A Novel Domain Knowledge-Informed Machine Learning Approach for Modeling Solid Waste Management Systems.

Sustainability challenges, such as solid waste management, are usually scientifically complex and data scarce, which makes them not amenable to science-based analytical forms or data-intensive learning paradigms. Deep integration between data science and sustainability science in highly complementary manners offers new opportunities for tackling these conundrums. This study develops a novel hybrid neural network (HNN) model that imposes the holistic decision-making context of solid waste management systems (SWMS) on a traditional neural network (NN) architecture. Equipped with adaptable hybridization designs of hand-crafted model structure, constrained or predetermined parameters, and a customized loss function, the HNN model is capable of learning various technical, economic, and social aspects of SWMS from a small and heterogeneous data set. In comparison, the versatile HNN model not only outperforms traditional NN models in convergence rates, which leads to a 22% lower mean testing error of 0.20, but also offers superior interpretability. The HNN model is capable of generating insights into the enabling factors, policy interventions, and driving forces of SWMS, laying a solid foundation for data-driven decision making.

Impact of COVID-19 lockdown measures on waste production behavior in Lisbon.

The recent restrictions on mobility and economic activities imposed by governments due to the COVID-19 pandemic have significantly affected waste production and recycling patterns in cities worldwide. This effect differed both between cities and within cities as the measures of confinement adopted by governments had diverse impacts in different areas of cities, depending on their characteristics (e.g., touristic, or residential). In the present work, mixed waste collection areas were created, based on waste collection points, that define spatial units in which contextual data such as tourism and residential characteristics were aggregated. The difference in mixed waste collected compared with previous years was analyzed along with the impacts on recycling due to the modification in operations regarding waste collection during the lockdown. The results showed that despite the suspension of the door-to-door recycling system during the lockdown, this did not translate into an increase in the production of mixed waste, and the recycling levels of previous years have not been reached after the lockdown, indicating a possible change in recycling habits in Lisbon. The touristic and non-residential mixed waste circuits presented significantly reduced mixed waste production compared to the non-pandemic context. Also, tourist, mobility, and economic activity were measured to understand which factors contributed to waste production changes during the COVID-19 pandemic. While little evidence of a relationship with these exogenous variables was found at the citywide level, evidence was found at the waste collection circuit level.