WCW26

Utilities must prioritize large inventories of linear assets to develop defensible capital plans. The task is complicated by the volume and variability of data that must be considered. This joint investigation by New Castle County, DE (NCC) and Jacobs evaluates how different risk scoring formulas influence pipe asset prioritization in rehabilitation programs. The study compares the traditional risk = LOF × COF methodology, which multiplies likelihood of failure (LOF) and consequence of failure (COF) into a single value, with alternative additive approaches.
Our objectives were to evaluate how each scoring method affects rehab prioritization, 10‑year rehabilitation schedules and budgets, and identify the risk prioritization methodology best aligning with NCC’s operational goals and risk tolerance.
This study reflects ongoing collaboration between NCC and Jacobs to create risk scores and manage their sewer and stormwater assets. Analysis incorporates NCC’s GIS asset inventory, work order history, and condition assessments. Additionally, remaining useful life (RUL) estimates and cost estimates were generated, and a predictive AI model was used to flag pipes with high potential defect acceleration using an acceleration factor (AF). NCC is reviewing modeled results and comparing them with field observations, maintenance trends, and planned rehabilitation.
Three prioritization techniques were compared using identical datasets and business rules and differing prioritization techniques.

• Traditional: Single risk value calculated using LOF × COF
• Alternative 1: Refined priority value calculated as COF + 2×LOF 
• Alternative 2: Refined priority value calculated as COF + 2×LOF + AF

When LOF or COF scores were missing, substitutes were made using percent‑life‑used or a peer comparison of pipes within the same basin and age range, for the same material and diameter. For comparison purposes, a 10‑year program was constructed under equal annual budget assumptions, filling each year with the highest‑priority assets.


Findings:
Assessing the Options
When assessing the possible prioritization outcomes, the scoring methods produced meaningfully different prioritization spreads. Traditional LOF × COF provided an irregular range of possible outcomes while the additive options created a more normalized range of outcomes. When assessing the prioritization outcomes, we focused on two hypothetical example pipes.
Comparing Outcomes Using NCC Data
The three prioritization methodologies have been applied across NCC’s full pipe inventory, generating priority scores for every asset. To validate these modeled results, NCC selected a representative subset of pipes to apply manual, engineering‑judgment‑based prioritization, drawing on institutional knowledge. This manually ranked set will serve as a ground‑truth benchmark. The study then compares the modeled priorities to both NCC’s hand‑assigned rankings and NCC’s planned rehabilitation projects to evaluate alignment, highlight discrepancies, and identify opportunities to refine the risk scoring approach.
Significance
Choice of risk formula has direct implications on rehab prioritization, construction workload, budget stability, and long‑term system performance. For NCC, adopting COF + 2×LOF+AF offers tangible benefits: it highlights condition‑driven assets that require timely intervention while still assessing criticality, targets pipe defect degradation, and supports proactive rehabilitation. More broadly, this study provides a replicable, transparent method for utilities to reevaluate their risk modeling and integrate rehabilitation-centric prioritization into capital planning and budgeting.

Municipalities across Canada face the same challenge: thousands of aging sewer assets, inconsistent inspection records, scattered data systems, and limited budgets for renewal. The Regional Municipality of Wood Buffalo (RMWB) tackled these issues by developing a transparent, replicable risk‑based condition assessment framework that any municipality—large or small—can adopt.
In its inaugural year of it's five-year program, transformed 48 km of CCTV inspections and 700 MACP manhole scans into a unified, easy‑to‑communicate asset condition story. Using standardized NASSCO Inc.© (NASSCO) Pipeline Assessment Certification Program ™ (PACP) and Manhole Assessment Certification Program ™ (MACP) defect coding as the foundation, the team applied a structured (Water Research centre’s Sewerage Risk Management approach), using a Structural Performance Grade (SPG) workflow, that translates raw observations into a clear, defensible “likelihood‑of‑failure” score. This score is then combined with a four‑index discretized Consequence of Failure (CoF) model to produce a risk‑ranked inventory that municipal leaders can use for capital planning, budgeting, and Council reporting.


What makes this approach attractive to municipalities is its repeatability and practicality. The SPG model accounts for real‑world field conditions that engages the pipe’s internal condition grade with soil behaviour, surcharge evidence, corrosion potential, and construction impacts, while remaining simple enough for operators, engineers, asset managers, and decision‑makers to understand. By standardizing the process, asset owners minimize subjectivity and create a consistent pipeline of priority‑based work orders, from early trenchless opportunities to urgent repairs.


The first‑year implementation produced an actionable rehabilitation program: a $6.2M sewer backlog and $472k manhole program, later refined into a targeted high‑risk package of approximately $1.75M—a format any municipality can emulate to justify investment and sequence renewal.


This paper demonstrates how municipalities can move from fragmented inspections to a defensible, risk‑driven capital plan within a single inspection cycle, offering a proven roadmap for communities seeking transparency, efficiency, and long‑term sustainability in their wastewater asset management programs.

Across Western Canada, water and wastewater systems are under increasing pressure as aging infrastructure, capacity constraints, and rising construction costs collide with limited government funding and market capacities. Data from Canada’s Core Public Infrastructure Survey shows that the average remaining useful life of waterworks infrastructure in Manitoba, Saskatchewan, Alberta, and British Columbia continues to decline – highlighting the urgent need to renew the critical systems communities rely on every day. But what can municipalities do to address these growing challenges while minimizing financial impacts on the public?
When applied strategically and proactively, lifecycle asset management provides a long-term, data-driven approach to thoughtful decision-making and optimized investment for both new and existing infrastructure – helping owners stretch limited capital dollars, prioritize critical needs, maintain service levels, and reduce lifecycle costs.
Join this session as industry experts share how lifecycle asset management and integrated capital planning can be used as practical tools to deliver water infrastructure projects more strategically, efficiently, and affordably. Attendees will gain insight into designing successful and cost-conscious procurement solutions, as well as how strategic project packaging and thoughtful selections of delivery frameworks can increase long-term value through improved cost certainty, reduced delivery risk, and long-term fiscal management.
Drawing from an active water project in Saskatoon, we will share actionable strategies and real-word guidance to help municipalities better align asset management, capital planning, and project delivery. In the end, attendees will learn how to successfully execute water infrastructure projects that meet the unique needs of communities, while supporting the long-term renewal of aging systems in today’s challenging funding environment.

The City of Regina performs proactive assessment and renewal of the City's water, wastewater, and storm sewer linear networks.  From 2015 to 2024, 60 km of water and trunk mains were either rehabilitated by Cured In Place Plastic Pipe (CIPP) lining or replaced using pipe bursting, horizontal direction drilling (HDD), and traditional open cut methods.  During the same period, 475 km of sanitary mains and trunks were cleaned and inspected, and 125 km were rehabilitated by CIPP lining.  This presentation attempts to quantify the impact of these proactive programs by examining a variety of parameters including water demands and sewage flows, water losses, and system response during rainfall events. 

Effective headworks screening is the foundation of reliable and cost-efficient wastewater treatment. Our presentation, Wastewater Screen Technologies and Design Considerations, provides a comprehensive and practical guide to selecting and designing screening systems that maximize protection of downstream processes, extend equipment life, and reduce long-term operating costs.
 
Drawing on data from the UK Water Industry Research’s internationally recognized National Screen Evaluation Facility, we will demonstrate how Screenings Capture Ratio (SCR) directly impacts plant performance and operational efficiency. Attendees will gain a clear understanding of the comparative effectiveness of screen types—including center flow, through flow, multi-rake, and step screens—and how SCR influences debris removal, maintenance demands, and sludge quality.
 
Beyond theory, the session emphasizes real-world application. We highlight design standards for screen velocities, explore velocity adjustment strategies, and share proven approaches to minimizing headloss and eliminating bypass. Attendees will see how advanced design features—such as stainless steel construction, non-submerged components, replaceable wear tracks, and fully enclosed housings—optimize safety, reliability, and odor control.
 
We will also address the full screening process by examining screenings handling systems, including washing, compacting, dewatering, and transport technologies, ensuring that participants leave with a complete understanding of both front-end screening and downstream solids management.
 
The presentation concludes with case examples across municipal and industrial applications—from membrane bioreactors (MBR) and combined sewer overflows (CSO) to septage receiving stations and industrial intakes—demonstrating the versatility of modern screen designs.
 
By blending technical rigor with practical insights, this session equips decision-makers, designers, and operators with the knowledge needed to select the right technology, ensure regulatory compliance, and deliver long-term operational savings.

Coagtech has been working with utilities in Western Canada to assess optimization of reservoir and pump station operation. For pressure zones where water is provided from a single pump station, optimization to meet system demands is relatively straightforward. However, for complex distribution networks where multiple pump stations provide water to a complex network with reservoirs, pressure reducing stations, and other pump stations the complexity increases significantly. Optimization of operation of these systems can reduce non-revenue water loss, reduce wear on pump station assets, reduce electricity usage, and improve reservoir cycling and water quality.


This presentation will discuss key considerations for optimizing reservoir and pump station operation in complex distribution networks and how machine learning is being used to support decision making at one utility. Specific challenges related to data analysis, hydraulic interactions of the distribution system, and overall system optimization will be shared. A hybrid machine learning methodology for modelling complex distribution systems will be discussed. Technology implementation approach to support operations in real time, challenges and benefits of technology adoption, and the central role of the operator will be highlighted.

Everyone understands the importance of water and wastewater service master planning. Few understand the importance of undertaking a similar exercise for their SCADA system. After all, it’s just that black box in the corner, right? Why would you want to spend the time, effort and money putting together a master plan for something that costs so little? The answer to that question lies in the cost of failure, the risk to your business and the potential impacts to others including the public.
 
Your SCADA system is the single asset that provides you with the ability to remotely monitor and control all your water and wastewater assets. So why is the perceived value of SCADA systems so low? Why aren’t they given the attention that other assets are? Imagine if your SCADA system failed and it took a week to restore. Could you operate your facilities locally for that long? Would you be able to record regulatory data at the required frequency for that long? What would it cost? When you perform inventory and condition assessments of your assets, are the instruments, PLCs and network equipment overlooked? A SCADA master plan will not only shed light on the true value of your SCADA system, but begin to help plan for its continued improvement over time. 
 
Like anything else, SCADA master plans can come in all shapes and sizes. There is no pre-defined scope or scale for a SCADA master plan. It can be whatever you want it to be. Whatever fits the size and complexity of your organization. Or even whatever you have budget for right now. The key is not to treat your SCADA system with the ‘if it ain’t broke, don’t fix it’ mentality. It’s worth more than that and should be treated with more attention and care.

Coagulation chemistry is a complex process impacted by several variables and is regarded as “the single most important factor affecting treatment plant performance” (AWWA M37, 2011). Changes in source water characteristics due to seasonality, runoff, and other conditions require appropriate adjustments to coagulant and polymer doses to maintain efficient treatment. Adjustment can be challenging, as the full impacts of coagulant dosing decisions are not seen for hours, and in some cases, days, and may be impacted by combinations of several parameters. Predictive models can help operational staff optimize coagulant and polymer dosing decisions during both rapidly changing and stable raw water conditions.


Coagtech has been working with several large drinking water treatment plants with varying source waters, coagulants, clarification technologies, and levels of instrumentation to assess and deploy machine learning for coagulation optimization. Assessments have been completed at water treatment plant serving a combined population of >4M people.


This presentation will provide an overview of coagulation, machine learning, and the key considerations for water treatment coagulation optimization. Specific challenges related to data gathering, data analysis, and modelling will be highlighted. Technology implementation approach, including the central role of the operator, and challenges and benefits of the technology adoption will be shared.

As digital tools rapidly expand across the construction and asset assessment industries, practitioners are challenged to determine which technologies genuinely enhance workflows without adding complexity. This presentation highlights practical, high-value solutions that are already transforming how project teams capture information, make rehabilitation decisions, and reduce time in the field.
 
For site assessments, we demonstrate how Sphere XG (formerly HoloBuilder) provides remote, full context access to jobsites through consolidated 360° visual documentation. By integrating images from multiple scanning devices into a single platform, Sphere XG streamlines photo management, improves project transparency, and significantly reduces the number of required site visits. Examples from the City of Winnipeg’s NEWPCC Program will illustrate how this approach enhances information retention from site walks, supports future tie in planning, and accelerates decision making.


In parallel, artificial intelligence is reshaping gravity sewer condition assessment by drastically reducing the effort required for CCTV review. This presentation will show how AI can be embedded into existing workflows, how high quality data drives defensible rehabilitation recommendations, and how digital tools improve the accuracy and consistency of defect identification. Attendees will see real world examples of AI-assisted processes that save time, reduce costs, and support more reliable rehabilitation planning.


Together, these technologies demonstrate how embracing digital tools—rather than fearing them—can elevate project efficiency, improve documentation quality, and unlock better outcomes for both field and office teams. 

Machine learning (ML) is increasingly applied in Water Resource Recovery Facilities (WRRFs) to improve operational decision-making, yet most implementations remain fragmented and highly dependent on either large historical datasets or narrowly defined use cases. This work presents a unified fit-for-purpose perspective on scalable ML applications for WRRFs through two complementary case studies addressing both data-rich and data-scarce operational challenges.
The first case study focuses on influent flow forecasting for proactive plant-wide optimization. Accurate forecasts enable improved chemical dosing, staffing, maintenance planning, and mitigation of wet-weather impacts in combined sewer systems. An ensemble ML framework integrating Random Forest (RF), eXtreme Gradient Boosting (XGBoost), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU) models via a meta-learner was developed to leverage the usually available influent flow historical data and provide robust forecasts up to seven days ahead. Tested across 30 WRRFs (2022–2024) with average daily flows ranging from 0.3 to 146 MGD and peak flows approaching 300 MGD, the framework achieved average Mean Absolute Percentage Error (MAPE) below 11% and Nash–Sutcliffe Efficiency (NSE) around 50% for 7-day forecasts, including during extreme wet-weather events. Adaptive preprocessing tailored to dataset characteristics proved critical for consistent performance across diverse facilities.
The second case study addresses data scarcity through a new soft-sensing paradigm for monitoring biological processes without relying on historical plant data. Probabilistic ML models are trained exclusively on synthetic datasets generated from uncertainty-aware mechanistic simulations, producing priors over plausible process behavior. During deployment, predictions are refined through Bayesian updating using sparse laboratory or online measurements without model retraining. Demonstrated for real-time monitoring of both ammonia concentrations and the amount of simultaneous nitrification–denitrification (SND), the framework achieved 90% empirical coverage of true values in simulations and is currently being validated on pilot-scale using only occasional nitrogen measurements.
Together, these case studies illustrate how ML can support both predictive planning and real-time process insight across WRRFs with varying levels of data availability. By combining state-of-the-art ML methods, synthetic-data-driven probabilistic modeling, and Bayesian updating, this work outlines a scalable pathway toward uncertainty-aware digital monitoring and decision support in wastewater treatment systems.