Moata Smart Water
Developed in partnership with multiple water authorities, Moata Smart Water enables the real-time analysis of water datasets to support the proactive maintenance of the three water networks.
The use cases below demonstrate how the deployment of digital twins can support decision making throughout the water cycle to predict and better manage incidents.
Predictive Water Quality
Data analysis combining historical sampling data, network hydraulics, sewer monitoring, weather data and hydrodynamics to produce a three-day water quality forecast communicated to the public.
Leverage Moata API and data-feeds pipelines to enable real-time data analysis.
Generate custom analytics based on the quality and availability of your datasets.
Reduce occurrence of water quality incidents through early warning systems.
Configured in partnership with your team, our solution will meet your specific needs, integrate with your existing workflows, and get value from your investment from day one. This is in contrast to off-the-shelf software packages you can find elsewhere that only meet some of your needs.
Enhanced rainfall radar processing and nowcasting used in combination with hydraulic models and stormwater monitoring for flood forecasting, storm events response and post-event reporting.
Custom alarms to identify storm events before they happen.
Two-hour rain radar and flood nowcasting refreshed every five minutes.
Automated custom post-event reporting.
Real-time sensor data, traditional hydraulic models and machine learning combined to identify network anomalies in clean water and sewer systems.
Machine learning anomaly detection identifies incidents rapidly and with confidence.
Visual models and alarm and reporting systems to support decisions.
Network characteristics baselined to measure improvements.
Management of asset condition inspections, reporting, and machine learning combined to give priority to maintenance work and mitigate large scale failures.
Full workflow management from work package assignment to reporting.
All asset inspections kept in one place.
Automated asset scoring and custom reporting.
Machine learning used for inspection auditing and assigning priority to upcoming inspections.
Real-time sensor data and continuous biological simulations combined to predict and improve wastewater treatment operations.
Sensor drift and anomaly detection supported by machine learning.
Treatment improvements enabled through scenarios modelling simulation.
Automated reporting gives summaries of outcomes.