Assessment of Landsat-based terricolous macrolichen cover retrieval and change analysis over caribou ranges in northern Canada and Alaska

Terricolous macrolichens are an important food source for caribou (Rangifer tarandus) and can greatly influence their movement, distribution and demography over time. Mapping the spatial distribution and cover of macrolichens with remote sensing can serve as an important approach for assessing the impact of disturbances (e.g. fire, grazing, trampling) on lichen cover at the landscape scale and for monitoring post-disturbance rates of recovery. Previous remote sensing-based efforts to retrieve the distribution and abundance of lichen have been restricted to particular regions and thus are not indicative of the potential for large extent mapping and monitoring. In this study, we assessed the effectiveness of machine learning methods for retrieving lichen cover and change across different regions in northern Canada and Alaska using Landsat-5 images, topographic and climate data. Global and regional-scale models were evaluated to assess whether regionally specific analyses would improve performance. Of the models tested, the deep neural network was the most accurate for predicting lichen cover (model efficiency (ME) = 0.58, mean absolute error (MAE) < 7%). For the regional analysis, the performance was the best in north-central Canada (ME = 0.56, MAE = 8%) and the worst in north-eastern Canada (ME = 0.22, MAE < 4%) due to lower lichen cover, more exposed ground, and reduced sample quality and distribution. Analysis of trend-based change detection from 1984 to 2011 in the three regional test areas showed the expected directional response with declining lichen cover in north-western Canada in response to climate-induced shrub expansion, slow recovery to wildfire in north-central Canada, and declining lichen cover in north-eastern Canada related to caribou foraging/trampling and shrub expansion.