To address the decline in power supply capability of distribution networks during typhoons, it is necessary to fully utilize distributed resources in distribution networks and enhance the resilience of distribution networks during disasters from multiple aspects such as. To address the decline in power supply capability of distribution networks during typhoons, it is necessary to fully utilize distributed resources in distribution networks and enhance the resilience of distribution networks during disasters from multiple aspects such as. To improve the accuracy of typhoon-induced hazard intensity forecasting, an LSTM network enhanced with multi-scale attention (LSTM-MSA) is developed, which overcomes the deficiency of the traditional LSTM model that cannot capture the local attention mechanism. Building on this, a. Under the impact of typhoon disasters, the judicious utilization of tie lines and emergency resources can enhance the resilience of distribution systems. Leveraging Deep Reinforcement Learning (DRL) technology, a two-stage resilience enhancement (TSRE) method for distribution systems is proposed to. To enhance the resilience of cyber-physical distribution systems against typhoons, this paper proposes a resilience-oriented robust optimization model, in which planning-operational restoration measures are incorporated into a prevention and emergency response framework.