Random forest classifier for remote sensing classification

By Mahesh Pal. 2005

3,119 citations recorded by the source corpus.

Subfields: Ecology, Environmental Engineering, Management, Monitoring, Policy and Law

View Paper: https://www.semanticscholar.org/paper/69df1caff94c73addf54d6f43e803cbb0932ace4

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 Management, Monitoring, Policy and Law

Citations in the corpus

Tree Species Classification with Random Forest Using Very High Spatial Resolution 8-Band WorldView-2 Satellite Data (2012, background): “A detailed description of RF can be found in [16,17] and in particular for remote sensing applications in [18,22].”
Predicting Diabetes Mellitus With Machine Learning Techniques (2018, background): “RF generates many decision trees, which is very different from decision tree algorithm (Pal, 2005).”
Geographical random forests: a spatial extension of the random forest algorithm to address spatial heterogeneity in remote sensing and population modelling (2019, background): “The former is set as high as computationally ef ﬁ cient with most RS applications ranging between 200 and 500 while the latter is determined through minimization of the OOB error (Pal 2005).”
On Oblique Random Forests (2011, background): “1 Introduction Random forests have gained popularity in high-dimensional and ill-posed classification and regression tasks, for example on micro-arrays [19], time series [37], or spectral data [39, 29], but also for inference in application such as image segmentation or object recognition in compute”
Mapping vegetation morphology types in a dry savanna ecosystem: integrating hierarchical object-based image analysis with Random Forest (2014, background): “In land-cover mapping studies, RF classification has been found to yield overall accuracies that are either comparable to or better than other state-of-the-art classifiers such as neural networks and support vector machines (Pal 2005).”
Support Vector Machine Versus Random Forest for Remote Sensing Image Classification: A Meta-Analysis and Systematic Review (2020, methodology): “Although methods based on bagging, such as RF, unlike other methods based on boosting, are not sensitive to noise or overtraining [129], [130], the above-stated”
Random forest regression and spectral band selection for estimating sugarcane leaf nitrogen concentration using EO-1 Hyperion hyperspectral data (2013, methodology): “The usefulness of the technique was also explored to predict (e.g. Ismail 2009) or classify (Pal 2005; Gislason, Benediktsson, and Sveinsson 2006; Everingham et al. 2007) features of interest using hyperspectral data.”
A comparative analysis of kNN and decision tree methods for the Irish National Forest Inventory (2009, methodology): “It has been utilized widely in boreal forest conditions (Mäkelä and Pekkarinen 2001, Haapanen et al. 2004, Gjertsen 2007) and in Mediterranean forest conditions (Maselli et al. 2005). These studies have all assessed a wide variety of configurations of operational parameters and explanatory variables”
The multispectral separability of Costa Rican rainforest types with support vector machines and Random Forest decision trees (2010, methodology): “Amazonian studies have demonstrated that previously unrecognized rainforest types show a statistically significant relationship with Landsat Thematic Mapper (TM) and Enhanced Thematic Mapper (ETMþ) spectral bands (Tuomisto et al. 2003a, Salovaara et al. 2005).”
Mapping invasive plants using hyperspectral imagery and Breiman Cutler classifications (RandomForest) (2006, background): “, 2004), and recently in remote sensing studies (Bunn et al., 2005; Pal, 2005).”
Implementation of machine-learning classification in remote sensing: an applied review (2018, methodology): “As with so much in the machine-learning literature, studies that have investigated parameterization for SVMs provide contradictory results.”
Comparing Machine Learning Classifiers for Object-Based Land Cover Classification Using Very High Resolution Imagery (2014, background): “Therefore, many studies have been conducted to investigate the effectiveness and efficiency of different classifiers [11–14].”