This series of projected future flood susceptibility maps were generated using an XGBoost machine learning model trained on major floods from 2005 to 2023. The trained model was applied to future climate scenarios for 2050, 2070, and 2100, under two SSP scenarios: 245 and 585. The model uses temperature and precipitation time series to estimate potential future flood susceptibility. These maps represent model projections and should be interpreted as indicators of potential flood susceptibility, not precise forecasts.This dataset forms part of a broader collection of flood susceptibility datasets, offering related information and analyses. The collection includes an overview page with associated publications, historic susceptibility values, temporal trends, and future projections.- [Collection – Flood Susceptibility Mapping]( https://open.canada.ca/data/en/dataset/1074f781-85d3-4c86-86cb-fd1c339197dc)- [Historic - Flood Susceptibility Mapping]( https://open.canada.ca/data/en/dataset/ea1384df-bf4a-4743-97bb-870dc43f8d77)- [Trends and Extremes – Flood Susceptibility Mapping]( https://open.canada.ca/data/en/dataset/3202e0a0-0afb-4120-b102-b0c41f0fb9eb)

This series of historic flood susceptibility maps comes from an XGBboost machine learning model trained on major floods from 2005 to 2023. The trained model is then run for each year from 2000 to 2023, including unique temporal characteristics of temperature, precipitation, land use land cover and Normalized Difference Vegetation Index (NDVI), to predict the flood susceptibility of any given year.This dataset forms part of a broader collection of flood susceptibility datasets, offering related information and analyses. The collection includes an overview page with associated publications, historic susceptibility values, temporal trends, and future projections.- [Collection – Flood Susceptibility Mapping]( https://open.canada.ca/data/en/dataset/1074f781-85d3-4c86-86cb-fd1c339197dc)- [Trends and Extremes – Flood Susceptibility Mapping]( https://open.canada.ca/data/en/dataset/3202e0a0-0afb-4120-b102-b0c41f0fb9eb)- [Future - Flood Susceptibility Mapping]( https://open.canada.ca/data/en/dataset/c00f95a3-7bab-4d28-b9cc-b30f06b5afd2)

The data shared are spatially explicit projections of wildfire burn probability across Canada’s forested ecozones under multiple future climate scenarios at a 30-m spatial resolution. It is developed within the framework of Canada’s National Terrestrial Ecosystem Monitoring System (NTEMS). Four future climate scenarios were used to examine the spatiotemporal distribution of burn probability in the 21st century based on climate, vegetation, and topographic conditions ( Mulverhill et al. 2024). Projected burn probability is provided for four Shared Socioeconomic Pathways (SSP1-2.6, SSP2-4.5, SSP3-7.0, and SSP5-8.5) and four future time periods, including 2021-2040, 2041-2060, 2061-2080, and 2081-2100, along with a baseline period representing average climate conditions and burn probability between 1991 and 2020. Outputs represent the probability that the conditions (climate, vegetation, topography) of a given pixel resemble those of historically burned areas. All non-climate variables were held static; therefore, projections represent burn probability under future climate scenarios given contemporary (2020) forest conditions. When using this dataset, please cite Mulverhill et al. (2025), as below.Mulverhill, C., Coops, N. C., Wulder, M. A., Hermosilla, T., White, J. C., & Bater, C. W. (2025). Projected Future Changes in Burn Probability in Canada’s Forests and Communities Under Different Climate Change Scenarios. Canadian Journal of Remote Sensing, 51(1). https://doi.org/10.1080/07038992.2025.2560347(Mulverhill et al. 2025).For a detailed description of the source data and methods applied to the baseline period to enable the Mulverhill et al. (2025) projections, see:Mulverhill, C., Coops, N.C., Wulder, M.A., White, J.C., Hermosilla, T., and Bater, C.W. 2024. “Multidecadal mapping of status and trends in annual burn probability over Canada’s forested ecosystems.” ISPRS Journal of Photogrammetry and Remote Sensing, Vol. 209 pp. 279–295. https://doi.org/10.1016/j.isprsjprs.2024.02.006(Mulverhill et al. 2024).

The Global Deterministic Wave Prediction System (GDWPS) produces wave forecasts out to 120 hours in the future using the third generation spectral wave forecast model WaveWatch III® (WW3). The model is forced by the 10 meters winds and the ice concentration from the Global Deterministic Prediction System (GDPS). The ice concentration is used by the model to attenuate wave growth in areas covered by 25% to 75% ice and to suppress it for concentration above 75%. Forecast elements include significant wave height, peak period and primary swell height, direction and period.

This series of projected future flood susceptibility maps were generated using an XGBoost machine learning model trained on major floods from 2005 to 2023. The trained model was applied to future climate scenarios for 2050, 2070, and 2100, under two scenarios: 245 and 585. The model uses temperature and precipitation time series to estimate potential future flood susceptibility. These maps represent model projections and should be interpreted as indicators of potential flood susceptibility, not precise forecasts. **This third party metadata element follows the Spatio Temporal Asset Catalog (STAC) specification.**

The Regional Deterministic Wave Prediction System (RDWPS) produces wave forecasts out to 48 hours in the future using the third generation spectral wave forecast model WaveWatch III® (WW3). The model is forced by the 10 meters winds from the High Resolution Deterministic Prediction System (HRDPS). Over the Great Lakes, an ice forecast from the Water Cycle Prediction System of the Great Lakes (WCPS) is used by the model to attenuate or suppress wave growth in areas covered by 25% to 75% and more than 75% ice, respectively. Over the ocean, an ice forecast from the Regional Ice Ocean Prediction System (RIOPS) is used: in the Northeast Pacific, waves propagate freely for ice concentrations below 50%, above this threshold there is no propagation; in the Northwest Atlantic the same logic is used as in the Great Lakes. Forecast elements include significant wave height, peak period, partitioned parameters and others. This system includes several domains: Lake Superior, Lake Huron-Michigan, Lake Erie, Lake Ontario, Atlantic North-West and Pacific North-East.

This series of projected future flood susceptibility maps were generated using an XGBoost machine learning model trained on major floods from 2005 to 2023. The trained model was applied to future climate scenarios for 2050, 2070, and 2100, under two scenarios: 245 and 585. The model uses temperature and precipitation time series to estimate potential future flood susceptibility. These maps represent model projections and should be interpreted as indicators of potential flood susceptibility, not precise forecasts. **This third party metadata element follows the Spatio Temporal Asset Catalog (STAC) specification.**

The Regional Deterministic Wave Prediction System (RDWPS) produces wave forecasts out to 48 hours in the future using the third generation spectral wave forecast model WaveWatch III® (WW3). The model is forced by the 10 meters winds from the High Resolution Deterministic Prediction System (HRDPS). Over the Great Lakes, an ice forecast from the Water Cycle Prediction System of the Great Lakes (WCPS) is used by the model to attenuate or suppress wave growth in areas covered by 25% to 75% and more than 75% ice, respectively. Over the ocean, an ice forecast from the Regional Ice Ocean Prediction System (RIOPS) is used: in the Northeast Pacific, waves propagate freely for ice concentrations below 50%, above this threshold there is no propagation; in the Northwest Atlantic the same logic is used as in the Great Lakes. Forecast elements include significant wave height, peak period, partitioned parameters and others. This system includes several domains: Lake Superior, Lake Huron-Michigan, Lake Erie, Lake Ontario, Atlantic North-West and Pacific North-East.

This series of projected future flood susceptibility maps were generated using an XGBoost machine learning model trained on major floods from 2005 to 2023. The trained model was applied to future climate scenarios for 2050, 2070, and 2100, under two scenarios: 245 and 585. The model uses temperature and precipitation time series to estimate potential future flood susceptibility. These maps represent model projections and should be interpreted as indicators of potential flood susceptibility, not precise forecasts. **This third party metadata element follows the Spatio Temporal Asset Catalog (STAC) specification.**

This series of projected future flood susceptibility maps were generated using an XGBoost machine learning model trained on major floods from 2005 to 2023. The trained model was applied to future climate scenarios for 2050, 2070, and 2100, under two scenarios: 245 and 585. The model uses temperature and precipitation time series to estimate potential future flood susceptibility. These maps represent model projections and should be interpreted as indicators of potential flood susceptibility, not precise forecasts. **This third party metadata element follows the Spatio Temporal Asset Catalog (STAC) specification.**