DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Generalizing machine learning regression models using multi-site spectral libraries for mapping vegetation-impervious-soil fractions across multiple cities

Okujeni, Akpona and Canters, Frank and Cooper, Sam D. and Degerickx, Jeroen and Heiden, Uta and Hostert, Patrick and Priem, Frederik and Roberts, Dar and Somers, Ben and van der Linden, Sebastian (2018) Generalizing machine learning regression models using multi-site spectral libraries for mapping vegetation-impervious-soil fractions across multiple cities. Remote Sensing of Environment, 216, pp. 482-496. Elsevier. DOI: https://doi.org/10.1016/j.rse.2018.07.011 ISSN 0034-4257

Full text not available from this repository.

Official URL: https://www.sciencedirect.com/science/article/abs/pii/S0034425718303389


Forthcoming spaceborne imaging spectrometers will provide novel opportunities for mapping urban composition globally. To move from case studies for single cities towards comparative and more operational analyses, generalized models that may be transferred throughout space are desired. In this study, we investigated how single regression models can be spatially generalized for vegetation-impervious-soil (VIS) mapping across multiple cities. The combination of support vector regression (SVR) with synthetically mixed training data generated from spectral libraries was used for fraction mapping. We developed three local models based on separate spectral libraries from Berlin (Germany), Brussels (Belgium), and Santa Barbara (U.S.), and a generalized model based on a combined multi-site spectral library. To examine the performance and transferability of the generalized model compared to local models, we first applied all model variants to simulated Environmental Mapping and Analysis Program (EnMAP) data from the three cities that were represented in the models, i.e., known sites. Next, we transferred the models to two unknown sites not represented in the models, San Francisco Bay Area (U.S.) and Munich (Germany). In the first mapping constellation, results demonstrated that the generalized model was capable of accurately mapping VIS fractions across all three known sites. Average mean absolute errors (AV-MAEs) were 8.5, 12.2, and 11.0% for Berlin, Brussels, and Santa Barbara. The performance of the generalized model was very similar to the local models, with ∆AV-MAEs falling within a range of ±0.7%. A detailed assessment of fraction maps and class-wise accuracies confirmed that modeling errors related to remaining limitations of urban mapping based on optical remote sensing data rather than to the choice between a local or generalized model. For the second mapping constellation, the generalized model proved to be useful for mapping vegetation and impervious fractions in the unknown sites. MAEs for both cover types were 5.4 and 10.9% for the San Francisco Bay Area, and 6.3 and 15.4% for Munich. In contrast, the three local models were only found to have similar accuracies as the generalized model for one of the two sites or for individual VIS categories. Despite the enhanced transferability of the generalized model to the unknown sites, deficiencies remained for accurate soil mapping. MAEs were 22.4 and 12.3%, and high over - and underestimations were observed at the low and high end of the fraction range. These shortcomings indicated possible limitations of the spectral libraries to account for the spectral characteristics of soils in the unknown sites. Overall, we conclude that the combination of SVR and synthetically mixed training data generated from multi-site libraries constitutes a flexible modeling approach for generalized urban mapping across multiple cities.

Item URL in elib:https://elib.dlr.de/124347/
Document Type:Article
Title:Generalizing machine learning regression models using multi-site spectral libraries for mapping vegetation-impervious-soil fractions across multiple cities
AuthorsInstitution or Email of AuthorsAuthors ORCID iD
Okujeni, AkponaHumboldt-Universität zu BerlinUNSPECIFIED
Canters, FrankVrije Universiteit BrusselUNSPECIFIED
Cooper, Sam D.Humboldt-Universität zu BerlinUNSPECIFIED
Degerickx, JeroenKU LeuvenUNSPECIFIED
Heiden, Utauta.heiden (at) dlr.deUNSPECIFIED
Hostert, PatrickHumboldt Universität zu BerlinUNSPECIFIED
Priem, FrederikVrije Universiteit BrusselUNSPECIFIED
Roberts, DarUniversity of California, Santa BarbaraUNSPECIFIED
van der Linden, SebastianHumboldt Universität zu BerlinUNSPECIFIED
Journal or Publication Title:Remote Sensing of Environment
Refereed publication:Yes
Open Access:No
Gold Open Access:No
In ISI Web of Science:Yes
DOI :https://doi.org/10.1016/j.rse.2018.07.011
Page Range:pp. 482-496
Keywords:Urban remote sensing; Imaging spectrometry; EnMAP; Support vector regression; Land cover fraction mapping; Generalization
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Earth Observation
DLR - Research area:Raumfahrt
DLR - Program:R EO - Erdbeobachtung
DLR - Research theme (Project):R - Remote sensing and geoscience
Location: Oberpfaffenhofen
Institutes and Institutions:German Remote Sensing Data Center > Land Surface Dynamics
Deposited By: Heiden, Dr.rer.nat. Uta
Deposited On:06 Dec 2018 14:00
Last Modified:06 Dec 2018 14:00

Repository Staff Only: item control page

Help & Contact
electronic library is running on EPrints 3.3.12
Copyright © 2008-2017 German Aerospace Center (DLR). All rights reserved.