Votre recherche
Résultats 3 ressources
-
In recent years, understanding and improving the perception of flood risk has become an important aspect of flood risk management and flood risk reduction policies. The aim of this study was to explore perceptions of flood risk in the Petite Nation River watershed, located in southern Quebec, Canada. A survey was conducted with 130 residents living on a floodplain in this river watershed, which had been affected by floods in the spring of 2017. Participants were asked about different aspects related to flood risk, such as the flood hazard experience, the physical changes occurring in the environment, climate change, information accessibility, flood risk governance, adaptation measures, and finally the perception of losses. An analysis of these factors provided perspectives for improving flood risk communication and increasing the public awareness of flood risk. The results indicated that the analyzed aspects are potentially important in terms of risk perception and showed that the flood risk perceptions varied for each aspect analyzed. In general, the information regarding flood risk management is available and generally understandable, and the level of confidence was good towards most authorities. However, the experiences of flood risk and the consequences of climate change on floods were not clear among the respondents. Regarding the adaptation measures, the majority of participants tended to consider non-structural adaptation measures as being more relevant than structural ones. Moreover, the long-term consequences of flooding on property values are of highest concern. These results provide a snapshot of citizens’ risk perceptions and their opinions on topics that are directly related to such risks.
-
In cold regions, ice jams frequently result in severe flooding due to a rapid rise in water levels upstream of the jam. Sudden floods resulting from ice jams threaten human safety and cause damage to properties and infrastructure. Hence, ice-jam prediction tools can give an early warning to increase response time and minimize the possible damages. However, ice-jam prediction has always been a challenge as there is no analytical method available for this purpose. Nonetheless, ice jams form when some hydro-meteorological conditions happen, a few hours to a few days before the event. Ice-jam prediction can be addressed as a binary multivariate time-series classification. Deep learning techniques have been widely used for time-series classification in many fields such as finance, engineering, weather forecasting, and medicine. In this research, we successfully applied convolutional neural networks (CNN), long short-term memory (LSTM), and combined convolutional–long short-term memory (CNN-LSTM) networks to predict the formation of ice jams in 150 rivers in the province of Quebec (Canada). We also employed machine learning methods including support vector machine (SVM), k-nearest neighbors classifier (KNN), decision tree, and multilayer perceptron (MLP) for this purpose. The hydro-meteorological variables (e.g., temperature, precipitation, and snow depth) along with the corresponding jam or no-jam events are used as model inputs. Ten percent of the data were excluded from the model and set aside for testing, and 100 reshuffling and splitting iterations were applied to 80 % of the remaining data for training and 20 % for validation. The developed deep learning models achieved improvements in performance in comparison to the developed machine learning models. The results show that the CNN-LSTM model yields the best results in the validation and testing with F1 scores of 0.82 and 0.92, respectively. This demonstrates that CNN and LSTM models are complementary, and a combination of both further improves classification.