Assessing machine learning tools for methane emission prediction from POME treatment in Malaysia

Abstract Palm oil mill effluent (POME) treatment is an anthropogenic activity contributing to global warming through methane emission. The inability address this issue would deem true the catastrophic impacts of temperatures exceeding 2 °C as was predicted by Intergovernmental Panel on Climate Change (IPCC) in 2015. Little research and development exist GHGs monitoring emissions POME facilities opposed improving biogas production. A emission prediction tool based machine learning models tools can problem consequently facilitate efficient carbon neutrality approaches plants. In study, six regression were explored alongside their kernels using eight predictors, linking towards volume. best model found support vector (SVM) producing performance metrics for R2 RMSE with values 0.45 0.749, respectively.