Votre recherche
Résultats 2 ressources
-
Fluvial flooding in Canada is often snowmelt-driven, thus occurs mostly in spring, and has caused billions of dollars in damage in the past decade alone. In a warmer climate, increasing rainfall and changing snowmelt rates could lead to significant shifts in flood-generating mechanisms. Here, projected changes to flood-generating mechanisms in terms of the relative contribution of snowmelt and rainfall are assessed across Canada, based on an ensemble of transient climate change simulations performed using a state-of-the-art regional climate model. Changes to flood-generating mechanisms are assessed for both a late 21st century, high warming (i.e., Representative Concentration Pathway 8.5) scenario, and in a 2 °C global warming context. Under 2 °C of global warming, the relative contribution of snowmelt and rainfall to streamflow peaks is projected to remain close to that of the current climate, despite slightly increased rainfall contribution. In contrast, a high warming scenario leads to widespread increases in rainfall contribution and the emergence of hotspots of change in currently snowmelt-dominated regions across Canada. In addition, several regions in southern Canada would be projected to become rainfall dominated. These contrasting projections highlight the importance of climate change mitigation, as remaining below the 2 °C global warming threshold can avoid large changes over most regions, implying a low likelihood that expensive flood adaptation measures would be necessary.
-
This proof-of-concept study couples machine learning and physical modeling paradigms to develop a computationally efficient simulator-emulator framework for generating super-resolution (<250 m) urban climate information, that is required by many sectors. To this end, a regional climate model/simulator is applied over the city of Montreal, for the summers of 2019 and 2020, at 2.5 km (LR) and 250 m (HR) resolutions, which are used to train and validate the proposed super-resolution deep learning (DL) model/emulator. The DL model uses an efficient sub-pixel convolution layer to generate HR information from LR data, with adversarial training applied to improve physical consistency. The DL model reduces temperature errors significantly over urbanized areas present in the LR simulation, while also demonstrating considerable skill in capturing the magnitude and location of heat stress indicators. These results portray the value of the innovative simulator-emulator framework, that can be extended to other seasons/periods, variables and regions.