The LANDFIRE image-based annual prototype: Detailed annual updates to vegetation maps for the United States using machine learning.

Background/Question/Methods

LANDFIRE is a national program charged with mapping over 700 vegetation types, as well as vegetation cover and height, for all lands at a 30-meter resolution. Historically, LANDFIRE has produced these maps using two methods: a base-layer method consisting of machine learning classification and regression tree (CART) models based on field plots and Landsat image composites (versions LF 2001 and LF 2016), and intervening update layers developed by combining mapped disturbances with rulesets representing changes to cover and height. However, with the growth of cloud-based image and lidar processing, LANDFIRE anticipates moving towards an annual mapping approach more similar to the base layer method, where changes to vegetation lifeform, cover, and height are modeled from annual imagery, compressing what was once a multi-year mapping process into a few months. A prototype is in development that uses recent cloud-based image composites designed for disturbance mapping along with established machine learning models to update vegetation lifeform, cover, and height in disturbed areas. In this presentation we will describe the methods we have investigated and evaluate the results for multiple regions.

Results/Conclusions

To date, preliminary results show that the modeled prototype outputs using the most recent Landsat image composites typically used for disturbance mapping consistently reflect the pattern and amount of vegetation. This prototype is the first step in our planned scaled deployment of these methods for the entire country. Prioritization of vegetation lifeform, cover, and height in areas that have experienced significant disturbance and regrowth may help operationalize these methods for vegetation updates, which will also lead to better fuel mapping for fire behavior modeling.