This internet browser is outdated and does not support all features of this site. Please switch or upgrade to a different browser to display this site properly.

Artificial night-time light data extraction

If artificial night-time lights (ANTL) are considered means for safety and security, then what is the optimum level of brightness to ensure safety and security without compromising the environment?

About the training

Artificial Night-time Lights (ANTL) have been widely used in social science research as a robust proxy for economic development, the quantification of disaster impacts, electricity consumption, and various other applications. However, employing ANTL in social science research requires a comprehensive understanding of confounding factors, necessitating their individual consideration based on the specific needs of the application. This training aims to provide hands-on experience in both the theory and application of ANTL.

Program objectives

This program will achieve the following outcomes:

  • Raise awareness among emerging global leaders about ANTL.
  • Share knowledge on ANTL theory, practice, and measurement techniques.
  • Train students from the global south to extract, analyse, and visualise ANTL.
  • Understand the limitations of satellite imagery in capturing artificial night-time lights. 

Use the tabs below to find the information required to participate in this course.

The program will run for three weeks with two two-hour sessions per week.

The first week will be a single two-hour general session with a keynote talk from an expert to provide the context and importance of ANTL. The following two weeks will have technical sessions. In the final session, participants will present their map and briefly discuss their interpretations of it.

Dates

Pre-training session: 11 June 2024

Week 1: 25-26 June 2024 (Introductory keynote and module 1)

Week 2: 2-3 July 2024 (Module 2)

Week 3: 9-10 July 2024 (Modules 3 and 4)

Times

22:30 NZDT (New Zealand), 15:15 NPT (Nepal), 10:30 WAT (Nigeria)

The training program will encompass core concepts related to ANTL data and get skills in extracting the images tailored to relevant research context.

It is designed to equip participants with fundamental skills for accessing a range of ANTL data repositories, utilising advanced software (where possible open source) to map, understand the quality of data, pre-process data, calculate zonal statistics, and analyse the spatial distribution.

The training has 4 major modules, allowing participants to select the modules that align with their preferences. However, we recommend attending all the modules for better understanding.

Recognising that everyone progresses at their own pace, we have established separate breakout rooms to provide additional support from the technical support team.  

Pre-training session

This session will make sure all participants start the course with the same level of data knowledge.

Module one

Module 1.1: Introductions and Theory of ANTL
• Understanding ANTL data
• Discuss the sources and confounding factors of ANTL (Spatial, data constraints, satellite sensors)

Module 1.2: Introduce the scope and limits of ANTL dataset
• Temporal resolutions
• Spatial resolutions

Module two

Introduction to Google Earth Engine
• Upload files from computer and catalogue
• Basic commands
• Display data

Part 4: Experiment with maps
Identify hotspots and potential sources emitting ANTL.

Module three

Module 3.1: Using annual data – plotting the ANTL dataset
• Review the projection methodology concept
• Calculate the zonal statistics
• Export data to tabular data

Module 3.2: Using World Bank GDPdata
• Understanding the annual GDP data
• Download and check the dataset
• Export data

Module 3.3: Using ANTL and GDP data
• Merge two datasets
• Plot the scatter plot and conduct a correlation analysis

Module four

Presentations and communication
Students will present their report and discuss their learning. There will also be a Q & A.

Detailed information about each session is included below.

DateModuleSessionActivitiesFacilitatorObjective
Week 125 June 2024Introduction and keynotePart 1: Why and how of the training and session5 slides about the objective team, process and expectation (10 minutes)Sobia RoseLearn course, process and expectation
Part 2: Keynote and Q & AKeynote: Using Night Light data for socio-economic research (1.15 hour)Professor John Gibson Department of Economics University of WaikatoKeynote
Q&A with expert (25 min)Chizoba Obianuju Oranu, University Of Nigeria NsukkaQ & A
Summary and Thank you (10 minute)Professor Margaret Chitiga-Mabugu University of PretoriaThank you note.
26 June 2024Module 1Part 1: Understand the ANTL  Presentation on what is ANTL, how it is captured, and why it is useful in social, economic and environmental terms.Dipendra Bhattarai                    Observe the data and guess the possible sources of nighttime lights.  
Practical: From the reading materials find out and list the possible sources of nighttime lights.
Part 2: Data sourcesPotential data sources and confounding factors of ANTL.   Know open access data source and find the data that is useful for your study.
Week 22 July 2024Module 2Upload data and understandExtract data and understand the format.Dipendra Bhattarai, Darcy, Bishal, and WiZelleLearn mapping
Identify key issues and resolveIdentify key problem or issues in uploading data and resolve it. 
Map your chosen dataUse open-source ANTL data and map it.
Play with the maps Identify the hotspots and potential sources emitting ANTL.
 Week 33 July 2024Module 3Part 1: Extract the annual ANTL dataCalculate the zonal statistics and export the data to tabular format.Learn about application

These reading materials are useful resources to build your knowledge of the content that will be covered during the course.

Journal articles

Bhattarai, D., Lucieer, A., Lovell, H. and Aryal, J. 2023. Remote sensing of night‐time lights and electricity consumption: A systematic literature review and meta‐analysis. Geography Compass. https://doi.org/.10.1111/gec3.12684 

Bhattarai, D. and Lucieer, A. 2024. Random forest regression exploring contributing factors to artificial night-time lights observed in VIIRS satellite imagery. International Journal of Digital Earth, 17. https://doi.org/.10.1080/17538947.2024.2324941  

Dingel, J. I., Miscio, A. and Davis, D. R. 2021. Cities, lights, and skills in developing economies. Journal of Urban Economics, 125. https://doi.org/.10.1016/j.jue.2019.05.005

Baragwanath, K., Goldblatt, R., Hanson, G. and Khandelwal, A. K. 2021. Detecting urban markets with satellite imagery: An application to India. Journal of Urban Economics, 125. https://doi.org/.10.1016/j.jue.2019.05.004

Monroe, T. Big Data and Thriving Cities. https://elibrary.worldbank.org/doi/abs/10.1596/26299  

Blog

Min, B., Baugh, K., Monroe, T., Goldblatt, R., Stewart, B., Kosmidou-Bradley, W. & Crull, C. (2021). Light every night: New night-time light data set and tools for development. World Bank Blogs.

Useable dataset and tutorial for further information

World Bank. (n.d.). Light every night: Registry of open data on AWST

Training resources are available on the CIET GitHub.