Assistant Professor Koreen Millard
Multi-sensor data fusion for improved understanding of hydrology/vegetation change and interactions; Modelling spatial and temporal biophysical variables with time-series remote sensing and field-measurements; Machine learning image classification for mapping environmental change
|Degrees:||B.A. (Bishop's University), M.Sc. (Acadia University), Ph.D. (Carleton)|
|Phone:||613-520-2600 x 2566|
|Office:||A301D Loeb Building|
My research sits at a crossroads between geomatics, physical geography and big data science. I focus on ecosystem monitoring and extraction of biophysical parameters from remotely sensed imagery, but I also critically assess how bias and uncertainty can affect the use of these tools in a variety of landscapes. By coupling remote sensing with extensive monitoring in the field, my research helps detangle hydrological, vegetation and climate interactions so that we can better predict the responses of wetlands and northern ecosystems to change.
My work in ecosystem mapping began by researching the restoration potential of salt marshes that had been severely impacted by human alteration (dyking, ditching and conversion to agricultural land) in my home region of the Bay of Fundy. This research interest carried forward to my PhD research where I adapted machine learning methods for multi-sensor (polarimetric SAR, LiDAR and optical) imagery classification as well as modelling of soil moisture from Synthetic Aperture Radar (SAR) data for the prediction of surface soil moisture spatially and temporally in peatlands. I have also accumulated a variety of experiences working in the federal government. Most recently I have been leading research for the integration of geomatics methods for estimating emissions for Canada’s Greenhouse Gas (GHG) and Air Pollutant Emissions Inventories at Environment and Climate Change Canada. I am excited about new cloud-based platforms that enable large area mapping and consistent temporal monitoring.
2020 – 2021 Courses
- GEOG 5804 Introduction to GIS
Nandlall, S., and Millard K., (2019) “Quantifying the Relative Importance of Groups of Variables in Remote Sensing Classifiers using Shapley Value and Game Theory”. IEEE Geoscience and Remote Sensing letters. https://ieeexplore.ieee.org/document/8718372
Millard, K., Thompson, D., Parisien, M., Richardson, M., (2018). Soil Moisture Monitoring in a Temperate Peatland Using Multi-Sensor Remote Sensing and Linear Mixed Effects. Remote Sensing. 10(6). https://doi.org/10.3390/rs10060903
Millard, K., and Richardson, M., (2018) “Quantifying the Relative Contributions of Vegetation and Soil Moisture Conditions to Polarimetric C-Band SAR Response in a Temperate Peatland”, Remote Sensing of Environment. 206(1). https://doi.org/10.1016/j.rse.2017.12.011
Millard K., and Richardson M., (2015) “On the importance of training data sample selection in Random Forest classification: a case study in peatland mapping.” Remote Sensing – Special Issue Towards Remote Long-Term Monitoring of Wetland Landscapes, 7(7), 8489-8515, http://www.mdpi.com/2072-4292/7/7/8489
Millard, K., and Richardson, M., (2013) ” Fusion of LiDAR elevation and canopy derivatives with polarimetric SAR decomposition for wetland classification using Random Forest” Canadian Journal of Remote Sensing, 39(4): 290 – 307, http://pubs.casi.ca/doi/abs/10.5589/m13-038
Millard, K., Redden, A., Webster, T., and Stewart, H., (2013) “Use of GIS and high resolution LiDAR in salt marsh restoration site assessments in the upper Bay of Fundy, Canada” Wetlands Ecology and Management, 21(4): 243 – 262, https://link.springer.com/article/10.1007/s11273-013-9303-9
Millard, K, Burke, C., Stiff, .D., and Redden A. (2009) “Detection of a Low Relief 18th Century British Siege Trench Using LiDAR Vegetation Penetration Capabilities at Fort Beausejour – Fort Cumberland National Historic Site, Canada” Journal of Geoarchaeology, 24(5): 576 – 588, http://onlinelibrary.wiley.com/doi/10.1002/gea.20281/full