Quantifying meteorological impacts on local landfill methane emissions by using field measurements and machine learning

Landfills are a major anthropogenic source of methane (CH 4 ), contributing up to 20 % of global CH 4 emissions. Although CH 4 emissions from landfills are highly sensitive to meteorological conditions, their response to climate variations remains not fully understood, leading to substantial uncertainty in emission projections under climate change. This study evaluated the impact of meteorological factors on landfill CH 4 generation, using a site-specific machine-learning-based model optimized for temperature and precipitation. The model optimized for meteorological conditions performed better than conventional models such as LandGEM and the IPCC model, with a root mean squared error (RMSE) of 6.57 million m 3 CH 4 , a mean absolute error (MAE) of 4.91 million m 3 CH 4 , and Pearson correlation coefficients of 0.89, when compared with field measurements. Sensitivity analysis and OLS regression showed that simulated CH 4 generation had strong positive association with temperature (0.8–1.0 % per 1 °C, p