Votre recherche

Les événements météorologiques extrêmes (EME) et les désastres qu’ils entrainent provoquent des conséquences psychosociales qui sont modulées en fonction de différents facteurs sociaux. On constate aussi que les récits médiatiques et culturels qui circulent au sujet des EME ne sont pas représentatifs de l’ensemble des expériences de personnes sinistrées : celles qui en subissent les conséquences les plus sévères tendent aussi à être celles qu’on « entend » le moins dans l’espace public. Ces personnes sont ainsi susceptibles de vivre de l’injustice épistémique, ce qui a des effets délétères sur le soutien qu’elles reçoivent. Face à ces constats s’impose la nécessité de mieux comprendre la diversité des expériences d’EME et d’explorer des stratégies pour soutenir l’ensemble des personnes sinistrées dans leur rétablissement psychosocial. Cet article soutient que la recherche narrative peut contribuer à répondre à ces objectifs. En dépeignant des réalités multiples, la recherche narrative centrée sur les récits de personnes sinistrées présente aussi un intérêt significatif pour l’amélioration des pratiques d’intervention en contexte de désastre. , Extreme weather events (EWE) and their resulting disasters cause psychosocial consequences that are moderated by different social factors. Media and cultural accounts of EWEs do not represent the full range of disaster survivor experiences, that is, those who experienced the most severe consequences also tend to be those least “heard” in the public arena. These people are therefore most likely to experience forms of epistemic injustice that negatively impact the support offered to cope with disaster. Considering these findings, there is a need to better understand the diversity of EWE experiences and explore strategies for supporting all disaster survivors in their psychosocial recovery. This article argues that narrative research can help meet these needs. By portraying the multiple realities of people affected by EWEs, narrative research focusing on the stories of disaster survivors is also of significant interest for improving intervention practices in this context.

Les récits médiatiques et culturels qui circulent sur les événements météorologiques extrêmes (EME) ne sont pas représentatifs de l’ensemble des expériences de personnes sinistrées. Les groupes qui en subissent les conséquences les plus sévères tendent à être ceux que l’on « entend » le moins dans l’espace public. L’approche de recherche narrative permet de documenter une diversité d’expériences d’EME pour en tracer un panorama plus complet. Adoptant une approche narrative féministe, notre recherche a été menée auprès de femmes touchées par des inondations en Beauce. Des extraits d’entrevues semi-directives menées avec des femmes sinistrées offrent une illustration des conséquences psychosociales entrainées par les inondations. Les forces des participantes et certains défis rencontrés en lien avec leurs rôles dans la famille et la communauté sont aussi abordés. La méthode adoptée a permis de collecter des récits d’expérience riches et singuliers qui rendent plus tangibles les effets différenciés des EME. Tenir compte de cette diversité d’expériences favoriserait une prise en charge plus équitable des personnes sinistrées à court, moyen et long terme.

Combined sewer surcharges in densely urbanized areas have become more frequent due to the expansion of impervious surfaces and intensified precipitation caused by climate change. These surcharges can generate system overflows, causing urban flooding and pollution of urban areas. This paper presents a novel methodology to mitigate sewer system surcharges and control surface water. In this methodology, flow control devices and urban landscape retrofitting are proposed as strategies to reduce water inflow into the sewer network and manage excess water on the surface during extreme rainfall events. For this purpose, a 1D/2D dual drainage model was developed for two case studies located in Montreal, Canada. Applying the proposed methodology to these two sites led to a reduction of the volume of wastewater overflows by 100% and 86%, and a decrease in the number of surface overflows by 100% and 71%, respectively, at the two sites for a 100-year return period 3-h Chicago design rainfall. It also controlled the extent of flooding, reduced the volume of uncontrolled surface floods by 78% and 80% and decreased flooded areas by 68% and 42%, respectively, at the two sites for the same design rainfall.

Résumé L'hydrogéomorphologie étudie la dynamique des rivières en se concentrant sur les interactions liant la structure des écoulements, la mobilisation et le transport des sédiments et les morphologies qui caractérisent les cours d'eau et leur bassin‐versant. Elle offre un cadre d'analyse et des outils pour une meilleure intégration des connaissances sur la dynamique des rivières pour la gestion des cours d'eau au sens large, et plus spécifiquement, pour leur restauration, leur aménagement et pour l'évaluation et la prévention des risques liés aux aléas fluviaux. Au Québec, l'hydrogéomorphologie émerge comme contribution significative dans les approches de gestion et d'évaluation du risque et se trouve au cœur d'un changement de paradigme dans la gestion des cours d'eau par lequel la restauration des processus vise à augmenter la résilience des systèmes et des sociétés et à améliorer la qualité des environnements fluviaux. Cette contribution expose la trajectoire de l'hydrogéomorphologie au Québec à partir des publications scientifiques de géographes du Québec et discute des visées de la discipline en recherche et en intégration des connaissances pour la gestion des cours d'eau . , Abstract Hydrogeomorphology studies river dynamics, focusing on the interactions between flow structure, sediment transport, and the morphologies that characterize rivers and their watersheds. It provides an analytical framework and tools for better integrating knowledge of river dynamics into river management in the broadest sense, and more specifically, into river restoration as well as into the assessment and prevention of risks associated with fluvial hazards. In Quebec, hydrogeomorphology is emerging as a significant contribution to risk assessment and management approaches, and is at the heart of a paradigm shift in river management whereby process restoration aims to increase the resilience of fluvial systems and societies, and improve the quality of fluvial environments. This contribution outlines the trajectory of hydrogeomorphology in Quebec, based on scientific publications by Quebec geographers, and discusses the discipline's aims in research and knowledge integration for river management . , Messages clés Les géographes du Québec ont contribué fortement au développement des connaissances et outils de l'hydrogéomorphologie. L'hydrogéomorphologie a évolué d'une science fondamentale à une science où les connaissances fondamentales sont au service de la gestion des cours d'eau. L'hydrogéomorphologie et le cortège de connaissances et d'outils qu'elle promeut font de cette discipline une partenaire clé pour une gestion holistique des cours d'eau.

RÉSUMÉ: Les courbes Intensité-Durée-Fréquence (IDF) sont l’outil mathématique principalement utilisé par les ingénieur(-e)s pour la modélisation des précipitations extrêmes à un endroit donné. Pour obtenir des courbes IDF fiables, des méthodes statistiques robustes sont nécessaires. L’utilisation de modèles d’échelle est indiquée pour estimer de façon plus précise les courbes IDF en réduisant le nombre de paramètres nécessaires pour modéliser le comportement ex-trême du processus de pluie. Un modèle d’échelle suppose l’existence d’une relation entre les distributions des maxima annuels d’intensité pour les différentes durées d’accumulation. Il existe différentes relations d’échelle possibles, donnant naissance à une variété de modèles. Dans ce mémoire, une procédure de test statistique est développée pour décider si un modèle d’échelle fixé est pertinent pour construire les courbes IDF à un endroit donné, basé sur les observations des maxima annuels historiques d’intensité de précipitations à cet endroit. Le test développé est une extension du test d’adéquation d’Anderson-Darling. Il implique de séparer la base de données en ensembles d’entraînement et de validation. L’ensemble d’entraînement est utilisé pour estimer les paramètres du modèle d’intérêt, et l’ensemble de validation est utilisé dans le calcul de la statistique. La distribution asymptotique de la statistique de test sous l’hypothèse nulle est établie dans un cadre général. Les quantiles de cette distribution théorique peuvent être approximés, ce qui permet de calculer analytiquement la région de rejet ainsi que la valeur-p pour le test. Dans le cas des courbes IDF, l’hypothèse nulle statue qu’un modèle d’échelle d’intérêt est adéquat. Les données sont des maxima d’intensité de précipitations. Les données correspondant à une durée d’accumulation fixée par l’utilisateur(trice) sont sélectionnées pour constituer l’ensemble de validation. Lorsque la durée choisie est la plus petite durée, les performances du test sont validées par une étude de simulation. Sous l’hypothèse nulle, le test rejette au taux nominal même pour des petits échantillons. Sous une hypothèse alternative (c’est-à-dire lorsque le modèle d’échelle utilisé pour générer les données s’écarte du modèle d’intérêt), le taux de rejet augmente avec la distance entre les modèles ainsi qu’avec la taille d’échantillon. Sur des données réelles, le test conduit à utiliser des modèles d’échelle différents à l’aéroport international Pierre-Elliott Trudeau de Montréal et à l’aérodrome Harbour de Vancouver. ABSTRACT: IDF curves are the primary mathematical tool used by engineers for modeling extreme precipitation at a given location. Reliable IDF curves require robust statistical methods. The use of scaling models allows for more precise estimations of IDF curves by reducing the num-ber of parameters needed to model the extreme behavior of the rainfall process. A scaling model assumes the existence of a relationship between the distributions of the annual inten-sity maxima accross the various accumulation durations. Diverse scaling relationships exist, giving rise to a variety of models. In this master thesis, a statistical testing procedure is developed to determine if a scaling model is suitable for constructing IDF curves at a given location, based on historical annual rain intensity maxima observed at that location. The developed test is an extension of the Anderson-Darling goodness-of-fit test. It involves splitting the database into training and validation sets. The training set is used to estimate the parameters of the model of interest, and the validation set is used in the calculation of the test statistic. The asymptotic distribution of the test statistic under the null hypothe-sis is established in a general framework. Quantiles of this theoretical distribution can be approximated, allowing for the analytical calculation of the rejection region as well as the p-value for the test. In the case of IDF curves, the null hypothesis states that a target scaling model is adequate. The data consist of precipitation intensity maxima. Data corresponding to a duration fixed by the user are selected to constitute the validation set. When the chosen duration is the smallest duration, the performances of the test are validated through a simulation study. Under the null hypothesis, the test maintains the nominal rejection rate even for small samples. Under an alternative hypothesis (i.e., when the scaling model used to generate the data deviates from the target model), the rejection rate increases with the discrepancy between the models as well as with the sample size. When applied to historical data, the test suggests the use of different scaling models at the Montréal Pierre-Elliott Trudeau international airport and at the Vancouver Harbour aerodrome.

Improving Disaster Preparedness Through Mutual Catastrophe Insurance In “A Mutual Catastrophe Insurance Framework for Horizontal Collaboration in Prepositioning Strategic Reserves,” H. Zbib, B. Balcik, M.-È. Rancourt, and G. Laporte present an innovative approach to collaborative disaster preparedness. The novel framework considers a risk-averse mutual insurer offering multiyear insurance contracts with coverage deductibles and limits to a portfolio of risk-averse policyholders. It is designed to foster horizontal collaboration among policyholders for joint disaster preparedness by effectively integrating operational and financial functions. The problem is modeled as a large-scale nonlinear multistage stochastic program and solved by using an effective Benders decomposition algorithm. The framework is validated with real data from 18 Caribbean countries focusing on hurricane preparedness. Given the predicted impacts of climate change, the proposed multiyear mutual catastrophe insurance framework promises to reshape global disaster preparedness and make a profound societal impact by providing a transparent disaster financing plan to protect vulnerable regions. The study’s findings stress the importance of long-term cooperation, prenegotiation of indemnification policies, and strategic setting of deductibles and limits by taking into account the correlation between policyholders. , We develop a mutual catastrophe insurance framework for the prepositioning of strategic reserves to foster horizontal collaboration in preparedness against low-probability high-impact natural disasters. The framework consists of a risk-averse insurer pooling the risks of a portfolio of risk-averse policyholders. It encompasses the operational functions of planning the prepositioning network in preparedness for incoming insurance claims, in the form of units of strategic reserves, setting coverage deductibles and limits of policyholders, and providing insurance coverage to the claims in the emergency response phase. It also encompasses the financial functions of ensuring the insurer’s solvency by efficiently managing its capital and allocating yearly premiums among policyholders. We model the framework as a very large-scale nonlinear multistage stochastic program, and solve it through a Benders decomposition algorithm. We study the case of Caribbean countries establishing a horizontal collaboration for hurricane preparedness. Our results show that the collaboration is more effective when established over a longer planning horizon, and is more beneficial when outsourcing becomes expensive. Moreover, the correlation of policyholders affected simultaneously under the extreme realizations and the position of their claims in their global claims distribution directly affects which policyholders get deductibles and limits. This underlines the importance of prenegotiating policyholders’ indemnification policies at the onset of collaboration. Funding: G. Laporte and M.-È. Rancourt were funded by the Canadian Natural Sciences and Engineering Research Council (NSERC) [Grants 2015-06189 and 2022-04846]. Funding was also provided by the Institute for Data Valorisation (IVADO) and the Canada Research Chair in Humanitarian Supply Chain Analytics. B. Balcik was partially supported by a grant from the Scientific and Technological Research Council of Turkey (TUBITAK) 2219 program. This support is gratefully acknowledged. Supplemental Material: The online appendix is available at https://doi.org/10.1287/opre.2021.0141 .

Abstract This study investigates possible trends and teleconnections in temperature extremes in New South Wales (NSW), Australia. Daily maximum and minimum temperature data covering the period 1971–2021 at 26 stations located in NSW were used. Three indices, which focus on daily maximum temperature, daily minimum temperature, and average daily temperature in terms of Excessive Heat Factor (EHF) were investigated to identify the occurrence of heatwaves (HWs). The study considered HWs of different durations (1-, 5-, and 10-days) in relation to intensity, frequency, duration, and their first occurrence parameters. Finally, the influences of three global climate drivers, namely – the El Niño/Southern Oscillation (ENSO), the Southern Annular Mode (SAM), and the Indian Ocean Dipole (IOD) were investigated with associated heatwave attributes for extended Austral summers. In this study, an increasing trend in both hot days and nights was observed for most of the selected stations within the study area. The increase was more pronounced for the last decade (2011–2021) of the investigated time period. The number, duration and frequency of the heatwaves increased over time considering the EHF criterion, whereas no particular trend was detected in cases of TX90 and TN90. It was also evident that the first occurrence of all the HWs shifted towards the onset of the extended summer while considering the EHF criterion of HWs. The correlations between heatwave attributes and climate drivers depicted that heatwave over NSW was positively influenced by both the IOD and ENSO and negatively correlated with SAM. The findings of this study will be useful in formulating strategies for managing the impacts of extreme temperature events such as bushfires, floods, droughts to the most at-risk regions within NSW.

Extreme precipitation events play a crucial role in shaping the vulnerability of regions like Algeria to the impacts of climate change. To delve deeper into this critical aspect, this study investigates the changing patterns of extreme precipitation across five sub-regions of Algeria using data from 33 model simulations provided by the NASA Earth Exchange Global Daily Downscaled Climate Projections (NEX-GDDP-CMIP6). Our analysis reveals a projected decline in annual precipitation for four of these regions, contrasting with an expected increase in desert areas where annual precipitation levels remain low, typically not exceeding 120 mm. Furthermore, key precipitation indices such as maximum 1-day precipitation (Rx1day) and extremely wet-day precipitation (R99p) consistently show upward trends across all zones, under both SSP245 and SSP585 scenarios. However, the number of heavy precipitation days (R20mm) demonstrates varied trends among zones, exhibiting stable fluctuations. These findings provide valuable foresight into future precipitation patterns, offering essential insights for policymakers and stakeholders. By anticipating these changes, adaptive strategies can be devised to mitigate potential climate change impacts on crucial sectors such as agriculture, flooding, water resources, and drought.

Les changements climatiques sont un défi mondial imminent, dont les conséquences sont déjà observées. On sait que ces effets s’intensifieront, entraînant une augmentation de la fréquence et de la gravité des événements météorologiques extrêmes, une perturbation substantielle de la production alimentaire et le déplacement de dizaines de millions de personnes en raison de vagues de chaleur mortelles et de sécheresses. La question est donc : que peut-on y faire ? Dans cette thèse, nous faisons des changements climatiques notre objet central et explorons les voies par lesquelles la recherche en apprentissage profond peut contribuer à son atténuation. Un obstacle connu à des politiques climatiques ambitieuses est le manque de soutien et de demande populaires. Cela peut être attribué, en partie, aux causes et conséquences extrêmement complexes et imbriquées des changements climatiques. Une mauvaise conception courante est qu'ils affecteront principalement d’autres personnes que soi-même, des personnes éloignées dans le temps ou l’espace. Pour y remédier, la recherche a montré que présenter aux gens des \textit{images} authentiques, locales et pertinentes d'un concept les aide à mieux comprendre et appréhender ce qui est en jeu. Dans notre première contribution, nous explorons donc comment les récentes avancées en apprentissage profond pour la vision par ordinateur et les réseaux antagonistes génératifs peuvent être utilisées pour générer des images \textit{personnalisées} représentant les impacts du changement climatique. Notre objectif avec \textit{ClimateGAN} est de visualiser à quoi pourrait ressembler une inondation d’un mètre à n’importe quelle adresse, indépendamment de son risque réel d’inondation sous l’effet des changements climatiques. Cette approche vise à susciter l’empathie en rendant les impacts abstraits du changement climatique plus tangibles et personnalisés. En utilisant une image de Google Street View et en la traitant avec \textit{ClimateGAN}, nous générons des images d’inondation physiquement plausibles et visuellement réalistes basées sur l’adaptation de domaine à partir d’un environnement simulé, la prédiction de profondeur et la segmentation sémantique. Ce modèle a été déployé sur un site web dans le but de sensibiliser et d’engager l’action en faveur des changements climatiques. En plus d’aider les gens à mieux visualiser à quoi pourrait ressembler un avenir climatique hors de contrôle, nous étudions également dans cette thèse comment l’apprentissage profond peut améliorer les technologies existantes. Un domaine majeur de recherche dans cette direction est la recherche de nouveaux matériaux. Dans cette thèse, nous explorons plus particulièrement la prédiction des propriétés des matériaux comme moyen d’accélérer la découverte d'électro-catalyseurs, une famille de matériaux impliqués dans le stockage d’énergie à base d’hydrogène. Nous présentons deux contributions, \textit{PhAST} et \textit{FAENet}, qui se concentrent sur l’amélioration du compromis performance/scalabilité dans les réseaux de neurones géométriques de graphe (GNN). Avec \textit{PhAST}, nous introduisons un ensemble de méthodes pour adapter la procédure GNN classique--de la création du graphe d’entrée aux prédictions d’énergie et de forces de sortie--à la tâche spécifique de prédire l’énergie d’un système atomique adsorbant-catalyseur relaxé. Nous démontrons comment, en plus d’améliorer les performances, ces modifications améliorent l’efficacité et permettent un entraînement compétitif des GNN dans des environnements CPU. Dans \textit{FAENet}, nous présentons un nouveau GNN efficace pour les prédictions équivariantes E(3). En particulier, nous transposons la charge de l’équivarience sur la représentation des données afin de réduire les contraintes sur le modèle lui-même. Cette approche nous permet d’introduire une nouvelle architecture légère et expressive visant à faire des prédictions meilleures et plus rapides de diverses propriétés des matériaux. Enfin, nous examinons de manière critique notre propre domaine et discutons des impacts environnementaux associés aux technologies de l’IA. Nous nous penchons sur la façon dont les praticiens peuvent estimer leurs émissions de carbone, quelles mesures ils peuvent prendre aujourd’hui pour les réduire, et quelles autres étapes sont nécessaires pour des déclarations et responsabilités environnementales plus précises.

Agriculture is the traditional and leading field of economy of Tetritskaro Municipality, but faces the challenge of changing climate. The study investigates male and female farmers’ perception of climate change issues in Tetritskaro, their main source of information, adaptation measures choosen and their needs. Climate change data available in Tetritskaro focused on characteristic extreme weather events coupled with face-to-face interviews from 254 farmers (male - 53%, female - 47%) was analyzed. The study revealed that men and women have more or less similar perceptions of climate change issues. For male farmers, the main source of information on climate, seasonal prediction and weather forecast is conversations with fellow farmers, and for female farmers it is indigenous knowledge of the local environment. Male and female farmers, have adapted to the changes in climate similarly applying measures such as pesticides, fertilizer and irrigation, early sowing, and earlier harvest, while the exchange of information between fellow farmers, use of various hail protection products and crop diversification techniques is more frequent among male farmers. Farmers expressed the need for low interest loans to purchase agricultural products, equipment and restore/create windbreak zones. Most of the male farmers indicate the need for introduction new technologies, while female farmers are more in need of information and training in agricultural activities. The study shows the need for development of climate change adaptation policies and interventions in Tetritskaro. Obtained results can be used not only in other agricultural regions of Georgia, but in other countries with the same problems. , Agriculture is the traditional and leading field of economy of Tetritskaro Municipality, but faces the challenge of changing climate. The study investigates male and female farmers’ perception of climate change issues in Tetritskaro, their main source of information, adaptation measures choosen and their needs. Climate change data available in Tetritskaro focused on characteristic extreme weather events coupled with face-to-face interviews from 254 farmers (male - 53%, female - 47%) was analyzed. The study revealed that men and women have more or less similar perceptions of climate change issues. For male farmers, the main source of information on climate, seasonal prediction and weather forecast is conversations with fellow farmers, and for female farmers it is indigenous knowledge of the local environment. Male and female farmers, have adapted to the changes in climate similarly applying measures such as pesticides, fertilizer and irrigation, early sowing, and earlier harvest, while the exchange of information between fellow farmers, use of various hail protection products and crop diversification techniques is more frequent among male farmers. Farmers expressed the need for low interest loans to purchase agricultural products, equipment and restore/create windbreak zones. Most of the male farmers indicate the need for introduction new technologies, while female farmers are more in need of information and training in agricultural activities. The study shows the need for development of climate change adaptation policies and interventions in Tetritskaro. Obtained results can be used not only in other agricultural regions of Georgia, but in other countries with the same problems.

Abstract Extreme precipitation events can have a significant impact on the environment, agriculture, economy and safety, making close monitoring of their short‐ and long‐term trends essential for the development of effective mitigation and adaptation strategies. In this study, we analysed 16 in situ observation datasets from four different climate zones in Algeria, spanning from 1969 to 2021. The trend analysis was conducted using the original Mann–Kendall test and seven modified tests to eliminate the effects of short‐term persistence. Our findings reveal a significant increasing trend of extreme precipitation variability for most stations in the Warm Mediterranean climate zone, except for the Consecutive dry days index, which showed a negative trend for the same zone, while stations in the Cold/Warm semi‐arid climate and Cold desert climate (Bwk) zones showed a decreasing trend. Additionally, all index series with significant long‐term trends were affected by a significant shift in their means, which was confirmed by both the Lombard and Pettitt tests. However, when we used the modified MPT and the test eliminating the effects of long‐term persistence, the significance of the shifts and the trend decreased. Our results suggest that while extreme precipitation events have been increasing in some parts of Algeria; the trend may not be statistically significant in the long‐run, indicating the necessity of revisiting and refreshing the findings of previous studies for a more current perspective.

To study the mechanical and cracking modes of anhydrite rock under the freeze–thaw weathering process, the physico-mechanical characteristics and morphology evolutions of anhydrite samples were determined by a series of laboratory tests. Then, a numerical simulation model was established through the PFC2D program, and the types and number of cracks during the uniaxial compression conditions were analyzed. Finally, the distribution of maximum principal stress and shear stress was revealed. The results indicate that as the number of freeze–thaw cycles increases, there is a growth in the mass loss rate and macroscopic damage variables while the uniaxial compression strength and elastic modulus decrease exponentially. Under uniaxial compression stress, the proportion of tensile cracks in the anhydrite model is the highest, followed by tensile shear cracks and compressive shear cracks. As the number of freeze–thaw cycles increases, the proportion of tensile cracks increases exponentially, while the proportion of tensile shear cracks and compressive shear cracks decreases exponentially. Furtherly, it is found that the maximum principal stress and maximum shear stress extreme values decrease exponentially with the increase of freeze–thaw cycles. For example, after 120 cycles, the maximum shear stress at the peak stress point decreased by 47.3%. The research results will promote the comprehension of anhydrite rock geotechnical engineering disaster mechanisms in cold regions.

Abstract Understanding the relationship between urban form and structure and spatial inequality of property flood risk has been a longstanding challenge in urban planning and emergency management. Here we explore eight urban form and structure features to explain variability in spatial inequality of property flood risk among 2567 US counties. Using datasets related to human mobility and facility distribution, we identify notable variation in spatial inequality of property flood risk, particularly in coastline and metropolitan counties. The results reveal variations in spatial inequality of property flood risk can be explained based on principal components of development density, economic activity, and centrality and segregation. The classification and regression tree model further demonstrates how these principal components interact and form pathways that explain spatial inequality of property flood risk. The findings underscore the critical role of urban planning in mitigating flood risk inequality, offering valuable insights for crafting integrated strategies as urbanization progresses.

The 2023 wildfire season in Québec set records due to extreme warm and dry conditions, burning 4.5 million hectares and indicating persistent and escalating impacts associated with climate change. This study reviews the unusual weather conditions that led to the fires, discussing their extensive impacts on the forest sector, fire management, boreal caribou habitats, and particularly the profound effects on First Nation communities. The wildfires led to significant declines in forest productivity and timber supply, overwhelming fire management resources, and necessitating widespread evacuations. First Nation territories were dramatically altered, facing severe air quality issues and disruptions. While caribou impacts were modest across the province, the broader ecological, economical, and social repercussions were considerable. To mitigate future extreme wildfire seasons, the study suggests changes in forest management practices to increase forest resilience and resistance, adapting industrial structures to changes in wood type harvested, and enhancing fire suppression and risk management strategies. It calls for a comprehensive, unified approach to risk management that incorporates the lessons learned from the 2023 fire season and accounts for ongoing climate change. The studyunderscores the urgent need for detailed planning and proactive measures to reduce the growing risks and impacts of wildfires in a changing climate.

Droughts have extensive consequences, affecting the natural environment, water quality, public health, and exacerbating economic losses. Precise drought forecasting is essential for promoting sustainable development and mitigating risks, especially given the frequent drought occurrences in recent decades. This study introduces the Improved Outlier Robust Extreme Learning Machine (IORELM) for forecasting drought using the Multivariate Standardized Drought Index (MSDI). For this purpose, four observation stations across British Columbia, Canada, were selected. Precipitation and soil moisture data with one up to six lags are utilized as inputs, resulting in 12 variables for the model. An exhaustive analysis of all potential input combinations is conducted using IORELM to identify the best one. The study outcomes emphasize the importance of incorporating precipitation and soil moisture data for accurate drought prediction. IORELM shows promising results in drought classification, and the best input combination was found for each station based on its results. While high Area Under Curve (AUC) values across stations, a Precision/Recall trade-off indicates variable prediction tendencies. Moreover, the F1-score is moderate, meaning the balance between Precision, Recall, and Classification Accuracy (CA) is notably high at specific stations. The results show that stations near the ocean, like Pitt Meadows, have higher predictability up to 10% in AUC and CA compared to inland stations, such as Langley, which exhibit lower values. These highlight geographic influence on model performance.