LAUSR

Extensive monitoring data on waste generation is increasingly collected in order to implement cost-efficient and sustainable waste management operations. In addition, geospatial data from different registries of the society are opening for free usage. Novel data analytics approaches can be built on the top of the data to produce more detailed, and in-time waste generation information for the basis of waste management and collection. In this paper, a data-based approach based on the self-organizing map (SOM) and the k-means algorithm is developed for creating a set of waste generation type profiles. The approach is demonstrated using the extensive container-level waste weighting data collected in the metropolitan area of Helsinki, Finland. The results obtained highlight the potential of advanced data analytic approaches in producing more detailed waste generation information e.g. for the basis of tailored feedback services for waste producers and the planning and optimization of waste collection and recycling.