You are here

Keyword: imputation

Users guide to the Most Similar Neighbor Imputation Program Version 2

Publications Posted on: August 01, 2018
The Most Similar Neighbor (MSN, Moeur and Stage 1995) program is used to impute attributes measured on some sample units to sample units where they are not measured. In forestry applications, forest stands or vegetation polygons are examples of sample units. Attributes from detailed vegetation inventories are imputed to sample units where that information is not measured.

Fire Lab tree list: A tree-level model of the western US circa 2009 v1

Datasets Posted on: March 15, 2018
Maps of the number, size, and species of trees in forests across the western United States are desirable for many applications such as estimating terrestrial carbon resources, predicting tree mortality following wildfires, and for forest inventory.

Mapping forest vegetation for the western United States using modified random forests imputation of FIA forest plots

Publications Posted on: October 25, 2016
Maps of the number, size, and species of trees in forests across the western United States are desirable for many applications such as estimating terrestrial carbon resources, predicting tree mortality following wildfires, and for forest inventory.

A tree-level model of forests in the western United States

Science Spotlights Posted on: September 14, 2016
https://www.treesearch.fs.fed.us/pubs/53114Maps of the number, size, and species of trees in forests across the western United States are desirable for a number of applications including estimating terrestrial carbon resources, tree mortality following wildfires, and for forest inventory. However, detailed mapping of trees for large areas is not feasible with current technologies. We used a statistical method called random forests for matching forest plot data with biophysical characteristics of the landscape in order to populate entire landscapes with a limited set of forest plot inventory data. 

Temporal transferability of LiDAR-based imputation of forest structure attributes

Publications Posted on: October 06, 2015
Forest inventory and planning decisions are frequently informed by LiDAR data. Repeated LiDAR acquisitions offer an opportunity to update forest inventories and potentially improve forest inventory estimates through time.

Utilizing random forests imputation of forest plot data for landscape-level wildfire analyses

Publications Posted on: October 05, 2015
Maps of the number, size, and species of trees in forests across the United States are desirable for a number of applications. For landscape-level fire and forest simulations that use the Forest Vegetation Simulator (FVS), a spatial tree-level dataset, or “tree list”, is a necessity.

Quantifying aboveground forest carbon pools and fluxes from repeat LiDAR surveys

Publications Posted on: May 08, 2012
Sound forest policy and management decisions to mitigate rising atmospheric CO2 depend upon accurate methodologies to quantify forest carbon pools and fluxes over large tracts of land. LiDAR remote sensing is a rapidly evolving technology for quantifying aboveground biomass and thereby carbon pools; however, little work has evaluated the efficacy of repeat LiDAR measures for spatially monitoring aboveground carbon pools through time.

The national tree-list layer

Publications Posted on: January 31, 2011
The National Tree-List Layer (NTLL) project used LANDFIRE map products to produce the first national tree-list map layer that represents tree populations at stand and regional levels. The NTLL was produced in a short time frame to address the needs of Fire and Aviation Management for a map layer that could be used as input for simulating fire-caused tree mortality across landscapes.

Aggregating pixel-level basal area predictions derived from LiDAR data to industrial forest stands in North-Central Idaho

Publications Posted on: October 01, 2008
Stand exams are the principal means by which timber companies monitor and manage their forested lands. Airborne LiDAR surveys sample forest stands at much finer spatial resolution and broader spatial extent than is practical on the ground. In this paper, we developed models that leverage spatially intensive and extensive LiDAR data and a stratified random sample of field plots across two mixed conifer forest landscapes in north-central Idaho.

yaImpute: An R package for kNN imputation

Publications Posted on: February 05, 2008
This article introduces yaImpute, an R package for nearest neighbor search and imputation. Although nearest neighbor imputation is used in a host of disciplines, the methods implemented in the yaImpute package are tailored to imputation-based forest attribute estimation and mapping.