Methods

Atlas relies on the incredible data storage and geospatial analysis capacities of super computing. Atlasx requires only geo-referenced training points that identify the different classes of interest, which most often represents ecosystems or land cover classes. Each training point is then intersected with a range of training datasets (predictors) to train a random forest classifier. Once the random forest is trained, Atlasx classifies all of the pixels present in a study area into one of the classes present in the training set. Atlasx uses freely available, high resolution, ecosystem-scale, and publicly available biophysical (slope, elevation), spectral, and climatic (precipitation, temperature) datasets to inform the classification. Users can also upload their UAV orthomosaics to Atlasx. Each dataset is quickly processed into relevant indices, such as the Normalized Difference Vegetation Index (NDVI), before having to training and run the classifier.