Municipal　solid　waste　incineration　(MSWI)　can　realize　the　resource,　harmlessness　and　reduction　of　municipal　solid　waste　(MSW),　which　is　a　very　effective　method　of　MSW　treatment.　The　furnace　temperature　is　crucial　for　this　process,　ensuring　complete　breakdown　of　harmful　substances　and　stable　operation.　The　mechanism　of　MSWI　is　complex,　and　there　are　many　variables　and　uncertain　factors.　In　order　to　improve　the　accuracy　of　the　furnace　temperature　model,　the　Light　Gradient　Boosting　Machine　(LightGBM)　is　used　to　model　the　furnace　temperature　with　Bayesian　Optimization　(BO)　for　model＇s　hyperparameter　tuning.　The　results　indicate　a　substantial　enhancement　in　the　accuracy　of　the　furnace　temperature　model　based　on　LightGBM　optimized　by　BO.　©　2024　IEEE.