Most of the distribution network accidents in coastal areas are caused by natural disasters, among which typhoon is the most serious. Although typhoon is a small probability weather event, once it appears, it will have a serious impact. Making scientific and effective optimization strategy for emergency repair and recovery is conducive to improve the speed of power restoration after disaster. This paper presents a two-stage optimization strategy for emergency repair and recovery of distribution network under typhoon disaster. In the first stage, the fault probability of distribution network line is calculated according to the multi-source heterogeneous data monitored under typhoon disaster. On this basis, the location model of temporary allocation center for emergency repair of distribution network is established with the goal of minimizing the loss of load caused by fault line waiting for emergency repair. In the second stage, considering the uncertainty of distribution network fault after typhoon disaster, Monte Carlo scenario generation and synchronous back generation scenario reduction are used to generate the post-disaster distribution network fault scenario. Based on the idea of cooperation between mobile distributed power supply and emergency repair personnel, the improved genetic algorithm is used to solve the optimization model of post-disaster distribution network fault emergency repair and recovery. Finally, IEEE 33 bus system is used to verify the scientific nature and validity of the proposed method.