Random Forest Modelling and Monitoring of Surface-Atmosphere Carbon Dioxide Flux in the Hudson Bay Lowlands

Peatlands are a critical component of the global carbon cycle despite covering only 3% of the earth's surface.Within Canada the largest contiguous peatland is the Hudson Bay Lowlands (HBL), storing an estimated 33 Gt of carbon as peat as a result of a small but persistent difference between gross primary productivity (GPP) and ecosystem respiration (ER) over millennia.The vastness and remote nature of the HBL makes insitu monitoring of its carbon cycle difficult.To address this, random forest (RF) regression models driven solely by remote sensing imagery (either 500 m MODIS or 30 m Harmonized Landsat Sentinel) are trained to predict GPP based on eddy covariance CO2 flux data from 2012-2019 for five sites spanning a climatic gradient in the HBL.There is little difference between daily GPP simulations for spatial resolutions between 30 m and 500 m (R 2 = 0.65-0.78),but better temporal resolution improves model results at the annual time step.Additional RF models are trained to predict ER and the net difference between ER and GPP (net ecosystem exchange; NEE) using MODIS data.NEE models are weaker (R 2 = ~0.48)but generally do better than published semiempirical methods based on light use efficiency and temperature-respiration relationships, while ER remains accurately predicted (R 2 = 0.71) by the models.These RF models are then applied to three 48 km  48 km regions around the field sites and compared with established global products from other machine learning algorithms, process-based, atmospheric inversion, and remote sensing-based models for the period 2000-2020.These products predict greater GPP compared to the RF models as few include peatland-specific parameterizations.However, all models (RF and global products) present a common latitudinal trend with the greatest GPP in the south and iii decreasing northward.Most of the models agree that the HBL is a net sink of CO2 for this period but there is less agreement on the magnitude and latitudinal gradient.Remote sensing-based RF models of CO2 flux show promise for monitoring changes in the HBL's carbon flux, particularly when there is land use change or other impactful disturbances on a large scale.formed the supervisory committee and brought a wealth of experience and mastery to the research and writing.I would like to acknowledge the Ontario Ministry of Environment, Conservation and Parks Air Monitoring and Modelling Section led by Aaron Todd and Chris Charron and supported by Andrew Warner and Mike Luciani who have installed and maintained the eddy covariance towers central to this research as well as Dr. Salvatore Curasi for his provision of the AMBER and CLASSIC data products used in the fifth chapter.I am grateful to Emma Stockton for her camaraderie, commiseration and the countless conversations that have kept spirits high as we have both worked towards graduation.Special thanks to my family, especially my parents, who have been supportive of my path since the beginning.And lastly, I would like to recognize my brothers in all but blood who have always had my back.

Récupéré en direct depuis OpenAlex et désinversé. Les résumés ne sont pas conservés dans cette base de données : les index inversés représentent 8,6 Go des 9,3 Go de texte de la base, et le serveur dispose de 13 Go libres.