Estimating change in the spatial economy of the city of Johannesburg using nighttime lights imagery and population data in a Random Forest modelling environment

Yashena Naidoo; Gillian Maree; Laven Naidoo

doi:10.1117/12.2684320

19 October 2023 Estimating change in the spatial economy of the city of Johannesburg using nighttime lights imagery and population data in a Random Forest modelling environment

Yashena Naidoo, Gillian Maree, Laven Naidoo

Author Affiliations +

Proceedings Volume 12735, Remote Sensing Technologies and Applications in Urban Environments VIII; 1273504 (2023) https://doi.org/10.1117/12.2684320
Event: SPIE Remote Sensing, 2023, Amsterdam, Netherlands

Abstract

Nighttime lights imagery is obtained using a low-light sensor on a satellite that captures quantitative measurements of light emissions at night. The value of this data is that artificial light emissions highlight human activity. It provides a unique perspective on the spread of our activities across the world. It has been used to estimate economic activity, as an alternative to traditional economic metrics such as Gross Domestic Product (GDP). Previous studies using nighttime lights data focused on the relationship between light intensity and GDP to determine if light intensity correlated strongly with GDP at national and subnational levels. In this study, annual composites of nighttime lights (for 2011, 2016, 2019 and 2021) and Landscan population estimates were used to create a model, using the Random Forest algorithm, that predicted Gross Value Added (GVA) at a one-kilometre spatial resolution for the City of Johannesburg – a metropolitan municipality located in Gauteng, South Africa that is the largest contributor to the country’s economy. The predicted model had a Spearman’s coefficient of 0.88 and an RMSD of 2468.54 Rands Million. The results in the predicted GVA showed a trend of increasing GVA from the period between 2011 and 2019, however, there was a noticeable decline in GVA and a contraction of the spatial spread of economic activity between 2019 and 2021. This coincides with the impact of Covid-19 and resulting lockdown measures, as well as the ongoing electricity interruptions, on the economy.

Conference Presentation

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Yashena Naidoo, Gillian Maree, and Laven Naidoo "Estimating change in the spatial economy of the city of Johannesburg using nighttime lights imagery and population data in a Random Forest modelling environment", Proc. SPIE 12735, Remote Sensing Technologies and Applications in Urban Environments VIII, 1273504 (19 October 2023); https://doi.org/10.1117/12.2684320

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available