Earth observation guideApplications

Financial services

Satellites give investors, lenders and analysts an independent view of economic activity and of the assets behind a loan or a claim, often sooner than official figures.

The basics

Official statistics on a country's economy arrive months late and are sometimes unreliable. A satellite does not wait for a report. It sees how brightly a region is lit at night, how full a port is, whether a new factory is being built and whether a farm that borrowed money is actually planted. Banks use these views to check what they are lending against, investors to judge a company's claims, and food and timber buyers to prove that what they sell did not come from freshly cleared forest.

Why it matters

Decisions about lending and investing are only as good as the information behind them. Satellite data offer a view that is independent of the company or country being assessed, consistent across the world and updated often.

A large river port seen from above. A wide river crosses the image and splits into dark harbour basins between long quays, some lined with coloured containers, with clusters of round white storage tanks, ships moored alongside, farmland to the south and west and dense city streets to the north-east.
The port of Hamburg, Germany, on 12 June 2025, in natural colour from Sentinel-2. The Elbe crosses the image and splits into harbour basins. Container terminals show as long quays covered in coloured stacks, tank farms as clusters of round white tanks, and moored ships as small shapes along the quays. Counting individual containers or cars needs much finer imagery. The image is about 18 km across.

In depth

Economists have taken up satellite data quickly. A review for economists describes how petabytes of imagery have become publicly accessible at increasing resolution, how algorithms for extracting social and economic information from it have become routine, and how cloud computing lets them run at global scale [1]. Financial firms use the same data for four broad purposes, below. Related uses are covered on the insurance, agriculture and mining and commodities pages.

Measuring economic activity

Light at night tracks economic activity. A statistical framework that uses growth in lights to improve measured income growth found that, for countries with good national accounts, lights add little, but for countries with the worst accounts the best estimate gives lights and official data roughly equal weight, and differs from official growth figures by as much as 3 percentage points a year. Lights also measure growth in regions and cities that official accounts do not cover [2]. The night lights page explains the measurement.

What is measured
Radiance of artificial light at night, summed over a country, region or city and followed over time.
Data
Night lights at around 500 m to 1 km for regions, and finer optical imagery for individual sites such as ports, car parks and factories.
How often
Monthly or annual composites for lights; site imagery as often as it is ordered.
Limits
Lights measure lighting, not output, so the link to income varies between places and over time, and agriculture and services may emit little light.
Who uses it
Macroeconomic analysts, sovereign debt investors and development banks.

Poverty and development

Where household surveys are rare, daytime imagery fills gaps. A convolutional neural network trained on survey and satellite data from Nigeria, Tanzania, Uganda, Malawi and Rwanda identified image features that explain up to 75 per cent of the variation in local consumption and asset wealth, using only publicly available data [3].

What is measured
Features in imagery, such as roofs, roads and farmland, that correlate with household wealth.
Data
High resolution optical imagery, often with night lights as an extra signal.
How often
Every year or few years, as new imagery and surveys arrive.
Limits
Models trained on one set of countries may not transfer to others, and they predict averages for villages or districts, not individual households.
Who uses it
Development finance institutions, impact investors and governments targeting aid.

Supply chains and deforestation rules

The European Union's deforestation regulation covers cattle, cocoa, coffee, oil palm, rubber, soya and wood, and products made from them. Operators must give the geolocation of the plots of land where the commodities were produced, as polygons for plots of more than four hectares, and the regulation names Earth observation data, such as those of the Copernicus programme, among the means of checking that products are deforestation-free [4]. Satellite forest maps and alerts, described on the forestry page, are the evidence behind such checks [5, 6].

What is measured
Whether forest cover inside each declared plot has changed since the regulation's cut-off date.
Data
Multispectral and radar time series at 10 to 30 m, and very high resolution optical images to resolve doubtful cases.
How often
Once for each shipment's plots, and continuously for the farms and forests a buyer sources from.
Limits
Only as good as the declared plot boundaries. Forest definitions, degradation and small plots are hard cases.
Who uses it
Importers and traders, banks financing commodity trade, and auditors.

Asset inventories and monitoring

Imagery can count assets that no register lists. Machine learning on a long series of remote sensing images located and verified 68,661 commercial, industrial and utility-scale solar installations worldwide, 432 per cent more facilities than previously available asset-level data held, with an estimated capacity of 423 gigawatts at the end of 2018 [7]. The same approach lets a lender watch the progress of a building site, a mine or a plantation it has financed, using the change detection methods described on the defence and security page.

What is measured
The presence, size and state of physical assets, and how they change.
Data
Multispectral images at 10 m for large assets, very high resolution optical imagery for small ones, and radar where cloud persists.
How often
Monthly or quarterly for project monitoring, and once for an inventory.
Limits
An image shows what is built, not who owns it or whether it is running at full capacity.
Who uses it
Lenders, project finance teams, equity analysts and investors assessing environmental, social and governance claims.

References

  1. Donaldson, D. and Storeygard, A. (2016) The View from Above: Applications of Satellite Data in Economics. Journal of Economic Perspectives, 30(4), 171-198. https://doi.org/10.1257/jep.30.4.171
  2. Henderson, J. V., Storeygard, A. and Weil, D. N. (2012) Measuring Economic Growth from Outer Space. American Economic Review, 102(2), 994-1028. https://doi.org/10.1257/aer.102.2.994
  3. Jean, N., Burke, M., Xie, M. et al. (2016) Combining satellite imagery and machine learning to predict poverty. Science, 353(6301), 790-794. https://doi.org/10.1126/science.aaf7894
  4. European Parliament and Council of the European Union (2023) Regulation (EU) 2023/1115 of 31 May 2023 on the making available on the Union market and the export from the Union of certain commodities and products associated with deforestation and forest degradation. Official Journal of the European Union, L 150, 206-247. https://eur-lex.europa.eu/eli/reg/2023/1115/oj
  5. Hansen, M. C., Potapov, P. V., Moore, R. et al. (2013) High-Resolution Global Maps of 21st-Century Forest Cover Change. Science, 342(6160), 850-853. https://doi.org/10.1126/science.1244693
  6. Reiche, J., Mullissa, A., Slagter, B. et al. (2021) Forest disturbance alerts for the Congo Basin using Sentinel-1. Environmental Research Letters, 16(2), 024005. https://doi.org/10.1088/1748-9326/abd0a8
  7. Kruitwagen, L., Story, K. T., Friedrich, J. et al. (2021) A global inventory of photovoltaic solar energy generating units. Nature, 598(7882), 604-610. https://doi.org/10.1038/s41586-021-03957-7

Data Sphere for lenders and asset managers