Estimating areal means and variances of forest attributes using the k-Nearest Neighbors technique and satellite imagery

By Ronald E. McRoberts, Erkki Tomppo, Andrew O. Finley, Juha Heikkinen. 2007

214 citations recorded by the source corpus.

Subfields: Ecology, Environmental Engineering, Nature and Landscape Conservation

View Paper: https://www.semanticscholar.org/paper/840e2766274a9c020bd9e4289b4dec7bdf57f5e4

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Ecology

In Environmental Engineering

In Nature and Landscape Conservation

Citations in the corpus

Predicting categorical forest variables using an improved k-Nearest Neighbour estimator and Landsat imagery (2009, methodology): “Thus, multivariate, non-parametric, nearest neighbour techniques have enjoyed increasing popularity for forest inventory mapping and estimation applications (McRoberts et al., 2007; Muinonen & Tokola, 1990; Tomppo, 1990).”
Parametric, bootstrap, and jackknife variance estimators for the k-Nearest Neighbors technique with illustrations using forest inventory and satellite image data (2011, methodology): “McRoberts et al. (2007) derived k-NN estimators for the variance and covariances necessary for use with Eq.”
A survey of remote sensing-based aboveground biomass estimation methods in forest ecosystems (2016, methodology): “Detailed descriptions of the K-NN approach can be found in previous publications (Franco-Lopez et al. 2001; McRoberts et al. 2007; Tomppo et al. 2008; McRoberts 2012).”
Multi-sensor data fusion for estimating forest species composition and abundance in northern Minnesota (2011, background): “In recent years, the estimationof forest biophysical parameters using satellite data has become increasingly routine (Franco-Lopez et al., 2001; Cohen et al., 2003; Pulliainen et al., 2003; Rauste, 2005; Hyde et al., 2006; Chopping et al., 2008; McRoberts et al., 2007, and many more).”
Comparison of nearest neighbour approaches for small area estimation of tree species-specific forest inventory attributes in central Europe using airborne laser scanner data (2010, methodology): “It was also sufficient to calculate variances of the kNN predictions (McRoberts et al. (2007) suggest k C 5) and was considered comparable to k values applied in other studies that used ALS data for area-based inventories (e.g., Packalén and Maltamo 2006).”
Model-based mean square error estimators for k-nearest neighbour predictions and applications using remotely sensed data for forest inventories (2009, methodology): “McRoberts et al. (2007) estimators rely on two key assumptions regarding the attribute values of target unit and the k reference units: i) equality of expected values, and ii) equality of the variances.”
A comparative analysis of kNN and decision tree methods for the Irish National Forest Inventory (2009, background): “( 2007 ) stated that due to nearest neighbour techniques being unable to accurately extrapolate, it is important to ensure that the distribution of the covariates of the reference datasets sufficiently cover those of the target dataset.”
Estimation of forest structural parameters using 5 and 10 meter SPOT-5 satellite data (2009, methodology): “…stem density (Cohen & Spies, 1992; Hudak et al., 2006; McRoberts, 2008), basal area (Franklin, 1986; Franco-Lopez et al., 2001; Hudak et al., 2006; McRoberts et al., 2007; McRoberts, 2008; Wolter et al., 2008), above ground biomass or volume (Franco-Lopez et al., 2001; Santoro et al., 2002;…”
Using k-nn and discriminant analyses to classify rain forest types in a Landsat TM image over northern Costa Rica (2008, background): “…as total volume and basal area for temperate and boreal zones (Eisele, 1998; Gjertsen et al., 2000; Koukal et al., 2007; McInerney et al., 2005; McRoberts et al., 2007; Nilsson, 1997; Tomppo, 1991, 1996; Tomppo et al., 1999, 2001), however, it is less commonly used for image based…”