## Satellite Data for Nowcasting: Estimating Cambodia’s GDP in Real Time Using Satellite Data in a Machine Learning Framework

_Selected Issues Papers, January 8, 2026_

## Source details

**Canonical URL:** [Satellite Data for Nowcasting: Estimating Cambodia’s GDP in Real Time Using Satellite Data in a Machine Learning Framework](https://www.imf.org/en/publications/selected-issues-papers/issues/2026/01/08/satellite-data-for-nowcasting-estimating-cambodias-gdp-in-real-time-using-satellite-data-573043)

## Other formats

- [Markdown version](/en/publications/selected-issues-papers/issues/2026/01/08/satellite-data-for-nowcasting-estimating-cambodias-gdp-in-real-time-using-satellite-data-573043/index.md)
- [Structured JSON version](/en/publications/selected-issues-papers/issues/2026/01/08/satellite-data-for-nowcasting-estimating-cambodias-gdp-in-real-time-using-satellite-data-573043/index.json)
- [Bundle manifest](/en/publications/selected-issues-papers/issues/2026/01/08/satellite-data-for-nowcasting-estimating-cambodias-gdp-in-real-time-using-satellite-data-573043/bundle-manifest.json)

## Bibliographic details
- Authors: Iyke Maduako, Dharana Rijal, Alberto Sanchez Rodelgo
- Published: January 8, 2026
- Series: Selected Issues Papers
- DOI: https://doi.org/10.5089/9798229035323.018

---

### Core findings
- Combining satellite-derived indicators (e.g., nighttime lights, NO₂ emissions, vegetation indices) with traditional high-frequency indicators in a machine learning framework significantly improves the accuracy of GDP nowcasts.
- Satellite data enables closer examination of subnational patterns, providing granular, near-real-time insights into economic activity.
- Non-traditional data sources can complement conventional methods and strengthen macroeconomic surveillance in data-scarce environments.

### Methodology and tools
- Use of satellite-derived indicators: nighttime lights, NO₂ emissions, vegetation indices.
- Integration with traditional high-frequency indicators.
- Application of machine learning methods (keywords include: random forest, machine learning, nowcast, nowcasting).

### Policy implications and recommendations
- Non-traditional, high-frequency satellite data should be considered to supplement official statistics where capacity limitations exist in the production and timely release of key indicators.
- Incorporating satellite data into nowcasting frameworks can improve the evidence base for data-driven policy decisions and macroeconomic surveillance.
- Subnational analysis enabled by satellite indicators can inform more granular policy targeting.

### Subject areas and keywords
- Subjects: Agricultural sector, Economic forecasting, Economic sectors, Health.
- Keywords: Agricultural sector, big data, Global, IMF country, IMF staff, issues paper, machine learning, non-traditional data, nowcast, nowcasting, policy decision, random forest, satellite, satellite data.

---

## Content in this bundle

- **Sipea2026001**
  - [Sipea2026001 (Markdown version)](/-/media/files/publications/selected-issues-papers/2026/english/sipea2026001.pdf.md){rel="alternate" type="text/markdown"}
  - [Sipea2026001 (PDF)](/-/media/files/publications/selected-issues-papers/2026/english/sipea2026001.pdf){rel="external" type="application/pdf"}

---

_Source: https://www.imf.org/en/publications/selected-issues-papers/issues/2026/01/08/satellite-data-for-nowcasting-estimating-cambodias-gdp-in-real-time-using-satellite-data-573043_