FLAIR-HUB: Large-scale Multimodal Land Cover and Crop Map of France

Over 2,500 km² of diverse French ecoclimates and landscapes are covered by this large-scale, multi-sensor land-cover resource. It features 63 billion hand-annotated pixels across 19 land-cover and 23 crop type classes, building upon the FLAIR#1 and FLAIR#2 datasets. The dataset was created by IGNF and was last updated on the platform in April 2026.

Use Cases

• Train land cover classification models based on very-high-resolution annotations.
• Develop crop type identification algorithms based on the 23 distinct crop classes.
• Conduct multi-sensor data fusion research based on the integration of complementary satellite data sources.
• Study agricultural patterns and landscape diversity across French ecoclimates.

Strengths

• Contains 63 billion hand-annotated pixels, providing a substantial volume of labeled data.
• Covers over 2,500 km² of diverse French landscapes, offering geographic breadth.
• Includes annotations for 19 land-cover and 23 crop type classes, enabling detailed classification tasks.
• Unifies multiple prior datasets (FLAIR#1 and FLAIR#2) into a single resource.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count and file size are unknown, which may limit suitability assessment.
• The dataset's geographic scope is limited to France, which may not be globally representative.

Provenance

Source

IGNF

Collection Method

Integrates and expands the FLAIR#1 and FLAIR#2 datasets with hand-annotated pixels from multi-sensor sources.

Freshness

Last updated 2026-04-28 06:52:12; freshness should be verified.

Geography

France