Tetra Tech helped TasWater detect sewage blockages early and prevent major spills by developing a model that integrates predictive analytics with monitoring and reporting software.
TasWater is Tasmania’s primary water and sewerage utility, with more than 200,000 water connections and 176,000 sewerage connections across the state. A key challenge for this industry is managing sewer blockages and subsequent spills that occur in the mains system. Often the first notification of a spill comes from a member of the public, hours and sometimes days after the first spill. This can intensify public health and environmental impacts and the cost of clean-up efforts. Following a major spill at Midway Point, an environmentally significant site, TasWater contracted Nukon, A Tetra Tech Company, to take what they learned from Midway Point and design an online system that uses live and historical data to predict future sewer spills before they occur.
Benefits
- Fast deployment and low cost of implementation
- Early detection helps protect the environment by reducing significant incidents
- Event correlation provides improved insights into network and asset behavior
- Sophisticated analytical toolset for historical and real-time process data analytics
Leveraging historical time-series data and Seeq analytics, Tetra Tech built a proof-of-concept detection model for Midway Point sewage pumping stations that uses time between pump runs (time-to-fill) as the primary indicator. The team identified normal fill/run patterns for on‑peak versus off‑peak and weekday versus weekend profiles, then flagged deviations, such as unusually long fill times or absent pump runs during peak periods, in real time. The solution integrates monitoring and notification software so field teams receive early alerts for investigation before spills occur.
Validation data from the August 2017 spill showed Tetra Tech’s model would have detected the blockage 13 hours before the incident was reported, with zero false positives. After a 12‑month trial focused on Midway Point for tuning, the model was deployed across regional sewage pumping station sites with site‑specific behaviors and grace periods to minimize false alarms. Continued data collection and added variables have improved accuracy and the system has since enabled early response to an overflow notification and supported communication with the Environment Protection Authority. The approach delivers faster insights on time‑series data, reduces spreadsheet work, and helps protect residents, shellfish industries, the environment, and TasWater’s operations.
The solution has already demonstrated value in detecting abnormal operating conditions in the sewerage network trial area beyond the capability of previous methods.
Matt Jordan, Manager Network Asset Performance, TasWater
Hear from Tetra Tech’s Andrew May to learn how our solution for TasWater helped quickly predict and prevent potential major public health crises.