Chapter 09 · Sustainability & AISustainability & AI
AI-enabled Earth observation
Definition
The application of machine learning to satellite and aerial data to track land use, oceans, ice, crops and environmental change at scale.
References
This source provides part of the technical or institutional basis for the definition.
This source supports the explanation of how the term is applied, measured or governed in practice.
This source supports the wider sustainability significance and context described in the entry.
Overview
What it means
Earth-observation archives — notably the EU's Copernicus programme — are far too large for manual analysis. Machine learning classifies land cover, detects change, estimates biomass and tracks water bodies; ESA's Φ-lab works specifically at this AI–EO frontier, accelerating methods into operational services.
How it is used
Applications underpin carbon accounting for land use, deforestation and methane alerts, agricultural monitoring, disaster mapping and the measurement side of nature markets. Operational agencies increasingly blend AI products with conventional remote sensing.
Why it matters
Earth observation supplies the evidence layer for much of environmental policy. AI is what makes that evidence continuous, global and timely — with the caveat that classified products are model outputs, carrying uncertainty that downstream users must inherit honestly.