Funded research programs that combine field, laboratory, drone and satellite observations, from grasslands and forests to farmland, wetlands and urban environments, across scales and over time.
Updating the land use and land cover maps of the Toronto and Region Conservation Authority’s jurisdiction with 2025 PlanetScope imagery and deep learning. The 2020 and 2025 maps can be compared side by side in the lab’s TRCA Land Cover Mapping application.
Testing and evaluating machine learning models that predict nutrient water quality, for Environment and Climate Change Canada’s Freshwater Action Plan work on the phosphorus loads that cause toxic and nuisance algal blooms in the Great Lakes, especially Lake Erie.
The TOsustain project, with eight partner organizations, studies how urban and peri-urban agriculture in the Greater Toronto Area can reduce greenhouse gas emissions and build resilient food systems. Remote sensing is used to build a baseline inventory of land that is, or could be, used for urban agriculture.
Developing a rapid protocol, based on drone imagery and field sampling, for assessing restoration success on rehabilitated aggregate pits in southern Ontario, following a pilot study in 2023. Results from the 2023 surveys are in the lab’s Ecosystem Rehabilitation Dataset.
An infrastructure project at the University of Toronto Mississauga that provides drones, sensors, lab space and computing for flying labs that monitor vegetation health, plant productivity and environmental change, with applications in precision agriculture and carbon-cycle science.
A Hydro One-funded collaboration developing tools that help engineers assess the resilience of Ontario’s current and future power grid to extreme weather, in collaboration with Professor Oh-Sung Kwon’s team.
Integrating remote sensing into ecological research to understand the drivers and mechanisms shaping historical and current vegetation change. The program investigates cumulative and interacting stressors and uses emerging remote-sensing data and cloud platforms such as Google Earth Engine.
Developing efficient, accurate automated methods for detecting fine-scale land disturbance in high-resolution imagery from the Athabasca oil sands region.
A University of Toronto–Zhejiang University project developing an intelligent monitoring system for crop attributes at critical growth stages using multisource remote sensing, spectral unmixing and cloud computing.
Building consistent 50-year spatial datasets for northern Canada by integrating Earth observation and climate data, extending records toward the 1970s where possible.
Building a data assimilation system that brings SMAP and SMOS satellite soil moisture and GRACE/GRACE-FO terrestrial water storage observations into groundwater–surface water models, in support of water security in Canada.
Acquiring airborne hyperspectral imagery and field data for Agriculture and Agri-Food Canada’s project evaluating soil health and nutrient runoff in southern Ontario.
Studying interactions between people and primates, particularly crop-raiding on small farms, near the Lewa Conservancy in Kenya and at Lake Nabugabo in Uganda, with an approach that combines animal-behaviour studies, household surveys, and GIS and Landsat imagery to characterize habitat.
Integrating laboratory and field observations, radiative-transfer modelling and UAV hyperspectral imaging to understand how vegetation stress produces spectral change in Canadian grasslands and forests.
Mapping Emerald Ash Borer infestation in Ontario using field observations, satellite imagery and UAV data, in collaboration with Credit Valley Conservation and the Invasive Species Centre. The project began in 2014 with a UTM Research & Scholarly Activity Fund grant and received a five-year Ontario Early Researcher Award in 2015.
Assessing biomass availability and recovery in uneven-aged forests using LiDAR and harvesting trials, and developing a decision-support model (BiOS) for FPInterface, a tool that simulates the forest-operations supply chain. A collaborative project led by Prof. John Caspersen, Forestry, University of Toronto.
Developing remote sensing methods to map wetlands and predict wetland habitat.
CFI and Ontario Research Fund support established the laboratory’s integrated remote-sensing and ecosystem-modelling infrastructure for Canadian grassland research across biological levels, spatial scales and ecological dimensions.
Developing remote-sensing methods for spatially explicit grassland biochemical properties across scales, supporting carbon, climate, ecosystem-model and sustainability studies. Funded by an NSERC Discovery Grant and Early Career Researcher Supplement.
Using advanced remote sensing and spatial analysis with ecological modelling to identify critical habitat characteristics for the endangered, wetland-dependent Blanding’s turtle (Emydoidea blandingii) in southern Ontario. Geospatial analysis of the species’ movement then assessed the connectivity of critical wetland and upland habitat, identifying areas in need of protection, restoration or mitigation.
A sub-contract from Prof. Xulin Guo (Geography, University of Saskatchewan) to establish an object-based grassland biogeochemical model and test it at sites across Canadian grasslands.
Two NCC-funded projects: the first (2010) evaluated multi-date remote sensing for detecting and mapping endangered wild leek (Allium tricoccum); the second (2011) developed methods to map the endangered White Trillium (Trillium grandiflorum) and raised the accuracy of the wild leek map from 85% to 90%, using field surveys, remote sensing and GIS.
