Please use this identifier to cite or link to this item: https://hdl.handle.net/10419/187800 
Year of Publication: 
2018
Citation: 
[Journal:] Development Engineering [ISSN:] 2352-7285 [Volume:] 3 [Publisher:] Elsevier [Place:] Amsterdam [Year:] 2018 [Pages:] 83-99
Publisher: 
Elsevier, Amsterdam
Abstract: 
Urbanization is a fundamental trend of the past two centuries, shaping many dimensions of the modern world. To guide this phenomenon and support growth of cities that are competitive and sustainably provide needed services, there is a need for information on the extent and nature of urban land cover. However, measuring urbanization is challenging, especially in developing countries, which often lack the resources and infrastructure needed to produce reliable data. With the increased availability of remotely sensed data, new methods are available to map urban land. Yet, existing classification products vary in their definition of 'urban' and typically characterize urbanization in a specific point (or points) in time. Emerging cloud based computational platforms now allow one to map land cover and land use (LC/LU) across space and time without being constrained to specific classification products. Here, we highlight the potential use of publicly available remotely sensed data for mapping changes in the built-up LC/LU in Ho Chi Minh City, Vietnam, in the period between 2000 and 2015. We perform a pixel-based supervised image classification procedure in Google Earth Engine (GEE), using two sources of reference data (administrative data and hand-labeled examples). By fusing publicly available optical and radar data as input to the classifier, we achieve accurate maps of built-up LC/LU in the province. In today's era of big data, an easily deployable method for accurate classification of built-up LC/LU has extensive applications across a wide range of disciplines and is essential for building the foundation for a sustainable human society.
Subjects: 
Built-up land cover
Google Earth Engine
Landsat
Sentinel
Urbanization
Persistent Identifier of the first edition: 
Creative Commons License: 
cc-by-nc-nd Logo
Document Type: 
Article

Files in This Item:
File
Size





Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.