model is used to mimic the behavior of a physics-based model that allows for watershed scale simulations to be run at conversational speed. This integration enables the creation of two AI tools designed to address infrastructure planning and operational needs. The primary goals of the research are to successfully demonstrate interoperability of the AI platform, as well as demonstrate speed and accuracy of the the neural networks emulating individual spatial elements of process-based models within a unified watershed-scale model. The project will culminate in a year-long pilot of the AI platform and model-based tools in the DC Metro region. This pilot aims to demonstrate the platform's value in operational settings and bring the software to a commercially ready state, ultimately providing actionable insights for water infrastructure management and supporting the development of more resilient infrastructure. 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.

NSF Program Director: Rajesh Mehta