Riparian areas are an integral component of the forest hydrologic system. However, systematic management and conservation of riparian vegetation remains a challenge when the extent and nature of riparian vegetation is not easily characterized. Thus, describing riparian vegetation structural attributes and mapping riparian extent is important for stream protection and restoration. This study discriminated riparian and upland vegetation zones in two watersheds on Vancouver Island, Canada, and characterized vegetation attributes ascribed to streamside forest vegetation using fine-scale airborne laser scanning (ALS) data with field-based measurements for controls. Comparison of ALS metrics for riparian and upland vegetation plots indicated metrics of canopy cover, height, and vertical canopy complexity were significantly different. Machine learning was used to model the probability of riparian and upland vegetation zone extent in each watershed and to determine which ALS metrics were the most important for discriminating between these two zones. Separate models were built for each watershed and results indicated that each watershed's model had different ALS metrics that were important for model development, reflecting the different management histories associated with each watershed. Models achieved overall classification accuracies of 65–77% using a 10-fold cross validation. Probability maps were then developed to characterize riparian extent, indicating that the majority of riparian areas in these watersheds were within 20 m of a stream. Additionally, riparian areas were found up to 200 m away from the stream, which is beyond the current provincial regulation widths set for riparian buffers in forested areas in British Columbia, Canada. However, the majority (roughly 75%) of vegetation within existing management buffers was riparian, although this differed by stream classification. We conclude that ALS data provides a potentially useful source of information for determining the characteristics and extent of riparian vegetation.