This　paper　builds　a　time　series　combination　forecasting　model,　which　establishes　a　mapping　relationship　between　the　traffic　accident　data　at　the　current　moment,　the　weather　data　at　historical　moments　and　traffic　accident　data.　This　model　is　used　to　analyze　and　model　the　road　data　set　and　weather　data　set　in　Greater　London,　England　from　2000　to　2019,　to　predict　a　number　of　indicators　of　road　traffic　accidents,　and　to　explore　the　applicability　of　this　model　among　different　cities.The　overall　effect　of　the　model　proposed　in　this　paper　is　better,　which　has　important　practical　significance　for　improving　the　level　of　road　traffic　management.