Use Cases and Examples

Energy Saving with Geothermal Heating

See how machine learning can predict energy and cost savings.

Helsinki City Bike Prediction

Interactive demo that predicts bike availability depending on weather.

Time series predictions

Quantifying the cost reduction of geothermal heating.

It is known that geothermal heating lowers the heating costs. But what is the reduction and how the outdoor temperature affects the reduction?

Machine learning and namely time series predictions give a reliable insight on the potential electricity consumption reduction. To estimate this reduction and also to verify the impact of varying outdoor temperature a recurrent neural network (RNN) with gated recurrent units (GRUs) was deployed. With the model electricity consumption was predicted for the period when the old heating system was already swapped with a geothermal heating system.

 

In the graph the green vertical dotted line shows the time when the new heating system was deployed. The blue line shows the actual (relative) electricity consumption and the red line shows the predicted consumption if the new system was not deployed. The shaded area shows the difference (or savings) between the old and the new systems. Looking the graph, it is obvious that the impact has been remarkable.

Will I find a bike?

Predicting city bike availability

Launched in 2016, the city bikes in Helsinki have quickly gained a huge popularity. Just two years later, the service counts over 2500 bikes, distributed over more that 250 stations.

Combining open data from Helsinki Region Transport (HSL) and the Finnish Meteorological Institute (FMI; or Ilmatieteenlaitos), Churnbusters built a model that predicts the availability of the bikes depending on the weather and time of day, so you’ll never arrive at an empty station again.