Explore the vast range of titles available.

The well-documented decrease in the annual minimum Arctic sea ice extent over the past few decades is an alarming indicator of current climate change. However, much less is known about the thickness of the Arctic sea ice. Developing accurate forecasting models is critical to better predict its changes and monitor the impacts of global warming on the total Arctic sea ice volume (SIV). Significant improvements in forecasting performance are possible with the advances in signal processing and deep learning. Accordingly, here, we set out to utilize the recent advances in machine learning to develop non-physics-based techniques for forecasting the sea ice volume with low computational costs. In particular, this paper aims to provide a step-wise decision process required to develop a more accurate forecasting model over short- and mid-term horizons. This work integrates variational mode decomposition (VMD) and bidirectional long short-term memory (BiLSTM) for multi-input multi-output pan-Arctic SIV forecasting. Different experiments are conducted to identify the impact of several aspects, including multivariate inputs, signal decomposition, and deep learning, on forecasting performance. The empirical results indicate that (i) the proposed hybrid model is consistently effective in time-series processing and forecasting, with average improvements of up to 60% compared with the case of no decomposition and over 40% compared with other deep learning models in both forecasting horizons and seasons; (ii) the optimization of the VMD level is essential for optimal performance; and (iii) the use of the proposed technique with a divide-and-conquer strategy demonstrates superior forecasting performance.

The Arctic environment is experiencing profound and rapid changes that will have far-reaching implications for resilient and sustainable development at the local and global levels. To achieve sustainable Arctic futures, it is critical to equip policymakers and global and regional stake- and rights-holders with knowledge and data regarding the ongoing changes in the Arctic environment. Community monitoring is an important source of environmental data in the Arctic but this research argues that community-generated data are under-utilized in the literature. A key challenge to leveraging community-based Arctic environmental monitoring is that it often takes the form of large, unstructured data consisting of field documents, media reports, and transcripts of oral histories. In this study, we integrated two computational approaches—topic modeling and network analysis—to identify environmental changes and their implications for resilience and sustainability in the Arctic. Using data from community monitoring reports of unusual environmental events in the Arctic that span a decade, we identified clusters of environmental challenges: permafrost thawing, infrastructure degradation, animal populations, and fluctuations in energy supply, among others. Leveraging visualization and analytical techniques from network science, we further identified the evolution of environmental challenges over time and contributing factors to the interconnections between these challenges. The study concludes by discussing practical and methodological contributions to Arctic resiliency and sustainability.

Local weather forecasts in the Arctic outside of settlements are challenging due to the dearth of ground-level observation stations and high computational costs. During winter, these forecasts are critical to help prepare for potentially hazardous weather conditions, while in spring, these forecasts may be used to determine flood risk during annual snow melt. To this end, a hybrid VMD-WT-InceptionTime model is proposed for multi-horizon multivariate forecasting of remote-region temperatures in Alaska over short-term horizons (the next seven days). First, the Spearman correlation coefficient is employed to analyze the relationship between each input variable and the forecast target temperature. The most output-correlated input sequences are decomposed using variational mode decomposition (VMD) and, ultimately, wavelet transform (WT) to extract time-frequency patterns intrinsic in the raw inputs. The resulting sequences are fed into a deep InceptionTime model for short-term forecasting. This hybrid technique has been developed and evaluated using 35+ years of data from three locations in Alaska. Different experiments and performance benchmarks are conducted using deep learning models (e.g., Time Series Transformers, LSTM, MiniRocket), and statistical and conventional machine learning baselines (e.g., GBDT, SVR, ARIMA). All forecasting performances are assessed using four metrics: the root mean squared error, the mean absolute percentage error, the coefficient of determination, and the mean directional accuracy. Superior forecasting performance is achieved consistently using the proposed hybrid technique.

The idea that the American Great Plains and the Canadian Prairies are just \"fly-over\" country is a mistake. In the post-9/11 era, politicians and policy-makers are paying more attention to the region, especially where border enforcement is concerned. Beyond the Border provides interdisciplinary perspectives on the region's increasing importance. Drawing inspiration from Habermas's observation that certain modern phenomena - from ecological degradation and organized crime to increased capital mobility - challenge a state's ability to retain sovereignty over a fixed geographical region, contributors to this book question the ontological status of the Canada-US border. They look at how entertainment media represents the border for their viewers, how Canada and the US enforce the line that separates the two countries, and how the border appears from the viewpoint of Native communities where it was imposed through their traditional lands. Under this scrutiny, the border ceases to appear as self-evident, its status more fragile than otherwise imagined. At a time when the importance of border security is increasingly stressed and the Great Plains and Prairies are becoming more economically and politically prominent, Beyond the Border offers necessary context for understanding decisions by politicians and policy-makers along the forty-ninth parallel. Contributors include Phil Bellfy (Michigan State University), Christopher Cwynar (University of Wisconsin), Brandon Dimmel (Western University), Zalfa Feghali (University of Nottingham), Joshua Miner (University of Iowa), Paul Moore (Ryerson University), Michelle Morris (University of Waterloo), Paul Sando (Minnesota State University Moorhead), and Serra Tinic (University of Alberta).

Climate change in Arctic regions poses a threat to permafrost stability, potentially leading to issues such as infrastructure damage, altered ecosystems, and increased greenhouse gas emissions. The challenge of monitoring permafrost temperatures and identifying critical environmental factors is accentuated by the scarcity of subsurface thermal data in remote Arctic locales. To alleviate this lack of soil thermal data we set out to combine in situ observed soil temperatures with MERRA-2 reanalysis data and Machine Learning (ML) to develop local and season-specific subsurface soil temperature predictions in Alaska. First, reanalysis features are selected based on surface energy budget physics. Coupled with Julian calendar dates, reanalysis features are preprocessed and then fed to the ML prediction model. We conducted a series of computational experiments and tested the results against performance benchmarks to determine the optimal prediction models, length of look-back period of model inputs, and the training set size. Six conventional ML models (e.g., GBDT, RF, SVR) and five statistical baselines (e.g. ARIMA) using in situ time series of soil temperature data ranging from 0 - 1 m depth are considered for the prediction task. The models are trained using in situ soil temperatures at depths between 0 and 1 m, spanning 16+ years, from field sites at Deadhorse and Toolik Lake, Alaska. All prediction performances are assessed using root mean squared error (RMSE) and mean absolute error (MAE). Results show that locally trained ML models can estimate shallow soil temperatures with an average error of R M S E = 1 . 308 ∘ C. Plain English Summary Climate change in Arctic regions poses a threat to permafrost stability, potentially leading to issues such as infrastructure damage, altered ecosystems, and increased greenhouse gas emissions. The challenge of monitoring permafrost temperatures and identifying critical environmental factors is made more difficult by the lack of subsurface temperature data in remote Arctic regions. To reduce the problem of this lack of soil temperature data we set out to combine observed soil temperatures with atmospheric computer model data and Machine Learning (ML) to develop local and season-specific subsurface soil temperature predictions in Alaska. We conducted a series of computational experiments and tested the results of the experiments against other non-ML models to ascertain the effectiveness of ML in predicting soil temperature, to determine how much soil temperature data is required to develop a soil temperature prediction ML model, and the extent of atmospheric model data necessary for the ML model. All models were trained leveraging soil temperature data from Deadhorse or Toolik Lake, Alaska, and the results of the ML models show that soil temperatures can be predicted with an average error of 1 . 308 ∘ C.

In 1991, the Canadian documentary Starting Fire with Gunpowder was produced, focusing in part on the history of early media productions by the Inuit Broadcasting Corporation (IBC). It examined how the creation of Inuktitut media content could be an effective means of creative improvisation, linguistic and cultural preservation, and transmission of traditional knowledge. Almost 20 years later, the Internet serves as one of the primary communicative methods for young Inuit in the Canadian Arctic. However, it remains to be seen whether the quality of Inuktitut media online can compare with the example of linguistic and cultural preservation set by the visionaries of the early IBC. This article challenges prevailing critical approaches to the Inuit as linguistically and culturally vulnerable. It views Inuktitut New Media content as an embodiment of the word airaq (‘edible roots’), used here as a model of strength, resilience, and adaptability. It concludes that the creativity and prolificacy of the early IBC productions should set the standard for a new generation of Inuktitut content creators online.

In 1991, the Canadian documentary Starting Fire with Gunpowder was produced, focusing in part on the history of early media productions by the Inuit Broadcasting Corporation (IBC). It examined how the creation of Inuktitut media content could be an effective means of creative improvisation, linguistic and cultural preservation, and transmission of traditional knowledge. Almost 20 years later, the Internet serves as one of the primary communicative methods for young Inuit in the Canadian Arctic. However, it remains to be seen whether the quality of Inuktitut media online can compare with the example of linguistic and cultural preservation set by the visionaries of the early IBC. This article challenges prevailing critical approaches to the Inuit as linguistically and culturally vulnerable. It views Inuktitut New Media content as an embodiment of the word airaq ('edible roots'), used here as a model of strength, resilience, and adaptability. It concludes that the creativity and prolificacy of the early IBC productions should set the standard for a new generation of Inuktitut content creators online. // ABSTRACT IN FRENCH: En 1991 fut produit le documentaire canadien Starting Fire with Gunpowder, dont le sujet était l'histoire des premières productions médiatiques de l'Inuit Broadcasting Corporation (IBC). Il examinait comment la création d'un contenu en inuktitut dans les médias pouvait constituer un moyen efficace d'improvisation créative, de préservation linguistique et culturelle et de transmission des savoirs traditionnels. Presque 20 ans plus tard, Internet représente l'un des principaux moyens de communication pour les jeunes Inuit du Nord canadien. Cependant, reste à savoir si la qualité des médias en inuktitut disponibles électroniquement peut se comparer à l'exemple de la préservation culturelle et linguistique instaurée par les visionnaires de l'IBC à ses débuts. Cet article prend le contrepied des approches théoriques voulant que les Inuit soient linguistiquement et culturellement vulnérables. Il considère les contenus en inuktitut des nouveaux médias comme une concrétisation du mot airaq ('racines comestibles') utilisé ici comme un modèle de la force, de la résilience et de l'adaptabilité. L'article conclut que la créativité et la prolificité des premières productions de l'IBC devraient constituer la norme de référence pour une nouvelle génération de créateurs de nouveaux médias en inuktitut.

The Canada-US border serves a paradoxical function: it separates two countries, even as it sutures them together. As a result, weird things happen there. The border interrupts space and marks a break between one discrete place and another. We experience this each time we cross it, stop at the inspection station, and hand over our passports. The space we pass through is not continuous. The border also interrupts time, although the break is perhaps more abstract. To cross the border is to leave one temporal frame of reference and national timeline, replete with its own history and sense of order,

We opened this book with the observation that the border serves a paradoxical function, suturing and separating two countries. We then considered this paradox by examining the mediated border, the political border, and the native border, in each instance parsing out the multiple valences of terms such as mediated, political, and native. We also noted that scholars of the borderlands have long drawn on the discipline of history, which has provided productive tools for thinking about regionality or for comparing and contrasting related phenomena on either side of the border. Despite the richness of this research, however, the paradigms history