Kuva Space takes on illicit crop monitoring with hyperspectral satellites and AI

Kuva Space, a Finnish space-technology firm, has successfully piloted a system using hyperspectral satellites and AI to monitor illicit crop production, specifically opium poppy cultivation in Afghanistan. The project, which combined Kuva Space's Hyperfield imagery with Sentinel-2 data and AI-based classification, demonstrated the potential to accurately identify and map illicit crop fields across large regions, even where physical access is limited.

The system reduced false positives compared to Sentinel-2 alone, achieving 75% accuracy in identifying likely poppy fields in Helmand Province, Afghanistan. This approach can help authorities prioritize resources for investigation, as even small improvements in accuracy can result in significant cost savings and efficiency gains.

The company plans to improve accuracy through more ground-truth data, higher-quality hyperspectral data, and integration of other data sources, such as SAR, weather, and DEM data.