A Comparison of Advanced Regression Algorithms for Quantifying Urban Land Cover

Remote Sensing

Akpona Okujeni¹  Sebastian van der Linden¹  Benjamin Jakimow¹  Andreas Rabe¹  Jochem Verrelst² 

[1] Geography Department, Humboldt-Universität zu Berlin, Unter den Linden 6, 10099 Berlin, Germany; E-Mails:;Image Processing Laboratory, University of Valencia, C/Catedrático Agustin Escardino 9, 46980 Valencia, Spain; E-Mail:

关键词: machine learning;    regression;    sub-pixel mapping;    spatial resolution;    imaging spectrometry;    hyperspectral;    urban land cover;   

DOI  :  10.3390/rs6076324

来源: mdpi

【 摘 要 】

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.

【 授权许可】

CC BY   
© 2014 by the authors; licensee MDPI, Basel, Switzerland