Estimation and mapping of forest stand density, volume, and cover type using the k-nearest neighbors method

By Hector Franco-Lopez, A. Ek, Marvin E. Bauer. 2001

491 citations recorded by the source corpus.

Subfields: Ecology, Environmental Engineering, Nature and Landscape Conservation

View Paper: https://www.semanticscholar.org/paper/db2d3bbad3688b801b260cbab651d0974c8fe532

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

Estimation of forest structural parameters using 5 and 10 meter SPOT-5 satellite data (2009, background): “…Spies,1990; Song&Woodcock, 2003; Song, 2007), 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…”
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).”
Using satellite imagery as ancillary data for increasing the precision of estimates for the Forest Inventory and Analysis program of the USDA Forest Service (2005, methodology): “For the k-NN approach (Franco-Lopez et al. 2001; Katila and Tomppo 2001; McRoberts et al. 2002b), the set of pixels with associated plots was denoted the reference set, and the set of pixels requiring predictions was denoted the target set.”
Retrieving forest structure variables based on image texture analysis and IKONOS-2 imagery (2006, methodology): “For example, Franco-Lopez et al. (2001) reported a relative RMSE of about 55% on basal area estimates using Landsat TM data and the k-Nearest Neighbors method.”
yaImpute: An R Package for kNN Imputation (2008, methodology): “The basic method, within the forest attribute imputation context, is described by Tomppo (1990), McRoberts, Nelson, and Wendt (2002), and Franco-Lopez, Ek, and Bauer (2001).”
Enalos KNIME nodes: Exploring corrosion inhibition of steel in acidic medium (2013, methodology): “The produced model was validated using external validation and cross validation methods [21].”
Model-based mean square error estimators for k-nearest neighbour predictions and applications using remotely sensed data for forest inventories (2009, background): “The situation can be improved if one has ancillary data for each unit in the AOI that are correlated with the attribute(s) of interest.”
Estimating areal means and variances of forest attributes using the k-Nearest Neighbors technique and satellite imagery (2007, methodology): “The k-NN technique has gained popularity in forestry applications for mapping forest attributes using the spectral values of satellite imagery (Franco-Lopez et al., 2001; McRoberts et al., 2002a; Trotter et al., 1997).”
Non-parametric prediction and mapping of standing timber volume and biomass in a temperate forest: application of multiple optical/LiDAR-derived predictors (2010, methodology): “Different numbers of k have been applied in several studies (e.g. Franco-Lopez et al., 2001; Holmström and Fransson, 2003; Haapanen et al., 2004; Maltamo et al., 2006; Packalén and Maltamo, 2006; Packalén and Maltamo, 2007; Finley and McRoberts, 2008; Vauhkonen et al., 2010), in some of which the…”
Integration of forest mapping and inventory to support forest management (2010, methodology): “Examples of NN applications are provided by Franco-Lopez et al. (2001), Tomppo et al. (2002a, 2009), Chirici et al. (2008), McRoberts (2009a).”
Multi-sensor data fusion for estimating forest species composition and abundance in northern Minnesota (2011, methodology): “By and large, this is because it is difficult to adequately account for the full range of spectral variability of forests using ground-based training data (Holmgren & Thuresson, 1998; Franco-Lopez et al., 2001), due to differences in density, age, understory vegetation, soil, slope, etc.”
Nearest neighbor imputation of species-level, plot-scale forest structure attributes from LiDAR data (2008, methodology): “Imputation with a single nearest neighbor produces imputations with similar variance structure to that of the observations (Moeur & Stage, 1995; Franco-Lopez et al., 2001; McRoberts et al., 2002).”
A comparison of four methods to map biomass from Landsat-TM and inventory data in western Newfoundland (2006, methodology): “The value of k was chosen because earlier studies have shown that no real gain in accuracy was reached by using more than 10 neighbors, and that using a smaller number of k keeps the natural spatial variability and produces results with similar accuracies (Fazakas et al., 1999; Franco-Lopez et al., ”
A linear mixed-effects model of biomass and volume of trees using Landsat ETM+ images (2007, methodology): “The K nearest neighbor (KNN) represents one type of nonparametric methods extensively applied for forest classification (Atta-Boateng and Moser, 1998; Franco-Lopez et al., 2001; Trotter et al., 1997).”
Design-based approach to k-nearest neighbours technique for coupling field and remotely sensed data in forest surveys (2009, methodology): “Of these methodologies, the k-nearest neighbours (k-NN) technique is becoming increasingly popular (Franco-Lopez et al., 2001; Katila & Tomppo, 2001; Maselli et al., 2005; McRoberts et al., 2002; Tomppo et al., 2002; Tomppo & Halme, 2004).”