首页|Reports from University of Toronto Mississauga Provide New Insights into Machine Learning (Mapping Canopy Cover for Municipal Forestry Monitoring: Using Free La ndsat Imagery and Machine Learning)
Reports from University of Toronto Mississauga Provide New Insights into Machine Learning (Mapping Canopy Cover for Municipal Forestry Monitoring: Using Free La ndsat Imagery and Machine Learning)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
2024 OCT 03 (NewsRx)-By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Current study results on Machine Learn ing have been published. According to news originating from Mississauga, Canada, by NewsRx correspondents, research stated, "Trees across the urbanrural contin uum are recognized for their ecological importance and ecosystem services. Munic ipalities often utilize spatial canopy cover data for monitoring this resource." Financial supporters for this research include Natural Sciences and Engineering Research Council of Canada (NSERC), Department of Geography, Geomatics and Envir onment, Centre for Urban Environments at the University of Toronto Mississauga, Natural Sciences and Engineering Research Council of Canada (NSERC). Our news journalists obtained a quote from the research from the University of T oronto Mississauga, "Monitoring frameworks typically rely on fine-scale maps der ived from very high spatial resolution sensors, which are high quality but expen sive and unwieldy for consistent wide-area monitoring. In this paper, we explore how free Landsat imagery, supported by very high-resolution imagery interpretat ion and/or digital hemispherical photographs, can be used to effectively map can opy cover at a scale appropriate for municipal monitoring. We compare linear mod els and random forest machine learning for predicting canopy cover across a land scape (general) and within specific land covers (specialized). We create 2018 ca nopy cover maps and track progress towards forestry objectives in a region of so uthern Ontario, Canada. Random forest models using all reference data perform be st for general use (R-2: 0.90, RMSE: 10.1 %), separating non-canopy vegetation (e.g., agricultural fields) from tree canopy. Specialized models are useful in forest land cover patches, where hemispherical photographs relate wit h Landsat at a moderate strength (R-2: 0.67, RMSE: 2.73 %), and in residential areas, capturing the totality of canopy cover variation (R-2: 0.85, RMSE: 5.66 %). Accuracy was assessed with standard cross-validation , which is useful given limited resources. However, following best practice, an independent reference sample was also leveraged to assess the best general model (R-2: 0.86, RMSE: 11.4 %), indicating that cross-validation was sl ightly overoptimistic. Caledon, a rural-dominant municipality within the study a rea, is the greenest (34 % canopy cover). The two cities (Brampton and Mississauga) have 15.9 % and 17.5 % canopy cove r. Residential canopy criteria indicate ‘Good' performance in Caledon, ‘Moderate ' in Mississauga, and ‘Low' in Brampton based on our 2018 assessment."
MississaugaCanadaNorth and Central A mericaCyborgsEmerging TechnologiesMachine LearningUniversity of Toronto Mississauga
NETL
NSTL
