00000nam 2200000zi 4500 9.917108 CaOODSP 20221122112344 m o d f cr |n||||||||| 221109t20212021qucd ob f000 0 eng d CaOODSP eng rda CaOODSP n-cn-on n-cn-ab M154-151/2021E-PDF Pied, Marie, author. Comparing machine learning and linear regression methods for estimating marginal greenhouse gas emission factors of electricity generation with renewables / prepared by Marie Pied, Sophie Pelland, Steven Wong, Dave Turcotte and Vahid Raissi Dehkordi. [Ottawa] : Natural Resources Canada = Ressources naturelles Canada, 2021. ©2021 1 online resource (ix, 33 pages) : charts text txt rdacontent computer c rdamedia online resource cr rdacarrier "Date: November 30, 2021." Includes bibliographical references (pages 31-33). "The electricity sector is key to reducing greenhouse gas emissions: energy supply across sectors is shifting towards electricity, and electricity production in turn is shifting towards low carbon sources. Marginal greenhouse gas emission factors (MEFs) are needed to properly quantify the impact on greenhouse gas emissions of policies and programs that modify electricity demand. We compared different methods of estimating MEFs applied to the Canadian provinces of Ontario and Alberta: a new method using artificial neural networks and existing methods using simple and multiple linear regression"--Executive summary, page i. Electric power Ontario. Greenhouse gas mitigation Ontario. Climate change mitigation Ontario. Electric power Alberta. Greenhouse gas mitigation Alberta. Climate change mitigation Alberta. Électricité Ontario. Gaz à effet de serre Réduction Ontario. Climat Changements Atténuation Ontario. Électricité Alberta. Gaz à effet de serre Réduction Alberta. Climat Changements Atténuation Alberta. Canada. Natural Resources Canada, issuing body. CanmetENERGY (Canada), issuing body. PDF 2.20 MB https://publications.gc.ca/collections/collection_2022/rncan-nrcan/M154-151-2021-eng.pdf