VODA.ai METERS
See which meters have accuracy issues, quantify the volume at risk, and focus action where billable revenue is most exposed. Reduce apparent losses and make more confident replacement decisions.
revenue Recovery
See where meter performance puts billable revenue at risk across your system. Bring apparent losses into view, set priorities for investigation and testing, and protect your revenue with more targeted action.
Customer Satisfaction
Get ahead of meter issues before they create billing corrections, bill shock, and customer disputes. Support fair billing and protect customer trust with earlier visibility. When you know which meters need attention sooner, you can address issues earlier and reduce avoidable customer friction.
Capital Planning
Focus testing, investigation, and replacement planning on the meters with the strongest case for action. Direct limited capital and field effort toward the assets with the highest volume at risk and the greatest revenue exposure, and avoid replacing meters that are still performing as expected.
How it works
Use the data already in your system to set clearer priorities for investigation, testing, and replacement.
Step 1
Use meter reads and meter records, including usage history, age, size, model and more, to build a stronger foundation for decision-making.
Step 2
Identify the meters most likely to have an accuracy issue and narrow the field for investigation and testing.
Step 3
Estimate Volume at Risk, connect it to revenue at risk, and support payback analysis so you can prioritize field action and make better replacement decisions.
REAL RESULTS
A leading U.S. utility used VODA.ai Meters to uncover meters that were silently under-measuring water – outperforming traditional age-based meter replacement strategies.
Water recovery
156 MGal/yr vs. 25 MGal/yr.
Cost avoided
$54.6M/yr vs. $7M/yr.
RESOURCES
Blog
Water meters are the financial backbone of any water utility. They track every gallon delivered, determine how much customers are…
Brochure
Inaccuracy is not the issue. The issue is where revenue is leaking and which meters require attention.
Event
Meet us at ACE 2026 in The Innovation Hub to learn how AI-driven risk prediction is delivering real world results for utilities across the US.
Webinar
How utilities are using AI to prioritize pipe renewal, foresee future risk, and uncover failing meters before they create costly surprises.
FAQ
Water meters degrade over time and often begin under-registering flow silently. One recent study found meters undercounted water flow by up to 10%. Even small errors of 2-3% translate into millions in annual revenue loss for large utilities. Utilities may deliver water they aren’t fully billing for without triggering obvious alerts.
Meter accuracy loss happens quietly. A meter may appear normal while silently under-registering. Without precise visibility into which meters are failing, utilities can’t prioritize where to focus limited resources. Traditional approaches, age-based replacement, customer complaints, regional schedules, are blunt instruments. They often result in replacing meters still performing well while missing ones losing revenue silently.
Utilities traditionally rely on meter age, customer complaints, regional replacement schedules, and usage patterns. But these approaches are blunt instruments. A meter may be old and still perform well. Another may appear normal but quietly under-register. Without precise prioritization, utilities spend time and budget on low-priority meters while leaving revenue at risk elsewhere.
Complaint-driven replacement is reactive, by the time customers notice billing anomalies, the utility has already lost months of billable volume. Usage-pattern analysis requires manual work across large populations and is prone to errors. Age-only replacement assumes meters degrade predictably, which isn’t true. Utilities need a data-driven answer to: “Of our 100,000 meters, which 500 should we investigate first to maximize revenue recovery?” Without that clarity, they guess, and capital gets misallocated. The result: lost revenue and customer disputes.
Meter accuracy refers to how precisely a water meter measures flow. When meters lose accuracy, they typically under-register, recording less water than actually flowed through. This creates a silent revenue leak. When utilities under-measure water delivered, they bill customers for less than they should. That missed billable volume is lost revenue.
One recent study found meters undercounted water flow by up to 10%. Even 2-3% system-wide accuracy loss can represent significant annual revenue. Meter accuracy issues are silent; they don’t trigger alarms. A meter slowly under-registers for 12-18 months, accumulating missed revenue. When eventually discovered, utilities face two problems: revenue already lost and customer relations damage. When corrections occur, customers receive higher bills or back-billing notices, causing disputes and eroding trust. For utilities, meter accuracy isn’t just operational, it’s a revenue protection issue requiring early visibility and proactive correction.
VODA.ai Meters ingests data from existing meter reading systems and utility records most utilities already maintain: historical meter readings (typically monthly or more frequent), meter metadata (age, size, model, installation date), and meter records. No new hardware, sensors, or infrastructure investment required.
Most utilities already have the data needed to begin. The solution pulls directly from billing systems and operational records utilities maintain today. Key requirements: structured meter metadata (age, size, type) and monthly or more frequent meter reads. If you have 12 months of billing data and basic meter information, you can start identifying accuracy issues. Additional data sources, like SCADA readings or maintenance history, strengthen the analysis, but aren’t prerequisites to begin.
Traditional bench testing identifies meters currently out of specification; AI identifies meters likely to have accuracy issues. Bench testing is definitive but tests only sampled meters. AI analysis is predictive, ranking 100% of meters by risk. Both are valuable, AI prioritizes which meters deserve testing resources. Rather than testing random samples, utilities focus lab and field resources on high-risk meters AI identifies, making testing more efficient and effective.
VODA.ai Meters does not physically test, calibrate, or replace meters. It does not replace bench testing. It complements existing meter programs by providing data-driven prioritization. AI answers: “Which meters should we test first?” This approach supports more efficient capital spending. Utilities can focus field crews and bench-testing resources on meters with highest probability of accuracy issues and greatest Volume at Risk. Rather than guessing which meters deserve investigation, utilities have a ranked, data-driven roadmap for action.
Undetected meter under-measurement creates silent revenue leaks accumulating for months. When eventually discovered, utilities face cascading problems: revenue already lost, unexplained Non-Revenue Water raising questions in regulatory reporting, and customer disputes from sudden billing corrections. When meters are corrected, customers may receive bills 30-40% higher than normal or back-billing notices, triggering disputes and eroding trust.
Utilities end up spending hours explaining bill increases, defending NRW gaps without clear evidence of origin, and fielding complaints without visibility into root causes. Field crews deploy reactively (triggered by angry calls) rather than strategically (targeted by data). Customer disputes over bill shock damage utility-customer relationships and perception. Early detection prevents this cascade by enabling proactive correction before revenue is lost and disputes occur. By identifying meter accuracy issues earlier, utilities address them before they escalate into billing disputes and regulatory reporting problems.
Utilities need a ranked list of meters most at risk of accuracy issues with estimates of Volume at Risk per meter. This enables data-driven prioritization: investigating and testing high-revenue-impact meters first, avoiding unnecessary replacement of still-performing meters, and focusing field work strategically. VODA.ai Meters provides a risk score for each meter and Volume at Risk estimates to rank investigation priority.
Rather than guessing or relying on age-based rules, utilities get a clear roadmap for investigation and testing. This approach enables: recovering lost revenue by correcting inaccurate meters sooner, reducing unnecessary spending by avoiding replacement of performing meters, prioritizing field work toward highest-impact meters, and making defensible capital decisions with specific Volume at Risk estimates. Instead of defending replacement choices based on age or policy, utilities point to Volume at Risk data. Instead of discovering failures through customer complaints, utilities can be proactive, directing limited capital toward meters most likely to recover billable revenue.
Protect billable revenue, improve billing outcomes, and focus action where it matters most.
