Using Landsat and nighttime lights for supervised pixel-based image classification of urban land cover

Reliable representations of global urban extent remain limited, hindering scientific progress across a range of disciplines that study functionality of sustainable cities. We present an efficient and low-cost machine-learning approach for pixel-based image classification of built-up areas at a large...

Full description

Saved in:
Bibliographic Details
Published in:Remote sensing of environment 2018-02, Vol.205, p.253-275
Main Authors: Goldblatt, Ran, Stuhlmacher, Michelle F., Tellman, Beth, Clinton, Nicholas, Hanson, Gordon, Georgescu, Matei, Wang, Chuyuan, Serrano-Candela, Fidel, Khandelwal, Amit K., Cheng, Wan-Hwa, Balling, Robert C.
Format: Article
Language:English
Subjects:
Built-up land cover
Cities
Classification
Data integration
Fusion
Google Earth Engine
Image classification
Land
Land cover
Land use
Landsat
Landsat satellites
Learning algorithms
Multisensor fusion
Night
Nighttime
Nighttime light
Pixels
Remote sensing
Studies
Urban areas
Urban environments
Urbanization
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Reliable representations of global urban extent remain limited, hindering scientific progress across a range of disciplines that study functionality of sustainable cities. We present an efficient and low-cost machine-learning approach for pixel-based image classification of built-up areas at a large geographic scale using Landsat data. Our methodology combines nighttime-lights data and Landsat 8 and overcomes the lack of extensive ground-reference data. We demonstrate the effectiveness of our methodology, which is implemented in Google Earth Engine, through the development of accurate 30m resolution maps that characterize built-up land cover in three geographically diverse countries: India, Mexico, and the US. Our approach highlights the usefulness of data fusion techniques for studying the built environment and is a first step towards the creation of an accurate global-scale map of urban land cover over time. •An approach is proposed to map built-up land cover at a large geographical scale.•Our data fusion approach utilizes nighttime-lights data and Landsat imagery.•The approach overcomes the lack of extensive ground-reference data for urban research.•Hexagonal tessellation partition improves classification of heterogeneous land cover.•High quality maps of built-up LC are produced for 3 geographically diverse countries.
ISSN:0034-4257
1879-0704
DOI:10.1016/j.rse.2017.11.026