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.

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.

A predictive model for Canadian carbonatite-hosted REE ± Nb deposits is presented herein. This model was developed by integrating diverse data layers derived from geophysical, geochronological, and geological sources. These layers represent the key components of carbonatite-hosted REE ± Nb mineral systems, including the source, transport mechanisms, geological traps, and preservation processes. Deep learning algorithms were employed to integrate these layers into a comprehensive predictive framework. Here is a link to the publication that describes this product: https://link.springer.com/article/10.1007/s11053-024-10369-7

The Versatile Soil Moisture Budget (VSMB) is a soil water budget model that is continuous and deterministic in nature and was developed by AAFC. It is based on the premise that the water available for plant growth is gained by precipitation or irrigation, and lost through evapotranspiration and runoff as well as lateral and deep drainage. The daily net loss or gain is added or subtracted from the water already present in the rooting zone. Water is withdrawn simultaneously, but at different rates, from different soil depths, depending on the potential evapotranspiration, the stage of crop development, the water release characteristics of each soil layer and the available water.

This dataset contains the modelled and observed data used in the publication "Fjord circulation permits persistent subsurface water mass in a long, deep mid-latitude inlet" by Laura Bianucci et al., DFO Ocean Sciences Division, Pacific Region (published in the journal Ocean Science in 2024). An application of the Finite Volume Community Ocean Model (FVCOM v4.1) was run from May 24 to June 27, 2019 in the Discovery Islands region of British Columbia, Canada. Observed temperature and salinity profiles available in this area during this time period are included in the dataset, along with the modelled values at the same times and locations.

This deep water substrate bottom type model was created to aid in habitat modeling, and to complement the nearshore bottom patches. It was created from a combination of bathymetrically-derived layers in addition to bottom type observations. Using random forest classification, the relationship between observed substrates and bathymetric derivatives was estimated across the entire area of interest. The raster is categorized into: 1) Rock, 2) Mixed, 3) Sand, 4) Mud

GeoAI are buildings, hydrography, forests, and roads automatically extracted using Deep Learning models applied to a source dataset, typically aerial or satellite images. The primary aim of GeoAI is to increase Canada's availability of high-resolution foundational geospatial data for both spatial and temporal coverage.‌The infrastructure and expertise put in place by NRCan enables a rapid, efficient, and scalable data creation process through the use of leading-edge technology and Artificial Intelligence models. Published datasets for a given source can be revisited at a later date as more accurate models are developed and put into production. For now, only static files are available, but as the series develops, new products and services will be added.

The shallow substrate bottom type model was created to support near shore habitat modelling. Data sources include both available observations of bottom type and environmental predictor layers including oceanographic layers, fetch, and bathymetry and its derivatives. Using weighted random forest classification from the ranger R package, the relationship between observed bottom type and predictor layers can be determined, allowing bottom type to be classified across the study areas. The predicted raster files are classified as follows: 1) Rock, 2) Mixed, 3) Sand, 4) MudThe categorical substrate model domains are restricted to the extent of the input bathymetry layers (see data sources) which is 5 km from the 50 m depth contour.

The Coastal Ice Ocean Prediction System (CIOPS) provides a 48 hour ocean and ice forecast over different domains (East, West, Salish Sea) four times a day at 1/36° resolution. A pseudo-analysis component is forced at the ocean boundaries by the Regional Ice Ocean Prediction System (RIOPS) forecasts and spectrally nudged to the RIOPS solution in the deep ocean. Fields from the pseudo-analysis are used to initialize the 00Z forecast, whilst the 06, 12 and 18Z forecasts use a restart files saved at hour 6 from the previous forecast. The atmospheric fluxes for both the pseudo-analysis and forecast components are provided by the High Resolution Deterministic Prediction System (HRDPS) blended both spatially and temporally with either the Global Deterministic Prediction System (GDPS) (for CIOPS-East) or an uncoupled component of the Global Deterministic Prediction System (GDPS) at 10km horizontal resolution (for CIOPS-West) for areas not covered by the HRDPS.

The Coastal Ice Ocean Prediction System (CIOPS) provides a 48 hour ocean and ice forecast over different domains (East, West, Salish Sea) four times a day at 1/36° resolution. A pseudo-analysis component is forced at the ocean boundaries by the Regional Ice Ocean Prediction System (RIOPS) forecasts and spectrally nudged to the RIOPS solution in the deep ocean. Fields from the pseudo-analysis are used to initialize the 00Z forecast, whilst the 06, 12 and 18Z forecasts use a restart files saved at hour 6 from the previous forecast. The atmospheric fluxes for both the pseudo-analysis and forecast components are provided by the High Resolution Deterministic Prediction System (HRDPS) blended both spatially and temporally with either the Global Deterministic Prediction System (GDPS) (for CIOPS-East) or an uncoupled component of the Global Deterministic Prediction System (GDPS) at 10km horizontal resolution (for CIOPS-West) for areas not covered by the HRDPS.