Using Landsat and nighttime lights for supervised pixel-based image classification of urban land cover
This project aims to improve approaches to chart urban extent by integrating night light data with Landsat 30m resolution satellite images
Abstract
This project aims to improve current approaches to chart urban extent across the globe by integrating night light (NTL) data with Landsat 30m resolution satellite images. By applying state-of-the-art machine-learning techniques, its goal is to produce a comprehensive global mapping of urbanization in close to real time. These maps will be made available to the public through Google Earth Engine and updated annually. This project promises immense potential implication for policy-makers in developing countries. For example, accurate high-resolution maps of urban areas would help to create additional evidence on positive productivity spillovers from the arrival of new manufacturing facilities in developing regions, where the evidence of the spillover effects is scant, despite the active use of place-based industrial policies in these countries.
Citation
Ran Goldblatt, Michelle F. Stuhlmacher, Beth Tellman, Nicholas Clinton, Gordon Hanson, Matei Georgescu, Chuyuan Wang, Fidel Serrano-Candela, Amit K. Khandelwal, Wan-Hwa Cheng, Robert C. Balling, (2018) Using Landsat and nighttime lights for supervised pixel-based image classification of urban land cover. Remote Sensing of Environment, Volume 205, 2018, Pages 253-275, https://doi.org/10.1016/j.rse.2017.11.026.