Search Records

OneSoil employs a proprietary machine learning (ML) model based on state-of-the-art instance segmentation to detect field boundaries. Utilizing raw Sentinel-2 data aggregated according to local vegetation season maps and an additional upscaling module to enhance boundary accuracy, we ensure...

Datasets of daily snow water equivalent (SWE) over the Northern Hemisphere (excluding Greenland) were constructed using a multi-dataset approach for the time period 1981-2020. The data are on a regular 0.5-degree grid, with a threshold maximum of 2000mm. The general methodology for the creation...

This dataset comprises a map of inland water bodies in Canada and neighboring regions, as described by Ghayourmanesh et al. (2024). The data are mapped using the Lambert Conformal Conic (LCC) geographic projection with a spatial resolution of 250 meters. The LCC projection is frequently used as a...

In 2009 the Earth Observation Team of the Science and Technology Branch (STB) at Agriculture and Agri-Food Canada (AAFC) began the process of generating annual crop inventory digital maps using satellite imagery. Focusing on the Prairie Provinces, a Decision Tree (DT) based methodology was...

Knowledge of the location of Earth’s surface water in time and space is critical to inform policy decisions on environment, wildlife, and human security. Dynamic surface water maps generally represent water occurrence, also referred to as inundation frequency, depicting the percentage of valid...

These products are derived from RGB (red/green/blue) images, a satellite processing technique that uses a combination of satellite sensor bands (also called channels) and applies a red/green/blue (RGB) filter to each of them. The result is a false-color image, i.e. an image that does not...

These products are derived from RGB (red/green/blue) images, a satellite processing technique that uses a combination of satellite sensor bands (also called channels) and applies a red/green/blue (RGB) filter to each of them. The result is a false-color image, i.e. an image that does not...

From the point of view of ecological integrity and the responsibility of the park to protect and maintain a biotic community naturally associated with the ecoregion, we are primarily interested in the extent of two land cover classes, the old-growth forest, which should not decrease in the park,...

The Hudson Bay Lowlands (HBL) is the wettest ecozone in Canada with 80% of its area covered by wetlands. It forms the third largest wetland in the world and is composed almost entirely of permafrost and non-frozen subarctic peatlands that store more carbon in the first 2 m of soil than the total...

Radar coverage is provided to dynamically display the zones covered by the radars every 6 minutes, and to provide information on the availability (or not) of the contributing radars as well as on the areas of overlap.