GEOSPATIAL MODELING OF ROADSIDE VEGETATION RISK ON DISTRIBUTION POWER LINES IN CONNECTICUT

Abstract. Roadside trees cause almost 90% of the power outages in forested Northeastern US. Management roadside vegetation risk on electrical infrastructure demands timely and accurate information forest conditions. Tasking conventional ground-based scouting methods along thousands kilometers powerlines a repeated fashion are labor-/cost-/time-intense. Geospatial earth observation (EO) technologies serve as cost-effective tools monitoring, inspecting, managing utility corridors. EO technologies, from drones, aircraft, to satellites can efficiently acquire over large areas at regular intervals while probing physical structure health LiDAR is useful data stream for modeling terrain conditions estimation multiple inventory variables that explain forest. Various imagery provides bio-physical characteristics affect finer granularity. The goal this study combine environmental develop spatially-explicit model using machine learning algorithms. Some key inputs used our analysis include LiDAR-derived tree-related (e.g., tree height, proximity pixels, canopy cover), (slope, aspect, topographic index), soil characteristics, management (tree trimming methods), (wire type), reported 2005 2017 Connecticut. Findings research will be vital informing decision-making processes, which eventually reduce cost corridor maintenance.