This data product is currently under evaluation and review. It may contain inaccuracies or be subject to change. Users should exercise caution and discretion when interpreting or relying on this information. The government assumes no liability for any errors or decisions based on this preliminary data. For more details, please see the Government of Canada's Open Commons license (https://open.canada.ca/en/open-government-licence-canada). The Canadian Soil Information Service has developed a detailed dataset of Canada's soils and associated properties using advanced machine learning techniques. The Soil Landscape Grids of Canada is produced using a combination of historical and current data from both soil sampling and remote sensing. The machine learning model is trained using over 10,000 pedon locations from across Canada as well as 70 covariate datasets. This new dataset is pivotal in addressing the gaps left by legacy soil surveys and facilitates more comprehensive assessments nationwide. As new data becomes available and machine learning techniques advance, this information can be updated much faster than with traditional soil surveying methods.

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 precise results. OneSoil’s data preprocessing involves the utilization of their cloud detector module and local season mapping.

This national map of flood susceptibility or flood prone areas is based on patterns of historic flood events as predicted by an ensemble machine learning model.The recommended use is national, provincial or regional scale and can be used as a guide for identifying areas for further investigation. The Flood Susceptibility Index (FSI) Dataset, while processed and available at 30m cell size, is not recommended for use at the pixel or street level, given the uncertainty in the modelling process and the variability of results as discussed in https://www.mdpi.com/2673-4931/25/1/18 .For additional details on the methods, tests, models and datasets used to generate this data layer, please see https://geoscan.nrcan.gc.ca/starweb/geoscan/servlet.starweb?path=geoscan/fulle.web&search1=R=329493

A national map of flood susceptibility or flood prone areas based on patterns of historic flood events as predicted by an ensemble machine learning model. The recommended use is national, provincial or regional scale and can be used as a guide for identifying areas for further investigation. This dataset, while processed and available at 30m cell size, is not recommended for use at the pixel or street level, given the uncertainty in the modelling process and the variability of results as discussed in https: **This third party metadata element follows the Spatio Temporal Asset Catalog (STAC) specification.**

This model is derived from geological and geophysical data, which is processed using deep learning and natural language processing techniques. Displayed is a Pan-Canadian probability map indicating the likelihood of discovering next-generation lithium-cesium-tantalum (LCT) pegmatites. This map was generated using known Canadian LCT pegmatites and their associated geospatial features, incorporating geological and geophysical data analyzed through deep learning and natural language processing techniques. Higher probability values highlight areas with an increased likelihood of hosting next-generation deposits, making this map a valuable tool for decision-making.

Building on the initial effort (“Database of Open Water Areas in River Ice for Provinces of Manitoba, Ontario, Quebec, and the Maritimes - Potential Locations For River Hydrokinetic Energy Extraction Identified Through Optical Satellite Imager”; weblink: https://search.open.canada.ca/openmap/d9823004-29aa-40e2-aa47-9c54cf88c309), a follow-up research project has led to the publication of this extensive analysis encompassing the entirety of Canada’s major freezing rivers. This work has applied advanced image processing and classification algorithms to the selected images, elevating the classification and analysis to a higher level of accuracy and providing a more comprehensive dataset for exploring river hydrokinetic energy prospects across the country.This dataset identifies open water areas within ice-covered major Canadian rivers, aiming to evaluate potential hydrokinetic resources. The data is derived from high-resolution optical satellite imagery obtained from Landsat and Sentinel satellites corresponding to National Research Council (NRC) 2014 flow data of river reaches with water depths of at least 10 meters and a flow velocity of a minimum of 0.5 meters per second. Using advanced image processing and machine learning algorithms, the dataset efficiently differentiates between ice-covered and open water regions, providing a reliable basis for assessing hydrokinetic energy potential in the identified areas.Disclaimer:This dataset is subject to the following limitations:• Landsat and Sentinel optical satellite images are high-resolution, but they may contain resolution errors, possible distortions, and inaccuracies in depicting on-ground conditions. • Despite advanced image processing and machine learning algorithms, errors or biases may exist. • The dataset's reliability is also influenced by the NRC flow data.Therefore, users should view this dataset as a preliminary assessment tool, not a definitive guide for decision-making or investment in hydrokinetic projects. It is strongly recommended to validate its accuracy and suitability for specific applications through additional research and studies. By accessing and using this dataset, users acknowledge and accept these disclaimers. The providers of this dataset explicitly absolve themselves of any responsibility or liability for any consequences arising from the use, reliance upon, or interpretation of this dataset. Users are advised that their use of the dataset is at their own risk, and they assume full responsibility for any actions or decisions made based on the information contained therein. This disclaimer is in accordance with applicable laws and regulations, and by accessing or utilizing the dataset, users agree to release the providers of this dataset from any legal claims, damages, or liabilities that may arise from such use.

This dataset presents the first comprehensive, high-resolution (10-meter) wetland inventory map covering the entire 32.2 million square kilometers of the Pan-Arctic region, of which 14 million square kilometers (43%) is terrestrial and 18.4 million square kilometers (57%) is marine. Generated through advanced Earth Observation and machine learning techniques, the map was produced using multi-year (2020–2022), multi-source satellite imagery—including Sentinel‑1, Sentinel‑2, and ALOS PALSAR‑2—as well as various environmental features such as elevation. Over 1,000 wetland polygons were analyzed using an object-based random forest classification workflow on the Google Earth Engine cloud platform, achieving an average overall classification accuracy of 89%.The mapping extent was defined according to the Arctic Council’s Conservation of Arctic Flora and Fauna (CAFF) boundary, resulting in the identification of 2,947,618 km² of wetlands, representing 20% of the land area within the Pan-Arctic region. This dataset establishes a consistent and authoritative baseline for pan-Arctic wetlands, leveraging the latest advances in Earth Observation, machine learning, and cloud computing. The Canadian Wetland Classification System was used and includes the major wetland classes: bog, fen, marsh, swamp, and water.The overall wetlands coverage by country within the CAFF boundary was: Canada (27%), United States of America (i.e., Alaska 39%), Finland (31%), Iceland (8%), Norway (17%), Sweden (26%), Kingdom of Denmark (i.e., Greenland 1%), and the Russian Federation (21%).​Development of this product was undertaken by Natural Resource Canada's Canada Centre for Mapping and Earth Observation and the Canadian Geospatial Data Infrastructure Division in collaboration with the Arctic Council’s CAFF biodiversity group, CAFF Wetland Experts Group, national organisations mandated to monitor wetlands, and Arctic National Mapping Agencies, and Canadian company C-CORE, integrating ground truth data collected from Alaska, Finland, Sweden, and the Kingdom of Denmark through partner agencies and digital image interpretation. More than 60,000 images (2020-2022), primarily covering summer periods, were processed to ensure robust results.This dataset provides essential baseline information for Earth Observation monitoring of climate change impacts and supports critical environmental surveillance for Arctic and remote northern communities.

A national map of flood susceptibility or flood prone areas based on patterns of historic flood events as predicted by an ensemble machine learning model. The recommended use is national, provincial or regional scale and can be used as a guide for identifying areas for further investigation. This dataset, while processed and available at 30m cell size, is not recommended for use at the pixel or street level, given the uncertainty in the modelling process and the variability of results as discussed in https: **This third party metadata element follows the Spatio Temporal Asset Catalog (STAC) specification.**

The Canada Geological Map Compilation (CGMC) is a database of previously published bedrock geological maps sourced from provincial, territorial, and other geological survey organizations. The geoscientific information included within these source geological maps wasstandardized, translated to English, and combined to provide complete coverage of Canada and support a range of down-stream machine learning applications. Detailed lithological, mineralogical, metamorphic, lithostratigraphic, and lithodemic information was not previously available as onenational-scale product. The source map data was also enhanced by correcting geometry errors and through the application of a new hierarchical generalized lithology classification scheme to subdivide the original rocks types into 35 classes. Each generalized lithology is associated with asemi-quantitative measure of classification uncertainty. Lithostratigraphic and lithodemic names included within the source maps were matched with the Lexicon of Canadian Geological Names (Weblex) wherever possible and natural language processing was used to transform all of the available text-basedinformation into word tokens. Overlapping map polygons and boundary artifacts across political boundaries were not addressed as part of this study. As a result, the CGMC is a patchwork of overlapping bedrock geological maps with varying scale (1:30,000-1:5,000,000), publication year (1996-2023), andreliability. Preferred geological and geochronological maps of Canada are presented as geospatial rasters based on the best available geoscientific information extracted from these overlapping polygons for each map pixel. New higher resolution geological maps will be added over time to fill datagaps and to update geoscientific information for future applications of the CGMC.

This model is derived from geological, geophysical and other forms of geodata. Feature extraction used deep learning. Predictive modelling made use of the deep ensemble method. Displayed is a Pan-Canadian probability map of mineral potential of graphite. This map was generated using known graphite deposits and occurrences and their associated features. Higher probability values highlight areas with an increased probability of graphite mineral systems.