Predicting individual tree attributes from airborne laser point clouds based on the random forests technique

By Xiaowei Yu, Juha Hyyppä, Mikko Vastaranta, Markus Holopainen, R. Viitala. 2011

379 citations recorded by the source corpus.

Subfields: Environmental Engineering, Insect Science, Nature and Landscape Conservation

View Paper: https://www.semanticscholar.org/paper/1fb4ba2619a7679fb2f01048772618430e6a4f7d

How researchers see this paper

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

In Environmental Engineering

In Insect Science

In Nature and Landscape Conservation

Citations in the corpus

Analysis of the Influence of Plot Size and LiDAR Density on Forest Structure Attribute Estimates (2014, methodology): “As Figure 1 shows, there is some discrepancy when defining field sampling plot size when working with LiDAR data [5,9–31].”
An International Comparison of Individual Tree Detection and Extraction Using Airborne Laser Scanning (2012, background): “[38] presented an accuracy of 69% for tree detection under various forest conditions (different forest densities, ages, site types and tree species).”
IDENTIFYING STANDING DEAD TREES IN FOREST AREAS BASED ON 3D SINGLE TREE DETECTION FROM FULL WAVEFORM LIDAR DATA (2012, methodology): “Techniques for tree extraction from LIDAR data have been investigated for mapping forests at both plot and tree levels to identify important structural parameters (Korpela et al., 2010; Yu et al., 2011).”
Importance of sample size, data type and prediction method for remote sensing-based estimations of aboveground forest biomass (2014, methodology): “Zolkos et al. (2013) conducted a meta-analysis on LiDAR-based estimation of forest biomass and found a negative relationship between model errors and the size of inventory plots.”
Comparison of airborne laser scanning methods for estimating forest structure indicators based on Lorenz curves (2014, background): “Furthermore, random forest (RF) is also becoming increasingly popular in ALS remote sensing (Falkowski et al., 2009; McInerney et al., 2010; Yu et al., 2011).”
Evaluation of most similar neighbour and random forest methods for imputing forest inventory variables using data from target and auxiliary stands (2012, methodology): “Lidar data have been employed, alone or integrated with other sources of remote-sensing data, to provide useful information through modelling of forest attributes on tree, sample plot and stand levels (see, for example, Hudak et al. 2008, Straub et al. 2009, Yu et al. 2011).”
Allometric equation choice impacts lidar-based forest biomass estimates: A case study from the Sierra National Forest, CA (2012, methodology): “Although non-parametric approaches are increasingly used to odel forest parameters with airborne discrete return lidar data e.g., Hudak et al., 2006; Yu et al., 2011), further exploration is equired for more refined use of non-parametric approaches in iomass estimates using lidar data.”
Assessment of Low Density Full-Waveform Airborne Laser Scanning for Individual Tree Detection and Tree Species Classification (2014, methodology): “In addition, 27 DSC features were calculated from all normalized vegetation points of DSC data as some of them have been used in previous studies for individual tree attributes estimation [47].”
A new variable importance measure for random forests with missing data (2012, background): “However, the variety of recent publications, like that of Yu et al. (2011), indicate that the original permutation importance is still extremely popular in many research ﬁelds.”
Tree species classification and estimation of stem volume and DBH based on single tree extraction by exploiting airborne full-waveform LiDAR data (2012, neutral): “(Hyyppä & Inkinen, 1999; Hyyppä, Kelle, et al., 2001; Hyyppä, Schardt, et al.2001; Persson et al., 2002; Holmgren & Persson, 2004; Heurich, 2006; Yu et al., 2011; Korpela et al., 2010).”