Ecological “big data”: Human activities are rapidly altering the natural world. Nowhere is this more evident, perhaps, than in the Arctic, yet this region remains one of the most remote and difficult to study. Researchers have increasingly relied on animal tracking data in these regions to understand individual species' responses, but if we want to understand larger-scale change, we need to integrate our understanding across species. Davidsonet al.introduce an open-source data archive that currently hosts more than 15 million location data points across 96 species and use it to show distinct climate change responses across species. Such ecological “big data” can lead to a wider understanding of change.Science, this issue p.712
Arctic tundra vegetation communities are spatially heterogeneous and may vary dramatically from one meter to the next. Consequently, representing Arctic tundra vegetation communities accurately requires very high resolution raster maps (<5 m grid cell size). However, using remotely sensed data to produce maps with sufficient spatial detail at an extent appropriate for understanding landscape-scale ecological patterns is challenging. In this study, we used predictor layers derived from airborne lidar and high-resolution (∼5 cm) 4-band airborne imagery to classify vegetation communities at 20 cm spatial resolution for three landscapes (12.5 km2 total) near the Toolik Lake research area in the Alaskan Low Arctic. The maps were built using a Random Forest model that was trained and tested on 800 ground reference plots, using classes derived from commonly used legends on existing polygon maps of the area. Withheld test plots (25% of dataset) had a balanced map accuracy of 0.57, kappa of 0.47, and weighted (fuzzy) kappa of 0.65. These maps provide high-resolution plant community information that can serve as important baseline reference data for vegetation monitoring and change detection in this rapidly changing tundra ecosystem, and as validation for coarser scale maps. They also permit fine-scale characterization of landscape phenomena such as community-level nutrient dynamics and wildlife habitat suitability in an important Arctic research site. Our approach demonstrates that very high resolution mapping results can be achieved and validated by integrating high-resolution remote-sensing datasets from multiple sensors in a machine learning model trained on simple field reference data.