Random forest in remote sensing: A review of applications and future directions

By Mariana Belgiu, Lucian Dragut. 2016

6,167 citations recorded by the source corpus.

Subfields: Analytical Chemistry, Ecology, Media Technology

View Paper: https://www.semanticscholar.org/paper/81e20eec7983dea4e61842cc37d70a12c1c0606e

How researchers see this paper

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

In Analytical Chemistry

In Ecology

In Media Technology

Citations in the corpus

GLC_FCS30: global land-cover product with fine classification system at 30 m using time-series Landsat imagery (2020, methodology): “Many studies have demonstrated that the RF performs better with high-dimensional data, gives a higher classification accuracy and is less sensitive to noise and feature selection than other widely used classifiers such 315 as the support vector machine, artificial neural network, and the classificat”
Machine learning and deep learning—A review for ecologists (2022, positive): “…recent applications of ensemble models in E&E include predictions in ecological networks (Pichler et al., 2020 ), linking gene variation to phenotypes (Brieuc et al., 2018 ), species distribution models (Elith & Leathwick, 2009), and various applications in remote sensing (Belgiu & Drăguţ, 2016).”
Deep Learning for Land Use and Land Cover Classification Based on Hyperspectral and Multispectral Earth Observation Data: A Review (2020, methodology): “It has been broadly used to classify the land cover [88–90], and many other applications as reported in [91].”
Improving leaf area index (LAI) estimation by correcting for clumping and woody effects using terrestrial laser scanning (2018, background): “, 2015), as it can handle high data dimensionality with highly correlated features and is both fast and insensitive to overfitting (Belgiu and Drăguţ, 2016).”
Cascaded Recurrent Neural Networks for Hyperspectral Image Classification (2017, background): “For example, one can directly consider the rich spectral signature as features and feed them into advanced classifiers, such as support vector machine (SVM) [2], random forest [3], and extreme learning machine [4].”
Hyperparameters and tuning strategies for random forest (2018, background): “RF has been the topic of several reviews in the last few years including our own review (Boulesteix et al., 2012b) and others (Criminisi et al., 2012; Ziegler and König, 2014; Biau and Scornet, 2016; Belgiu and Drăguţ, 2016).”
A 30-m landsat-derived cropland extent product of Australia and China using random forest machine learning algorithm on Google Earth Engine cloud computing platform (2018, neutral): “…RF classi ﬁ ers can successfully handle high data dimensionality and typically achieve higher accuracies in comparison with other approaches such as maximum likelihood, single decision trees, and single layer neural networks (Belgiu and Dr ă gu ţ , 2016; Lawrence et al., 2006; Na et al., 2010).”
Smallholder maize area and yield mapping at national scales with Google Earth Engine (2019, background): “based applications including crop type mapping, and have the valuable advantage of being intrinsically not prone to overfitting (Inglada et al., 2015; Belgiu and Drăguţ, 2016).”
Assessing the robustness of Random Forests to map land cover with high resolution satellite image time series over large areas (2016, methodology): “A well-known ensemble learning method is Random Forests (RF) of Breiman (2001), which has demonstrated its ability to yield accurate land cover maps (Belgiu and Drăguţ, 2016).”
Quantifying Vegetation Biophysical Variables from Imaging Spectroscopy Data: A Review on Retrieval Methods (2018, methodology): “RF can handle a large number of training samples, does not suffer from overfitting and is robust to outliers and noise (Belgiu and Drăguţ 2016), which makes it an attractive method for spectroscopic mapping applications.”
A review of ensemble learning and data augmentation models for class imbalanced problems: combination, implementation and evaluation (2023, background): “Hence, random forests have been widely applied to remote sensing that deals with very large-scale image-based data [77].”