The Department of Defense (DoD) provides water and wastewater (W/WW) services to a continuously changing population with a broad set of local and federal water quantity and quality standards. To meet present and future needs without costly infrastructure upgrades or putting the installation at risk, data-driven monitoring and control must be leveraged. Data-driven modeling (DDM), including statistical and machine learning (ML), capture real-world variability and system-specific performance with precision unmatched by traditional mechanistic models and controllers. However, the majority of DoD W/WW systems lack the digital infrastructure and knowledge to implement real-time DDM for improved monitoring and control. To address this challenge, this project will do the following:  

• Characterize and assess the potential for data-driven monitoring and control of W/WW utilities at DoD installations.
• Define a framework for installations to develop and deploy data-driven monitoring and control at W/WW utilities.
• Demonstrate the framework at a W/WW utility on a DoD installation.
• Quantify the change in process efficiency (electrical or embedded energy use) and processes reliability (downtime) when data-driven monitoring or control is used.
• Identify the challenges, barriers, and opportunities associated with data-driven monitoring and control of W/WW processes for DoD installations.  

The final framework will allow DoD installations to target capacity building to become resilient digital utilities. 

DDM approaches can capture the complex, multivariate relationships of full-scale W/WW treatment systems with an accuracy that simple feedback controllers and mechanistic models cannot. Both statistical and ML modeling can identify functional correlations that describe the variability in target parameters and paired with modern computing can be executed in near real-time. DDM has shown to provide proactive and precise information for applications such as fault detection, prediction, forecasting, and optimization for W/WW in literature but face a variety of technical and nontechnical barriers for implementation at scale. These barriers include sufficient and quality data collection, accessible data management, operationalized data cleaning, model development for deployment, and functional integration with existing monitoring and control systems. This project will address these barriers for DoD installations and synthesize findings in the form of a framework. The framework will be deployed at a DoD installation to demonstrate the achievable full-scale benefits of DDM in terms of energy savings or event detection when paired with a secure, robust control strategy.

The expected benefits to the DoD include an understanding of the readiness for DoD installations to integrate big data technologies into their existing W/WW treatment infrastructure, and a framework detailing needs for smoothly integrating DDM a checklist for W/WW utilities on DoD installations to build capacity for DDM. The use of this framework could result in a variety of benefits depending on location-specific challenges: increased capacity without costly infrastructure upgrades, proactive response to major events, and reduced electrical and embedded energy use. While this project focuses on centralized applications, this work is a precursor for data-driven monitoring and control of decentralized applications (e.g. reverse osmosis water purification units). (Anticipated Project Completion - 2028)