The Forest Line Mapper: A Semi-Automated Tool for Mapping Linear Disturbances in Forests

Abstract

Forest land-use planning and restoration requires effective tools for mapping and attributing linear disturbances such as roads, trails, and asset corridors over large areas. Most existing linear-feature databases are generated by heads-up digitizing. While suitable for cartographic purposes, these datasets often lack the fine spatial details and multiple attributes required for more demanding analytical applications. To address this need, we developed the Forest Line Mapper (FLM), a semi-automated software tool for mapping and attributing linear features using LiDAR-derived canopy height models. Accuracy assessments conducted in the boreal forest of Alberta, Canada showed that the FLM reliably predicts both the center line (polyline) and footprint (extent polygons) of a variety of linear-feature types including roads, pipelines, seismic lines, and power lines. Our analysis showed that FLM outputs were consistently more accurate than publicly available datasets produced by human photo-interpreters, and that the tool can be reliably deployed across large application areas. In addition to accurately delineating linear features, the FLM generates a variety of spatial attributes associated with line geometry and vegetation characteristics from input canopy height data. Our statistical evaluation indicates that spatial attributes generated by the FLM may be useful for studying and classifying linear features based on disturbance type and ground conditions. The FLM is open-source and freely available and is aimed to assist researchers and land managers working in forested environments everywhere.

Identifying differences in roadless areas in Canada based on global, national, and regional road datasets

“…Previous mapping projects, including the Human Access of Canada's Landscapes (Global Forest Watch Canada, 2014) and the Boreal Ecosystem Anthropogenic Disturbances (BEAD; Environment and Climate Change Canada, 2012) datasets, produced broad‐scale maps of roads and other disturbances using interpretation of imagery, but manual maps of roads are challenging to create and consistently maintain at national scales. There have been some efforts to conduct automated extraction and mapping of roads (Clode et al, 2007; Doucette et al, 2004; Jin & Davis, 2005) and other linear features (Queiroz et al, 2020), but not at spatial extents such as the entirety of Canada or even a single province. Semi‐automated mapping techniques using artificial intelligence (AI) approaches, such as machine learning algorithms applied to high‐resolution satellite imagery, show promise for supplementing the fully manual approaches used in VGI datasets like OSM to fill gaps in global road network maps (Basu et al, 2019).…”

Quantifying forest disturbance regimes within caribou (Rangifer tarandus) range in British Columbia

“…High-resolution satellite data could be used to generate a snapshot of current linear disturbance levels; however imagery is not available throughout the complete study period. Data from airborne laser scanning (ALS) has also been shown to be effective at identifying linear disturbance, and with the BC government’s announcement of a plan to collect provincial wall-to-wall ALS data, this may be feasible within the next few years 94 , 95 , however, this will also only provide a snapshot of current linear disturbance levels, and long time-series analysis using this data will not be possible.…”