2022 – 01a Enhancing turfgrass carbon sequestration to improve sustainability and market access
Recent criticisms of the environmental impacts of lawns, including a high climate footprint from mowing, irrigation, and fertilization, pose challenges to the market acceptance of Oregon turfgrass domestically and internationally. However, turfgrass is a perennial crop with minimal soil disturbance, and turf has been shown in studies from Colorado to accumulate soil organic carbon (SOC) at rates comparable to fallowed cropland. The goal of this study is to evaluate how turf species and management practices can be manipulated to enhance soil carbon sequestration, and to characterize trade-offs between carbon sequestration, aesthetic characteristics, and other management requirements. This work will contribute to recommendations on how to manage turfgrass to enhance carbon sequestration, which can improve market access for Oregon seed producers.
2020 – 01a Understanding and predicting pesticide use on golf courses using deep machine learning, Dr. Guillaume Gregoire, Universite Laval
This project aims to use data from the Quebec Pesticides Management Code in order to identify key practices resulting in pesticide use reduction on golf courses and to predict pesticide use evolution under different climate change scenarios. To do so, we will develop a deep machine learning algorithm to analyse the data on golf course pesticide use collected by the Quebec Ministry of environment since 2006 in order to asses pesticide use evolution and its associated risks over the years. A subset of golf courses with different pesticide use profiles will be randomly selected for a further analysis including interviews with superintendents in order to refine the model. Finally, the model will be used in combination with open-source weather data to predict pesticide use evolution on golf courses for the future.