IDEA #7WCQ0X A method to forecast hurricane induced power loss from satellite nightlights. 23A0024

Key Words: Power, weather simulation, machine learning, forecasting. The developed algorithm produces forecast of the hurricane induced change in nighttime lights radiance, also referred as power loss. It uses a high resolution weather simulation model to make predictions. The main differences from traditional power outages forecast models is: a) the model can be trained and deployed without requiring any data from the utility (i.e. power outages records); and b) the model is fully based on publicly available data, mainly satellite-based nighttime lights. This power loss forecast model has a wide range of potential applications for: utility companies in areas where power outages records are not recorded or incomplete to anticipate were major damage is going to happen after a hurricane event, critical infrastructure management and the industry to be prepared for hurricane induced blackouts. The proposed power loss forecasting application has global implications as it can be implemented to any city or neighborhood around the world. 63/306,624 Filing Date : February 4, 2022