Next Article in Journal
Development of Methods for Detection and Monitoring of Fire Disturbance in the Alaskan Tundra Using a Two-Decade Long Record of Synthetic Aperture Radar Satellite Images
Previous Article in Journal
Evaporative Fraction as an Indicator of Moisture Condition and Water Stress Status in Semi-Arid Rangeland Ecosystems
Article Menu

Export Article

Open AccessArticle
Remote Sens. 2014, 6(7), 6324-6346; doi:10.3390/rs6076324

A Comparison of Advanced Regression Algorithms for Quantifying Urban Land Cover

1
Geography Department, Humboldt-Universität zu Berlin, Unter den Linden 6, 10099 Berlin, Germany
2
Image Processing Laboratory, University of Valencia, C/Catedrático Agustin Escardino 9, 46980 Valencia, Spain
*
Author to whom correspondence should be addressed.
Received: 31 March 2014 / Revised: 30 June 2014 / Accepted: 2 July 2014 / Published: 7 July 2014
View Full-Text   |   Download PDF [2420 KB, uploaded 7 July 2014]   |  

Abstract

Quantitative methods for mapping sub-pixel land cover fractions are gaining increasing attention, particularly with regard to upcoming hyperspectral satellite missions. We evaluated five advanced regression algorithms combined with synthetically mixed training data for quantifying urban land cover from HyMap data at 3.6 and 9 m spatial resolution. Methods included support vector regression (SVR), kernel ridge regression (KRR), artificial neural networks (NN), random forest regression (RFR) and partial least squares regression (PLSR). Our experiments demonstrate that both kernel methods SVR and KRR yield high accuracies for mapping complex urban surface types, i.e., rooftops, pavements, grass- and tree-covered areas. SVR and KRR models proved to be stable with regard to the spatial and spectral differences between both images and effectively utilized the higher complexity of the synthetic training mixtures for improving estimates for coarser resolution data. Observed deficiencies mainly relate to known problems arising from spectral similarities or shadowing. The remaining regressors either revealed erratic (NN) or limited (RFR and PLSR) performances when comprehensively mapping urban land cover. Our findings suggest that the combination of kernel-based regression methods, such as SVR and KRR, with synthetically mixed training data is well suited for quantifying urban land cover from imaging spectrometer data at multiple scales. View Full-Text
Keywords: machine learning; regression; sub-pixel mapping; spatial resolution; imaging spectrometry; hyperspectral; urban land cover machine learning; regression; sub-pixel mapping; spatial resolution; imaging spectrometry; hyperspectral; urban land cover
Figures

This is an open access article distributed under the Creative Commons Attribution License (CC BY 3.0).

Scifeed alert for new publications

Never miss any articles matching your research from any publisher
  • Get alerts for new papers matching your research
  • Find out the new papers from selected authors
  • Updated daily for 49'000+ journals and 6000+ publishers
  • Define your Scifeed now

SciFeed Share & Cite This Article

MDPI and ACS Style

Okujeni, A.; van der Linden, S.; Jakimow, B.; Rabe, A.; Verrelst, J.; Hostert, P. A Comparison of Advanced Regression Algorithms for Quantifying Urban Land Cover. Remote Sens. 2014, 6, 6324-6346.

Show more citation formats Show less citations formats

Related Articles

Article Metrics

Article Access Statistics

1

Comments

[Return to top]
Remote Sens. EISSN 2072-4292 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top