A framework for mapping tree species combining hyperspectral and LiDAR data: Role of selected classifiers and sensor across three spatial scales

By Aniruddha Ghosh, Fabian Ewald Fassnacht, P. Joshi, Barbara Koch. International Journal of Applied Earth Observation and Geoinformation, 2014

348 citations recorded by the source corpus.

Subfields: Ecology, Environmental Engineering, Media Technology

View Paper: https://www.semanticscholar.org/paper/9a3d5901cc046dc0ed9a841ce70e0ee012444bf3

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 Media Technology

Citations in the corpus

Identification of banana fusarium wilt using supervised classification algorithms with UAV-based multi-spectral imagery (2020, background): “Theoretical and empirical research has demonstrated that the classification accuracy is less sensitive to ntree than to the mtry parameter([26,48]).”
Implementation of machine-learning classification in remote sensing: an applied review (2018, background): “Another option is bootstrapping (e.g. Ghosh et al. 2014), where n randomly sampled replicates are performed and a certain proportion of the data is withheld, for example 33%.”
Will remote sensing shape the next generation of species distribution models? (2015, methodology): “As demonstrated below, these limitations can be overcome in certain cases by using remotely derived species occurrence records.”
Assessing the robustness of Random Forests to map land cover with high resolution satellite image time series over large areas (2016, result): “Many studies have compared RF and SVM accuracies showing comparable performances between both classifiers using different remote sensing data ( Waske & van der Linden, 2008; Duro et al., 2012; Hasan et al., 2012; Dalponte et al., 2013; Löw et al., 2013; Ghosh et al., 2014; Meyer et al., 2016).”
National mapping and estimation of forest area by dominant tree species using Sentinel-2 data (2020, background): “…relatively high spatial resolution (e.g. Waser et al. 2014, Immitzer et al. 2016, Persson et al. 2018); (3) lidar, which provides 3D point clouds (e.g. Hovi et al. 2016, Axelsson et al. 2018); and (4) a combination of these groups, mainly involving lidar (e.g. Ghosh et al. 2014, Liu et al. 2018).”
Comparison of support vector machine, random forest and neural network classifiers for tree species classification on airborne hyperspectral APEX images (2017, methodology): “Based on the work by Braga-Neto and Dougherty (2014)and Ghosh et al. (2014), we decided to use the 0.632 bootstrap approach for generating the test and training dataset.”