Temporal analysis of changes in Trois-Rivières, Québec, based on GeoAI features automatically extracted from satellite images acquired in 2013 and 2021-22. Simple geospatial analysis intersecting Statistics Canada's Open Database of Buildings, version 3 (ODB v3) with GeoAI multidate building features enables the detection of buildings observed in 2021-22 that were not detected in 2013. The addition of new buildings is a good indicator of urban development and/or sprawl. ‌ GeoAI enables temporal coverage of various areas in Canada, thus providing a useful tool for change detection and trend analysis at high resolution. While the series is still fairly new, and such examples are limited for the time being, NRCan strives to gradually increase its GeoAI data offering for both spatial and temporal coverage. For more information about the GeoAI - GeoBase Series, please visit the following link: https://open.canada.ca/data/en/dataset/74738ff5-5367-5958-9aee-98fffdcd1876

Each pixel value corresponds to the mean historical “Best-quality” Max-NDVI value for a given week, as calculated from the previous 20 years in the MODIS historical record (i.e. does not include data from the current year). These data are also often referred to as “weekly baselines” or “weekly normals”.

Land cover classification image for the Aspen Parkland ecoregion of Saskatchewan with a spatial resolution of 10m. The goal of this land cover classification was to distinguish native from tame grasslands. The classification was based on Sentinel-1 and Sentinel-2 imagery using machine learning analysis in the Google Earth Engine platform. The classification was conducted on imagery acquired in 2022, and the classification model was built with field data collected in 2020 - 2022. There are eight classes in total: native grassland, tame grassland, mixed/altered grassland, cropland, shrubs, trees, water, and urban area. Download: here The Prairie Landscape Inventory (PLI) aims to develop improved methods of assessing land cover and land use for conservation. Native grassland has historically been one of the hardest to map at-risk ecosystems because of the challenges in distinguishing native grassland from tame grassland land cover using remotely sensed imagery. This classification distinguishes native grassland from tame grassland and will provide valuable information for habitat suitability for native grassland species, identifying high biodiversity potential and invasion risk potential. The classification map has eight (8) classes:  1. Cropland This class represents all cultivated areas with crop commodities, including corn, pulse, soybeans, canola, grains, and summer-fallow. 2. Native grassland This class represents the native grassland areas that are composed of at least 75% native grass, sedge and forb species, such as the needle grasses and wheatgrasses along with June grass and blue grama grass. Unbroken grassland that is invaded by species like Kentucky bluegrass, crested wheatgrass or smooth brome, such that native cover is less than 75%, is not considered native for the purpose of this project.  3. Mixed/altered grassland This class represents a grassland with a mix of less than 75% native grass, sedge and forb species or less than 75% tame species. These are grassland areas that do not fit into either of the native or tame grassland definitions.  4. Tame grassland This class represents the tame grassland areas that are composed of at least 75% seeded or planted species with introduced grasses and forb species such as crested wheatgrass, smooth brome, Kentucky bluegrass, alfalfa, and sweet clover. 5. Water This class represents permanent water locations such as lakes and rivers. 6. Shrubs This class represents the sites dominated by woody vegetation of relatively low height (generally +/-2 meters) with shrub canopy typically >20% of total vegetation cover. 7. Trees This class represents the coniferous/deciduous trees, mixed-wood area, and other trees >2 meters height with tree canopy typically >20% of total vegetation cover. 9. Urban area This class represents both urban municipalities and buffered roads. Urban municipalities was used to mask the urban/developed area class of the Annual Crop Inventory 2021 (Agriculture Agri-Food Canada).   Colour Classes: Value Label Red Green Blue 1 Cropland 255 255 190 2 Native grassland 168 168 0 3 Mixed/altered grassland 199 215 158 4 Tame grassland 245 202 122 5 Water 190 232 255 6 Shrubs 205 102 153 7 Trees 66 128 53 9 Urban area 128 128 128 Accuracy metrics This model has an overall accuracy of 73 per cent. The table below summarizes the user’s accuracy, producer’s accuracy, and F1-score of the model on the validation dataset. Class User’s accuracy (%) Producer’s accuracy (%) F1-score Cropland 91.2 94.5 0.93 Native grassland 74.8 73.1 0.74 Mixed grassland 44.7 44.1 0.44 Tame grassland 67.9 72.8 0.70 Water 94.8 91.3 0.93 Shrubs 61.2 51.1 0.56 Trees 89.7 94.6 0.92

Each pixel value corresponds to the difference (anomaly) between the mean “Best-Quality” Max-NDVI of the week specified (e.g. Week 18, 2000-2014) and the “Best-Quality” Max-NDVI of the same week in a specific year (e.g. Week 18, 2015). Max-NDVI anomalies < 0 indicate where weekly Max-NDVI is lower than normal. Anomalies > 0 indicate where weekly Max-NDVI is higher than normal. Anomalies close to 0 indicate where weekly Max-NDVI is similar to normal.

The Canadian long term satellite data record (LTDR) derived from 1-km resolution Advanced Very High Resolution Radiometer (AVHRR) data was produced by the Canada Center for Remote Sensing (CCRS). Processing included: geolocation, calibration, and compositing using Earth Observation Data Manager (Latifovic et al. 2005), cloud screening (Khlopenkov and Trishchenko, 2006), BRDF correction (Latifovic et. al., 2003), atmosphere and other corrections as described in Cihlar et. al. (2004). For temporal analysis of vegetation cross-sensor correction of Latifovic et al. (2012) is advised. Data collected by the AVHRR instrument on board the National Oceanic and Atmospheric Administration (NOAA) 9,11,14,16,17,18 and 19 satellites were used to generate Canada-wide 1-km 10-day AVHRR composites. Data are available starting in 1985. It is important to note that there are three types of AVHRR sensors: (i) AVHRR-1 flown onboard TIROS-N, NOAA-6, NOAA-8, and NOAA-10; (ii) AVHRR-2 flown onboard NOAA-7, NOAA-9, NOAA-11, NOAA-12, and NOAA-14; and (iii) AVHRR-3 currently operational onboard NOAA-15, NOAA-16, NOAA-17, NOAA-18 and NOAA-19. The AVHRR-1 has four channels, AVHRR-2 has five channels and the AVHRR-3 has six channels, although only five channels of AVHRR-3 can be operational at any one time. As such, channels 3A (1.6 m) and 3B (3.7 m) work interchangeably. The processing procedure was designed to minimize artefacts in AVHRR composite images. There are thirty six 10-day image composites per year. The following three processing levels are provided: P1) top of atmosphere reflectance and brightness temperature, P2) reflectance at surface and surface temperature and P3) reflectance at surface normalized to a common viewing geometry (BRDF normalization). The processing level P1 and P2 are provided for all 36 composites while level P3 is provided for 21 composites from April – October.

The RADARSAT Constellation is the evolution of the RADARSAT Program with the objective of ensuring data continuity, improved operational use of Synthetic Aperture Radar (SAR) and improved system reliability. The three-satellite configuration provides daily revisits of Canada's vast territory and maritime approaches, as well as daily access to 90% of the world's surface. RCM is tasked solely by the Government of Canada, to acquire data, first and foremost in support of Government of Canada services and needs. RCM data and services contributes to ensuring the safety and security of Canadians; monitoring and protecting the environment; monitoring of climate change; managing Canada’s natural resources; and stimulating innovation, research and economic development. In addition to these core user areas, there are expected to be a wide range of ad hoc uses of RADARSAT Constellation data in many different applications within the public and private sectors, both in Canada and internationally. The current data set reflects the acquisition plans that are designed to meet the RCM SAR imaging demands of the Government of Canada. These are being made available publicly in advance of the acquisitions. To meet the data needs of the Government of Canada, acquisitions may be changed without notice. After their acquisition and processing, the RCM image products listed in the current data set, will be delivered to the Earth Observation Data Management System - EODMS (https://www.eodms-sgdot.nrcan-rncan.gc.ca/index-en.html) portal of Natural Resources Canada. Users can register to the EODMS portal as public users to retrieve the RCM image products. For those requiring a greater access to RCM imagery consisting of product types or spatial resolutions not available to public users: you may apply to upgrade your public account to an ‘RCM external vetted entity’ EODMS user type account. For more information on this process, please contact the Canadian Space Agency using the information available at the following link : https://www.asc-csa.gc.ca/eng/satellites/radarsat/access-to-data/how-to-become-a-user.asp Publication frequency : I. Future acquisition plans are published every two weeks for a two-week window that starts two weeks from the publication date. As an example, acquisition plan published on April 1st covers acquisitions from April 14 to 27. The next plan is published on April 14th and covers from April 28 to May 11. II. Past acquisitions plans are published monthly and covers a period of one month from the first to the last day As an example, acquisition plan published on April 1st covers acquisition made between the March 1 and March 31. The next plan covers the month of April.

Temporal analysis of changes in Winnipeg, Manitoba, based on GeoAI features automatically extracted from satellite images acquired in 2013 and 2023. Simple geospatial analysis enables the detection of features present in 2023 that were not already there in 2013. The addition of new buildings is a good indicator of urban development and/or sprawl. Complementarily, an analysis of changes in the forest coverage from the GeoAI datasets is done. This analysis reflects the gains and losses between both dates. ‌ GeoAI enables temporal coverage of various areas in Canada, thus providing a useful tool for change detection and trend analysis at high resolution. While the series is still fairly new, and such examples are limited for the time being, NRCan strives to gradually increase its GeoAI data offering for both spatial and temporal coverage. For more information about the GeoAI - GeoBase Series, please visit the following link: https://open.canada.ca/data/en/dataset/74738ff5-5367-5958-9aee-98fffdcd1876

The 2020 AAFC Land Use is a culmination and curated metaanalysis of several high-quality spatial datasets produced between 1990 and 2021 using a variety of methods by teams of researchers as techniques and capabilities have evolved. The information from the input datasets was consolidated and embedded within each 30m x 30m pixel to create consolidated pixel histories, resulting in thousands of unique combinations of evidence ready for careful consideration. Informed by many sources of high-quality evidence and visual observation of imagery in Google Earth, we apply an incremental strategy to develop a coherent best current understanding of what has happened in each pixel through the time series.

The 2015 AAFC Land Use is a culmination and curated metaanalysis of several high-quality spatial datasets produced between 1990 and 2021 using a variety of methods by teams of researchers as techniques and capabilities have evolved. The information from the input datasets was consolidated and embedded within each 30m x 30m pixel to create consolidated pixel histories, resulting in thousands of unique combinations of evidence ready for careful consideration. Informed by many sources of high-quality evidence and visual observation of imagery in Google Earth, we apply an incremental strategy to develop a coherent best current understanding of what has happened in each pixel through the time series.

Each pixel value corresponds to the best quality maximum NDVI recorded within that pixel over the week specified. Poor quality pixel observations are removed from this product. Observations whose quality is degraded by snow cover, shadow, cloud, aerosols, and/or low sensor zenith angles are removed (and are assigned a value of “missing data”). In addition, negative Max-NDVI values, occurring where R reflectance > NIR reflectance, are considered non-vegetated and assigned a value of 0. This results in a Max-NDVI product that should (mostly) contain vegetation-covered pixels. Max-NDVI values are considered high quality and span a biomass gradient ranging from 0 (no/low biomass) to 1 (high biomass).