Data analytics approach to create waste generation profiles for waste management and collection

Harri Niska*, Ari Serkkola

*Corresponding author for this work

Research output: Contribution to journalReview ArticleScientificpeer-review

10 Citations (Scopus)


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.

Original languageEnglish
Pages (from-to)477-485
Number of pages9
JournalWaste Management
Early online date1 May 2018
Publication statusPublished - Jul 2018
MoE publication typeA2 Review article in a scientific journal


  • Cluster analysis
  • Data analytics
  • Data mining
  • Machine learning
  • Waste generation
  • Waste monitoring

Fingerprint Dive into the research topics of 'Data analytics approach to create waste generation profiles for waste management and collection'. Together they form a unique fingerprint.

  • Projects

    ARVI: Materiaalien arvovirrat

    Serkkola, A., Usman, M. & Törn, M.


    Project: Business Finland: Strategic centres for science, technology and innovation (SHOK)

    Cite this