In a computer-implemented method, one or more digital aerial images of a property of a current or potential policyholder may be received. The digital aerial image(s) (e.g., camera images, spectrometer images, LiDAR images, etc.) may be processed according to one or more image analysis techniques to determine one or more features of the property. The property feature(s) (e.g., tree heights, distances between trees and homes, sizes and/or masses of tree limbs, presence of ice dams, etc.) may be analyzed to determine a risk of damage to a structure or object located on the property. Based on the risk of damage, a risk output that includes (i) an indication of whether action should be taken to mitigate the risk of damage, (ii) an indication of whether insurance coverage associated with the structure or object should be offered, and/or (iii) a measure of the risk of damage, may be generated.