Case study
Prediction of water consumption in the city enhanced by analysis of external factors.
Offices:
Poland
Company size:
60-200 employees (med)
Industry:
Government
Revenue:
Non-profit org
We build a tool increasing the efficiency of municipal water strategy and help water pumping station dispatcher
Supplying municipal water you can't afford to make a mistake - a shortage of water for some city institutions can have dire consequences. The inertia of the water supply system is high - as a result, you can't react quickly if a mistake is made. That's why predicting demand and the state of the water supply network can prove to be a key support in effective urban water management.
Water systems are intimately connected with natural systems, but Technology can upgrade water security
Water security isn’t only a matter of having enough water. It is also about having enough water of sufficient quality for all of the myriad ways we use water — to drink, bathe, clean, produce energy, build things, and make food. And that includes growing the food, processing it, transporting it, cleaning it, and cooking it. All of those require reliable and safe water supplies.
NO TIME TO WASTE
Scope of work
Our goal was to create dashboard providing data-driven insights for station dispatchers
WE LOVIN' IT
Challenges
Absorb domain knowledge
The field of urban water management is an extremely specific field with its own unique data characteristics. Part of our work was to learn about the nature of the processes and extract knowledge from experts
Enriching time series prediction with additional variables
The values of pressure and flow of water are continuously read by sensors monitoring the city's water supply, thus we can consider the problem of predicting successive values as a time-series prediction. In order to improve the quality of the model, it was also provided with external data,. which may affect the city's water resources management such as the weather or ongoing mass events.
Conformal prediction
Not only did we provide detailed information about water supply indicators but also showed how certain the model is. Confidence intervals were added to charts allowing quick identification of areas where the model lacked confidence.
Anomaly studies
The system for delivering water to residents is crucial, and absolutely no one can afford failures. Therefore, we have built a system that detects detections based on time-series data.
I am proud that our team can deploy technology where it impacts our daily lives
Engineers at bards.ai work mainly on commercial projects. In this project, we enjoyed the fact that we could not only test our knowledge, but also apply it to something that is useful to hundreds of thousands of people every day.
Michał Pogoda
Co-founder at bards.ai