You are here

TreeMap: A tree-level model of the forests of the United States

Machine learning matched forest plot data with biophysical characteristics of the landscape to produce a seamless tree-level forest map.

A map of the location, size, and species of every tree in the forests of the United States would be useful for any number of applications, ranging from habitat mapping to estimation of carbon resources. No such map currently exists, but we have used machine learning to make a spatial model of the trees in continental US forests. Detailed maps and descriptions of trees are available where the Forest Inventory Analysis program measures their annual forest plots, however, these plots are widely spaced (approximately one plot per 24.3 km). We based our TreeMap on this detailed forest plot data measured by FIA (https://www.fia.fs.fed.us/) and national gridded maps of forest cover, height, and vegetation type provided by the LANDFIRE project (https://www.landfire.gov/). Using random forests (a type of machine learning algorithm) we match the forest plot data to the gridded vegetation maps, producing a seamless map of the trees of the forests of the US. Specifically, the result is a map of plot ID numbers, which identify the best-matching forest plot for each 30x30 pixel in the map. The map of plot ID numbers can be linked back to the FIA databases (https://apps.fs.usda.gov/fia/datamart/) to generate maps of any number of forest characteristics, ranging from basal area to biomass to species types. Some current uses of the dataset include: 1) inventory of habitat types at regional scales by land managers, 2) research on evaluation of tradeoffs between fuel management and timber harvest targets, and 3) modeling hydrologic effects of fuel treatment.

Click on photos for larger view.

Image: TreeMap workflow

The project workflow. FIA forest plots (reference data) and raster landscape data from LANDFIRE (target data) were employed in a random forests algorithm that imputed the plot data to all forested pixels on the CONUS-wide landscape.

Image: Aerial view of tree list output

Aerial view of tree list output for a section of the Olympic Peninsula, Washington. Each plot ID appears with a different color. Plots cluster along biophysical gradients driven by mountainous topography and stream corridors.

Modified: May 22, 2020

Select Publications & Products

Riley, Karin L., Isaac C. Grenfell, Mark A. Finney, Jason M. Wiener, and Rachel M. Houtman. 2019. Fire Lab tree list: A tree-level model of the conterminous United States landscape circa 2014, https://www.fs.usda.gov/rds/archive/catalog/RDS-2019-0026

Karin L. Riley, Isaac C. Grenfell, Mark A. Finney, Jason M. Wiener. 2018. Fire Lab tree list: A tree-level model of the western US circa 2009 v1. https://doi.org/10.2737/RDS-2018-0003

Riley, Karin L., Isaac C. Grenfell, and Mark A. Finney. 2016. Mapping forest vegetation for the western US using modified random forests imputation of FIA forest plots. Ecosphere 7(10): 1-22. https://www.fs.usda.gov/treesearch/pubs/53114

Karin L. Riley, Isaac C. Grenfell, Mark A. Finney, and Nicholas L. Crookston. 2014. Utilizing random forests imputation of forest plot data for landscape-level wildfire analyses. In: Viegas, D.X. (editor). Proceedings of the VII International Conference on Forest Fire Research. Associacao para o Desenvolvimento da Aerodinamica Industrial. November 17-20, 2014, Coimbra, Portugal. https://www.fs.usda.gov/treesearch/pubs/49563

Conference presentations

Riley, Karin L., Isaac C. Grenfell, Mark A. Finney. 2018. Mapping forest vegetation and biomass for the continental United States using modified random forests imputation of FIA forest plots. Society for Ecological Restoration and Society of Wetland Scientists, Restoring Resilient Communities in Changing Landscapes: October 15-18, 2018, Spokane, Washington. (Invited.)

Riley, Karin L., Isaac C. Grenfell, Mark A. Finney, and Nicholas L. Crookston. 2014. Utilizing random forests imputation of forest plot data for landscape-level wildfire analyses. VII International Conference on Forest Fire Research. Associacao para o Desenvolvimento da Aerodinamica Industrial. November 17-20, 2014, Coimbra, Portugal.

Riley, Karin L., Isaac Grenfell, and Nicholas Crookston. 2014. Random forests imputation of forest plot data for landscape-level analyses. 2014 Society of American Foresters National Convention. Society of American Foresters. October 9-11, 2014, Salt Lake City, Utah.

Riley, Karin L., Isaac C. Grenfell, Mark A. Finney, Alan A. Ager, and Nicholas L. Crookston. 2012. Random Forests imputation of forest plot data for landscape-level wildfire analyses. Association for Fire Ecology 5th Fire Ecology Congress: Uniting Research, Education, and Management. December 3-7, 2012, Portland, Oregon.

Seminars/webinars

Riley, Karin L. Mapping forest vegetation for the continental United States using modified random forests imputation of FIA forest plots. Presented to the Society for Ecological Restoration, Pacific Northwest Chapter, webinar series on June 26, 2018. (Invited.)

Riley, Karin L., Isaac Grenfell, and Mark A. Finney. 2016. Imputation of forest plot data for landscape-level wildfire analyses. Presented at the U.S. Forest Service Fire Sciences Laboratory, as part of the Missoula Fire Lab Seminar Series, on February 4, 2016. (Invited.)