|
In the context of escalating energy demands and the quest for sustainable waste management
solutions, this paper evaluates the efficacy of three machine learning methods—ElasticNet,
Decision Trees, and Neural Networks—in predicting energy recovery from municipal waste across
the European Union. As renewable energy sources increasingly dominate the energy production
landscape, the integration ofWaste-to-Energy (WTE) processes presents a dual advantage: enhancing
waste management and contributing to the renewable energy mix. This study leverages a dataset incorporating
economic and environmental indicators from 25 European countries, spanning 2013–2020,
to compare the predictive capabilities of the three machine learning models. The analysis reveals that
Neural Networks, with their intricate pattern recognition capabilities, outperform ElasticNet and
Decision Trees in predicting energy recovery metrics, as evidenced by superior performance in key
statistical indicators such as R-value, Mean Squared Error (MSE), and Mean Absolute Error (MAE).
The comparative analysis not only demonstrates the effectiveness of each method but also suggests
Neural Networks as a pivotal tool for informed decision-making in waste management and energy
policy formulation. Through this investigation, the paper contributes to the sustainable energy and
waste management discourse, emphasizing the critical intersection of advanced technologies, policy
considerations, and environmental stewardship in addressing contemporary energy challenges.
|
