Using Machine Learning and our data processing pipeline running at scale on the AWS cloud, we build relationships between compiled ground plot attributes (species, height, volume, biomass) and characteristics (average height, point density, vegetation indexes) derived from remotely sensed landscape coverage data (LiDAR, imagery). 

Models are developed at the plot level, where the predictions are applied to segments seamlessly covering the entire landscape, creating an Enhanced Forest Inventory (EFI). 

Models can also be developed at an individual tree level, where predictions are subsequently applied to individual trees (segmented from the landscape coverage data), resulting in an Individual Tree Inventory (ITI). 

HRIS provides accuracies of the individual attribute predictions for each uniquely segmented EFI or ITI object.