Welvaarts Weegsystemen supplies weighing systems with which the weight per container is registered. Waste disposal is still a challenge in many cities. Think of garbage bags that are next to a container because it was full, or containers that are emptied while not yet full. MKB Datalab helped to optimize this process by creating a model that predicts how full an underground container is. Thanks to this insight, waste services can dynamically change their route and empty containers in a more targeted manner.
Welvaarts Weegsystemen has collected a lot of data in the past years. Amongst others the weighing results of underground waste containers, with the aim of creating management information that can ultimately be controlled. In addition to saving time, determining the ideal moment for emptying containers also entails other advantages, such as limiting emissions from the vehicles and relieving the burden on infrastructure. That is why Welvaarts can gain a lot from a good estimate of when a container is ‘nicely full’ and can best be emptied.
We started working with container data from Amsterdam as a starting point. We linked the weighing data from Welvaarts to external data such as the weather, public holidays and possible activities in the city. There is a chance that these affect the amount of waste at a given moment.
The data was then cleaned up and prepared for further analysis. Welvaarts’ weighing data was not always accurate and consistent, due to the dependence on drivers and trucks. Because the quality of the data was not optimal, we were able to make a predictive model, but the performance was less than hoped for.
However, this has led Welvaarts to reconsider how they can further automate this weighing process so that they are less dependent on the driver. In this way they can supply cleaner data in the future and possibly still get to a desired model.
“Although the outcome of the field test is not what we hoped for, we now have more insight into what we need to do to get our data in order so that we can work with dynamic route planning for garbage trucks in the future.”
Richard Welvaarts – Welvaarts Weegsystemen
JADS provides innovative data science programs at undergraduate, graduate and postgraduate level, conducts cutting edge data science research and offers great business opportunities with a continually growing ecosystem. From startups to SMEs and large corporates, our business partners gain access to talent, high level knowledge and business opportunities.
Partner up with JADS like 300+ other organizations and businesses and shape your data-driven future