Generalized models to predict the lower heating value (LHV) of municipal solid waste (MSW)

Accurately and efficiently predicting the LHV of MSW is vital for designing operating a waste-to-energy plant. However, previous prediction models possess limited geographical applicability. In this paper, we employ multiple linear regression artificial neural network (ANN) techniques to predict LHV. These data-driven utilize 151 globally distributed datasets identified during systematic literature review, describing wet physical composition measured The results show that built via both methods exhibited acceptable compatible levels performance in LHV, based on statistical indicators. ANN model proved be more robust handling diverse quality. Models developed from demonstrate clearly proportion food waste has negative impact Supported by strong significant correlation between moisture content, concluded high content outweighed its calorific value. Separating or any other with incineration can significantly improve energy recovery efficiency. Contrary expectation, also reveal higher contribution paper than plastic waste.