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

By Aaron E. Maxwell, Timothy A. Warner, Fang Fang. 2018

1,739 citations recorded by the source corpus.

ABSTRACT 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 data sets.

Subfields: Ecology, Media Technology

View Paper: https://www.semanticscholar.org/paper/b3de1062d8a462dfdc2938558258f8884abe9f4e

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 Media Technology

Citations in the corpus

A review of machine learning in processing remote sensing data for mineral exploration (2021, background): “Machine learning makes it possible to manage high dimensional data and map features with complicated characteristics (Maxwell et al., 2018).”
In-N-Out: Pre-Training and Self-Training using Auxiliary Information for Out-of-Distribution Robustness (2020, background): “Developing machine learning models trained on remote sensing data is currently a popular line of work for practical problems such as typhoon rainfall estimation, monitoring reservoir water quality, and soil moisture estimation [29, 33, 1].”
Land-Use Land-Cover Classification by Machine Learning Classifiers for Satellite Observations - A Review (2020, methodology): “The accuracy of a classification varied with methods, techniques, time and space [41,52,93,94].”
Land Cover Classification using Google Earth Engine and Random Forest Classifier - The Role of Image Composition (2020, methodology): “, SVM) is that only two parameters (ntree and mtry) are required to be optimized, facilitating the application of RF [72].”
Recent Applications of Landsat 8/OLI and Sentinel-2/MSI for Land Use and Land Cover Mapping: A Systematic Review (2020, methodology): “[46] analyzed machine learning implementation in LULC classification models, focusing on algorithms, training data requirements, user-defined parameters, and computational costs.”
A comparative assessment of canonical correlation forest, random forest, rotation forest and logistic regression methods for landslide susceptibility mapping (2018, neutral): “For effective use of machine learning algorithms, widely used to model highdimensional complex-structured data, this issue can be of particular concern (Maxwell et al. 2018).”
Remote Sensing Approaches for Monitoring Mangrove Species, Structure, and Biomass: Opportunities and Challenges (2019, background): “The recent application of machine learning algorithms and data integration to mangrove mapping has contributed to a number of new publications that shed light on various aspects of the mangrove ecosystem, especially those that have data with high dimensionality [19].”