A random forest (RF) classifier is an ensemble classifier that produces multiple decision trees, using a randomly selected subset of training samples and variables. This classifier has become popular within the remote sensing community due to the accuracy of its classifications. The overall objective of this work was to review the utilization of RF classifier in remote sensing. This review has revealed that RF classifier can successfully handle high data dimensionality and multicolinearity, being both fast and insensitive to overfitting. It is, however, sensitive to the sampling design. The variable importance (VI) measurement provided by the RF classifier has been extensively exploited in different scenarios, for example to reduce the number of dimensions of hyperspectral data, to identify the most relevant multisource remote sensing and geographic data, and to select the most suitable season to classify particular target classes. Further investigations are required into less commonly exploited uses of this classifier, such as for sample proximity analysis to detect and remove outliers in the training samples.

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

Land cover monitoring using remotely sensed data requires robust classification methods which allow for the accurate mapping of complex land cover and land use categories. Random forest (RF) is a powerful machine learning classifier that is relatively unknown in land remote sensing and has not been evaluated thoroughly by the remote sensing community compared to more conventional pattern recognition techniques. Key advantages of RF include: their non-parametric nature; high classification accuracy; and capability to determine variable importance. However, the split rules for classification are unknown, therefore RF can be considered to be black box type classifier. RF provides an algorithm for estimating missing values; and flexibility to perform several types of data analysis, including regression, classification, survival analysis, and unsupervised learning.

In this paper, the performance of the RF classifier for land cover classification of a complex area is explored. Evaluation was based on several criteria: mapping accuracy, sensitivity to data set size and noise. Landsat-5 Thematic Mapper data captured in European spring and summer were used with auxiliary variables derived from a digital terrain model to classify 14 different land categories in the south of Spain. Results show that the RF algorithm yields accurate land cover classifications, with 92% overall accuracy and a Kappa index of 0.92. RF is robust to training data reduction and noise because significant differences in kappa values were only observed for data reduction and noise addition values greater than 50 and 20%, respectively. Additionally, variables that RF identified as most important for classifying land cover coincided with expectations. A McNemar test indicates an overall better performance of the random forest model over a single decision tree at the 0.00001 significance level.

An assessment of the effectiveness of a random forest classifier for land-cover classification

(1991). Applied Linear Regression Models. Journal of Quality Technology: Vol. 23, No. 1, pp. 76-77.

Applied Linear Regression Models

Machine learning offers the potential for effective and efficient classification of remotely sensed imagery. The strengths of machine learning include the capacity to handle data of high dimensionality and to map classes with very complex characteristics. Nevertheless, implementing a machine-learning classification is not straightforward, and the literature provides conflicting advice regarding many key issues. This article therefore provides an overview of machine learning from an applied perspective. We focus on the relatively mature methods of support vector machines, single decision trees (DTs), Random Forests, boosted DTs, artificial neural networks, and k-nearest neighbours (k-NN). Issues considered include the choice of algorithm, training data requirements, user-defined parameter selection and optimization, feature space impacts and reduction, and computational costs. We illustrate these issues through applying machine-learning classification to two publically available remotely sensed dat...

https://www.tandfonline.com/doi/pdf/10.1080/01431161.2018.1433343

Implementation of machine-learning classification in remote sensing: an applied review

Machine learning predictive models for mineral prospectivity: an evaluation of neural networks, random forest, regression trees and support vector machines

Airborne lidar systems have become a source for the acquisition of elevation data. They provide georeferenced, irregularly distributed 3D point clouds of high altimetric accuracy. Moreover, these systems can provide for a single laser pulse, multiple returns or echoes, which correspond to different illuminated objects. In addition to multi-echo laser scanners, full-waveform systems are able to record 1D signals representing a train of echoes caused by reflections at different targets. These systems provide more information about the structure and the physical characteristics of the targets. Many approaches have been developed, for urban mapping, based on aerial lidar solely or combined with multispectral image data. However, they have not assessed the importance of input features. In this paper, we focus on a multi-source framework using aerial lidar (multi-echo and full waveform) and aerial multispectral image data. We aim to study the feature relevance for dense urban scenes. The Random Forests algorithm is chosen as a classifier: it runs efficiently on large datasets, and provides measures of feature importance for each class. The margin theory is used as a confidence measure of the classifier, and to confirm the relevance of input features for urban classification. The quantitative results confirm the importance of the joint use of optical multispectral and lidar data. Moreover, the relevance of full-waveform lidar features is demonstrated for building and vegetation area discrimination.

http://recherche.ign.fr/labos/matis/pdf/articles_revues/chehata_etal_IJPRS10.pdf

Relevance of airborne lidar and multispectral image data for urban scene classification using Random Forests

Various multi-echo and Full-waveform (FW) lidar features can be processed. In this paper, multiple classifers are applied to lidar feature selection for urban scene classification. Random forests are used since they provide an accurate classification and run efficiently on large datasets. Moreover, they return measures of variable importance for each class. The feature selection is obtained by backward elimination of features depending on their importance. This is crucial to analyze the relevance of each lidar feature for the classification of urban scenes. The Random Forests classification using selected variables provide an overall accuracy of 94.35%.

/pdf/airborne-lidar-feature-selection-for-urban-classification-4k06nvjjfv.pdf

Airborne lidar feature selection for urban classification using random forests

Large-scale classification of water areas using airborne topographic lidar data

Natural disasters are generally brutal and may affect large areas, which then need to be rapidly mapped to assess the impacts of such events on ecosystems and to prevent related risks. Ground investigations may be complex, whereas remote-sensing techniques enable a fast regional-scale assessment of damage and offer a cost-effective option for large and inaccessible areas. Here, an efficient, quasi-automatic object-based method for change mapping using high-spatial-resolution (HR) (5–10 m) satellite imagery is proposed. Our contribution comprises two main novelties with respect to similar works in forestry. First, an automatic feature selection process optimizes the image segmentation and classification steps via an original calibration-like procedure. Second, an automatic bitemporal classification enables the separation of damaged and intact areas thanks to a new descriptor based on the level of fragmentation of the obtained regions. The mean shift algorithm is used in both the segmentation and classifica...

Object-based change detection in wind storm-damaged forest using high-resolution multispectral images

In forested mountainous areas, the road location and characterization are invaluable inputs for various purposes such as forest management, wood harvesting industry, wildfire protection and fighting. Airborne topographic lidar has become an established technique to characterize the Earth surface. Lidar provides 3D point clouds allowing for fine reconstruction of ground topography while preserving high frequencies of the relief: fine Digital Terrain Models (DTMs) is the key product. This paper addresses the problem of road detection and characterization in forested environments over large scales (>1000 km 2 ). For that purpose, an efficient pipeline is proposed, which assumes that main forest roads can be modeled as planar elongated features in the road direction with relief variation in orthogonal direction. DTMs are the only input and no complex 3D point cloud processing methods are involved. First, a restricted but carefully designed set of morphological features is defined as input for a supervised Random Forest classification of potential road patches. Then, a graph is built over these candidate regions: vertices are selected using stochastic geometry tools and edges are created in order to fill gaps in the DTM created by vegetation occlusion. The graph is pruned using morphological criteria derived from the input road model. Finally, once the road is located in 2D, its width and slope are retrieved using an object-based image analysis. We demonstrate that our road model is valid for most forest roads and that roads are correctly retrieved (>80%) with few erroneously detected pathways (10–15%) using fully automatic methods. The full pipeline takes less than 2 min per km 2 and higher planimetric accuracy than 2D existing topographic databases are achieved. Compared to these databases, additional roads can be detected with the ability of lidar sensors to penetrate the understory. In case of very dense vegetation and insufficient relief in the DTM, gaps may exist in the results resulting in local incompleteness (∼15%).

Nesrine Chehata

Papers

Relevance of airborne lidar and multispectral image data for urban scene classification using Random Forests

Airborne lidar feature selection for urban classification using random forests

Large-scale classification of water areas using airborne topographic lidar data

Object-based change detection in wind storm-damaged forest using high-resolution multispectral images

Large-scale road detection in forested mountainous areas using airborne topographic lidar data