Pump Station Alerting
Protect performance. Avoid downtime.
Keep pump stations running at peak efficiency with early, precise alerts.
Pumps can fail
suddenly.
We see it first.
StormHarvester Pump Station Alerting is machine learning software that monitors the performance of every pump at a wastewater pumping station (lift station) and alerts operators to early signs of decline or failure.
It turns pump start and stop signals and wet well levels into a performance indicator for each pump, compares it with the site's normal behaviour and the current weather, and raises descriptive alerts such as run time longer or shorter than expected, wet well low, pump possibly ineffective, or level high with no pumps running. Because the thresholds adapt to rainfall, alerts are fewer and more trustworthy than static high-level alarms, so crews can fix issues during normal working hours instead of responding to out-of-hours failures.
Pump station alerting for reliable,
efficient performance
From reducing repair costs to protecting the environment, StormHarvester helps utilities keep pumps operating at their best. Our precise alerts let you act before issues cause service disruption or costly downtime.
Safeguard Environment
Early detection prevents pollution incidents and helps to maintain regulatory compliance.
Target Callouts
Send crews exactly where they’re needed, cutting response times and eliminating guesswork.
Optimise Assets
Maintaining a consistent performance reduces energy and maintenance costs.
How pump station alerting works
StormHarvester uses pump start and stop data to build an analogue performance indicator for each pump and each pumping station in your network. Combined with wet well levels and rainfall, machine learning detects when a pump is taking longer to draw down the wet well, starting more often, running shorter than expected or not moving water at all.
Pump ineffective
Pump performance declining
Shorter/longer than expected run-time
Wet well level low
Blockage detected
88%
Pump alert hit rate at Southern Water
85.6%
Positive intervention rate at Yorkshire Water
4,400+
Pumping station sensors monitored at Yorkshire Water
How AI pump station alerting works, step by step
1. Connect existing telemetry
StormHarvester is sensor-agnostic. It uses the pump start and stop signals and wet well level data your pumping stations already send to telemetry, with no new hardware on site.
2. Build a performance indicator
Machine learning creates a performance indicator for every pump, tracking run times, start frequency and how quickly each pump draws down the wet well.
3. Account for the weather
Thresholds adapt to hyperlocal rainfall, so a busy pump in a storm is not flagged, while the same behaviour in dry weather is.
4. Alert, fix and confirm
A descriptive alert tells crews what is wrong and where. At Southern Water, an alert for slow draw-down led crews to an impeller damaged by brick and rag, and the indicator returned to normal the day after repair.
See Pump Station Alerting in action
How StormHarvester uses pump data to flag faults early, so teams can act before a failure leads to a spill.
Pump Station Alerting demo
How AI flags pump station faults before they lead to a spill.
Pump station alerting results from water utilities
Measured outcomes from utilities using StormHarvester on their own networks.
Southern Water, UK
An 88% alert hit rate, replacing static high-level alarms that were routinely paused during heavy rain. Sites went alert-active within two weeks of the go-ahead, and faults found early included blocked pumps, worn impellers, passing non-return valves, air valve faults, tripped fuses, level control faults and burst rising mains (force mains).
Yorkshire Water, UK
An 85.6% positive intervention rate across more than 4,400 pumping station sensors, with 1,674 alerts helping operations teams prioritise work. In one example, an alert for a pump running shorter than expected led crews to a collapsed bearing, fixed within three days.
Discover how we keep pumps running
From extending equipment life to reducing maintenance costs, Pump Station Alerting helps you minimise downtime and maintain optimal network performance.
Optimise operations.
Enhance reliability.
Minimise downtime.
View real-time pump performance with alert locations
Monitor live pump run times, start frequency, and energy use
Access historical trends, logs, and rainfall correlations
Extend asset life and reduce unplanned maintenance costs through Condition Based Maintenance (CBM)
Inputs
Monitored
Stormharvester
AI Engine
Real-time
Alerts
StormHarvester Products
case studies
Our solutions drive transformative results for wastewater utilities, municipalities and environmental agencies, helping organisations meet regulatory, environmental, operational goals while protecting the environment.
Yorkshire Water
In 2024, Yorkshire Water recognised that reactive alarm and incident management was no longer sustainable. Alarm noise was consuming operational capacity and crowding out proactive work. By embedding StormHarvester, the utility set out to build a proactive, insight-led way of working that could keep pace with future requirements without adding complexity.
Southern Water
Southern Water replaced a system overwhelmed by noise with one built for signal. With StormHarvester’s Pump Station Alerting, alert accuracy reached 88% turning out-of-hours reactive callouts into planned, targeted responses during normal working hours.
South West Water
South West Water cut their blockage detection trial short not because it wasn’t working, but because it was working so well they moved straight to full deployment. They’ve since expanded from 300 sites to 1,500 overflow points across the network.
Our wastewater solutions
Stay ahead of challenges with real-time intelligence that helps you maximise network efficiency, reduce costs, and prevent pollution.
Inflow & Infiltration
Detection
Blockage
Detection
Rising Main
Alerting
Spill
Analysis
Network
Control
Built for performance. Trusted worldwide.
From the UK to New Zealand, water utilities rely on StormHarvester for fewer incidents, faster response, and easier reporting, all powered by AI-driven insight and real-time data.
Trusted by
