Waste Management 4.0: An Application of a Machine Learning Model to Identify and Measure Household Waste Contamination—A Case Study in Australia

Author:
Open Access
Publisher website
Google Scholar
Abstract
Waste management directly and indirectly contributes to all sustainable development goals. Hence, the modernisation of the current ineffective management system through Industry 4.0-compatible technologies is urgently needed. Inspired by the fourth industrial revaluation, this study explores the potential application of waste management 4.0 in a local government area in Perth, Western Australia. The study considers a systematic literature review as part of an exploratory investigation of the current applications and practices of Industry 4.0 in the waste industry. Moreover, the study develops and tests a machine learning model to identify and measure household waste contamination as a waste management 4.0 case study application. The study reveals that waste management 4.0 offers various opportunities and sustainability benefits in reducing costs, improving efficiency in the supply chain and material flow, and reducing as well as eliminating waste by achieving holistic circular economy goals. The significant barriers and challenges involve initial investments in developing and maintaining waste management 4.0 technology, platform and data acquisition. The proof-of-concept case study on the machine learning model detects selected waste with considerable precision (over 70% for selected items). The number and quality of the labelled data significantly influences the model’s accuracy. The data on waste contamination are essential for local governments to explore household waste recycling practices besides developing effective waste education and communication methods. The study concludes that waste management 4.0 can be an effective tool for acquiring real-time data; however, overcoming the current limitations needs to be addressed before applying waste management 4.0 into practice.
Funding Information
  • City of Canning (RES-63426)

This publication has 47 references indexed in Scilit: