The World Bank: developing a more accurate method of measuring nightlights

Previously, the World Bank had used off-the-shelf luminosity data night time satellite imagery. However, this data could often be ‘noisy’ due to contaminated satellite images (as a result of cloud cover, reflections of light on water, etc.).

Nighttime satellite imagery is a useful proxy for economic activity in the absence of official statistics. Luminosity is particularly useful as it is frequent (it is available monthly), timely (it is made available within a few weeks following the end of the month), and is granular (it can be used to measure economic activity in small regions).

In order to address these sources of noise, we conducted pixel-level processing of satellite imagery to address cloud cover, pixels falling on water bodies, and ephemeral light (e.g. lightning). This was done using a high performance computing environment.

We found that our cleaned luminosity estimates were significantly less noisy and volatile than unprocessed/off-the-shelf satellite imagery:

We subsequently examined the relationship between luminosity from (i) our processed data, (ii) the off-the-shelf luminosity data, and (iii) official provincial GDP for 2018 from the Vietnamese government (the only year currently available).

The below figure maps annualised provincial luminosity and GDP for 2018. We can see correlations between provinces such as Hanoi, Ho Chi Minh City, as well as Thanh Hoa – which experience high levels of luminosity as well as high levels of GDP.

When we conduct a regression analysis between each source of luminosity and log GDP, we find that our processed data has a higher level of statistical significance and a higher R² than the off the shelf log luminosity data. This indicates that the pre-processed BM data is a stronger indicator of economic activity than the CSM data.