Mapping Canada's Grassland
The detailed grassland classification of Manitoba’s PE using RF supervised ML classification model and S1 + S2 data combination. https://www.mdpi.com/remotesensing/remotesensing-16-04730/article_deploy/html/images/remotesensing-16-04730-g010.png
Grasslands are among Canada's most valuable ecosystems, providing essential services related to biodiversity conservation, carbon sequestration, forage production, and climate regulation. Yet these landscapes continue to face increasing pressures from land-use change and environmental disturbances.
DALab uses satellite remote sensing, machine learning, and geospatial analytics to map and monitor native, tame, and mixed grasslands across the Canadian Prairies. Our research seeks to improve understanding of ecosystem dynamics, biomass productivity, vegetation change, and carbon storage.
By developing innovative monitoring frameworks and decision-support tools, we aim to support conservation programs, sustainable grazing practices, and evidence-based land management strategies that ensure the long-term health and resilience of grassland ecosystems.
Team Members/ Collaborators
Publications
A Hierarchical Machine Learning-Based Strategy for Mapping Grassland in Manitoba’s Diverse Ecoregions Mousavi, M.; Biney, J.K.M.; Kishchuk, B.; Youssef, A.; Cordeiro, M.R.C.; Friesen, G.; Cattani, D.; Namous, M.; Badreldin, N. (2024). Remote Sensing, 16, 4730. https://doi.org/10.3390/rs16244730
Assessment of remotely sensed inventories for land cover classification of public grasslands in Manitoba, Canada Encabo, J. B. M., Cordeiro, M. R. C., Badreldin, N., McGeough, E. J., & Walker, D. (2023). Grass and Forage Science, 78(4), 590–601. https://doi.org/10.1111/gfs.12631
Enhanced Grassland Biomass Estimation Using Vegetation Indices and Biomass Proxy: A Comparative Study of Parametric and Non-parametric Models in Manitoba’s Prairie Ecozone M. Mousavi and N. Badreldin, IGARSS 2025 - 2025 IEEE International Geoscience and Remote Sensing Symposium, Brisbane, Australia, 2025, pp. 3459-3462, doi: 10.1109/IGARSS55030.2025.11243222