Prediction of container filling for the selective waste collection in Algeciras (Spain)

Abstract

The aim of this study is to create an intelligent system that improves the efficiency of garbage collection, (cardboard waste, in this particular case). The number of cardboard containers to be collected each day will be determined based on a prediction made on the filled volume recorded in each container. It will be reflected in the cost and fuel savings, reducing emissions and contributing to environmental sustainability. These results will allow planning the sequence of waste removal, which means the optimal collection route considering restrictive parameters such as the type of truck, the location of containers, collection times by zones, and the availability of working staff. A filling prediction system is proposed based on real historical data provided by the current waste collection company in Algeciras (ARCGISA). To achieve this objective, an intelligent system is designed using predictive analytics and several methods based on machine learning, modelling the collection system as a classification model, comparing the results from a statistical point of view (using sensitivity, specificity, etc.). The results obtained with the best-tested method indicate an improvement average rate of 26% in sensitivity performance index and 67% in specificity performance index. Currently, waste collection is carried out without predictive analysis. The relevance of an efficient waste collection system is becoming increasingly important. Achieving optimal waste collection will result in improved service to citizens, cost savings for the administration, and significant environmental improvements.