Back to data list

Data details

UID 943
Name CoSIA
Description The CoSIA dataset (Land Cover by Artificial Intelligence) was produced and used within the framework of the French large-scale reference land cover and land use mapping product (OCS GE). This database predicts land cover (that is, the nature of the soil) according to 15 classes: · Building · Impermeable area, Permeable area · Swimming pool, Water surface, Snow · Greenhouse, Bare soil · Coniferous, Deciduous, Shrubland, Lawn, Crop, Plowed land, Vineyard Main characteristics: These data are raw and obtained through artificial intelligence (AI) processes, notably deep learning methods. They represent so-called "prediction" information. They are obtained from a digital AI model that statistically estimates for each pixel its membership to a class. These data therefore do not comprehensively reflect the reality on the ground: There are margins of error that are documented for each object class in the links provided below.
Update Frequency Periodic Update
Area National
Temporal 01 Jan. 2017 - 01 Jan. 2025
Timeliness Latest version available
Data Policy Freely accessible
Data type Geospatial data
Copernicus service product
Data format Raster dataset
Quality Control Procedure TBD
Dissemination View and Download Service
Inspire themes

Annex II: Land cover

Geographical Coverage

France

Status Operational
State Valid
Created on May 4, 2026, 2:49 p.m.
Last modified on May 12, 2026, 9:09 a.m.

Data Providers

Data provider UID Data provider Role Is network Created on Last modified on
130 National Institute of Geographic and Forest Information Originator May 4, 2026, 2:54 p.m. May 4, 2026, 2:54 p.m.

Requirements

Requirement UID Requirement Level of compliace Note Information costs Handling costs Created on Last modified on
436 Land Cover Fully The CoSIA dataset (Land Cover by Artificial Intelligence) of two referenced years was used for a semi-automated change detection method for the CORINE land cover 2024 and CORINE land cover change (2018-2024) products in France. May 4, 2026, 9:36 p.m. May 4, 2026, 9:36 p.m.