Spatio-temporal features of permafrost thaw projected from long-term high-resolution modeling for a region in the Hudson Bay Lowlands in Canada

2013 ◽  
Vol 118 (2) ◽  
pp. 542-552 ◽  
Author(s):  
Yu Zhang
Keyword(s):  
High Resolution ◽  
Hudson Bay ◽  
Hudson Bay Lowlands ◽  
Permafrost Thaw ◽  
Temporal Features ◽  
Spatio Temporal

Predicting Human Mobility with Reinforcement-Learning-Based Long-Term Periodicity Modeling

2021 ◽  
Vol 12 (6) ◽  
pp. 1-23
Author(s):  
Shuo Tao ◽  
Jingang Jiang ◽  
Defu Lian ◽  
Kai Zheng ◽  
Enhong Chen
Keyword(s):  
Reinforcement Learning ◽  
Human Mobility ◽  
Recurrent Network ◽  
Mobility Prediction ◽  
Learning Framework ◽  
Temporal Features ◽  
Wide Range ◽  
Spatio Temporal ◽  
Historical Trajectory

Mobility prediction plays an important role in a wide range of location-based applications and services. However, there are three problems in the existing literature: (1) explicit high-order interactions of spatio-temporal features are not systemically modeled; (2) most existing algorithms place attention mechanisms on top of recurrent network, so they can not allow for full parallelism and are inferior to self-attention for capturing long-range dependence; (3) most literature does not make good use of long-term historical information and do not effectively model the long-term periodicity of users. To this end, we propose MoveNet and RLMoveNet. MoveNet is a self-attention-based sequential model, predicting each user’s next destination based on her most recent visits and historical trajectory. MoveNet first introduces a cross-based learning framework for modeling feature interactions. With self-attention on both the most recent visits and historical trajectory, MoveNet can use an attention mechanism to capture the user’s long-term regularity in a more efficient way. Based on MoveNet, to model long-term periodicity more effectively, we add the reinforcement learning layer and named RLMoveNet. RLMoveNet regards the human mobility prediction as a reinforcement learning problem, using the reinforcement learning layer as the regularization part to drive the model to pay attention to the behavior with periodic actions, which can help us make the algorithm more effective. We evaluate both of them with three real-world mobility datasets. MoveNet outperforms the state-of-the-art mobility predictor by around 10% in terms of accuracy, and simultaneously achieves faster convergence and over 4x training speedup. Moreover, RLMoveNet achieves higher prediction accuracy than MoveNet, which proves that modeling periodicity explicitly from the perspective of reinforcement learning is more effective.

scholarly journals Bird trends from long-term observation data at sites in the Hudson Bay Lowlands

2021 ◽  
Vol 16 (1) ◽  
Author(s):  
Rodney W. Brook ◽  
Lisa A. Pollock ◽  
Kenneth F. Abraham ◽  
Glen S. Brown
Keyword(s):  
Hudson Bay ◽  
Observation Data ◽  
Hudson Bay Lowlands ◽  
Long Term Observation

scholarly journals The Canadian Water Resource Vulnerability Index to Permafrost Thaw (CWRVIPT)

2020 ◽  
Vol 6 (4) ◽  
pp. 437-462
Author(s):  
C. Spence ◽  
M. Norris ◽  
G. Bickerton ◽  
B.R. Bonsal ◽  
R. Brua ◽  
...  
Keyword(s):  
Water Resources ◽  
Water Resource ◽  
Vulnerability Index ◽  
Climatic Conditions ◽  
The Arctic ◽  
Small Scale ◽  
Hudson Bay ◽  
Hudson Bay Lowlands ◽  
Permafrost Thaw ◽  
Canadian North

This study developed and applied a framework for assessing the vulnerability of pan-Canadian water resources to permafrost thaw. The national-scale work addresses a key, but neglected, information gap, as previous research has focused on small scale physical processes and circumpolar trends. The framework was applied to develop the Canadian Water Resources Vulnerability Index to Permafrost Thaw (CWRVIPT) and map the index across the Canadian North. The CWRVIPT is a linearly additive index of permafrost, terrain, disturbance, and climatic conditions and stressors that influence water budgets and aquatic chemistry. Initial results imply water resources in the western Northwest Territories and Hudson Bay Lowlands are most vulnerable to permafrost thaw; however, water resources on Banks, Victoria and Baffin Islands are also relatively vulnerable. Although terrain and permafrost sub-indices are the largest component of the CWRVIPT across a wide swath from the Mackenzie River Delta to the Hudson Bay Lowlands, the climate sub-index is most important farther north over parts of the southern portion of the Arctic Archipelago. The index can be used to identify areas of water resource vulnerability on which to focus observation and research in the Canadian North.

Lichens on the Hudson Bay Lowlands: a long-term survey in Wapusk National Park, Manitoba

2016 ◽  
Vol 48 (5) ◽  
pp. 581-592 ◽  
Author(s):  
Michele D. PIERCEY-NORMORE ◽  
Irwin M. BRODO ◽  
Chris DEDUKE
Keyword(s):  
Species Diversity ◽  
National Park ◽  
Hudson Bay ◽  
Beach Ridge ◽  
Habitat Types ◽  
Hudson Bay Lowlands ◽  
Coastal Beach ◽  
Physiographic Regions ◽  
Unique Species

AbstractWapusk National Park is part of the Hudson Bay Lowlands in Manitoba and covers 11 475 km2. Lichen surveys were initiated in 2002 but none have reported all species incorporating broad habitat types or a baseline on which to make management decisions. The objectives of this study were: 1) to determine species diversity, including species richness and evenness of the lichens present; 2) to explore species distributions; and 3) to compare lichen growth form and substratum relationships among physiographic regions. Fifty-six locations in four habitat types (physiographic regions: open coastal beach ridge, forested coastal beach ridge, boreal transition forest, and peat plateau bog) and three burned locations were visited over nine years and specimens were collected at each location. A total of 276 species and subspecies were collected. One species is new to Canada (Buellia uberior Anzi) and ten species are new to Manitoba. Species diversity, evenness, and richness were highest in the coastal beach ridge. The open coastal beach ridge, boreal transition forest, and peat plateau bogs formed separate clusters in the non-metric multidimensional scaling (NMS) but the forested coastal beach ridge overlapped with the open coastal beach ridge. Unique species in each region may serve as indicators to monitor long-term changes. While the coastal beach ridge facilitates travel along the coast, it also represents the region with the highest need for intervention to conserve species diversity.

scholarly journals Global warming triggers the loss of a key Arctic refugium

2013 ◽  
Vol 280 (1772) ◽  
pp. 20131887 ◽  
Author(s):  
K. M. Rühland ◽  
A. M. Paterson ◽  
W. Keller ◽  
N. Michelutti ◽  
J. P. Smol
Keyword(s):  
Global Warming ◽  
Sea Ice ◽  
Sediment Cores ◽  
Freshwater Ecosystems ◽  
The Arctic ◽  
Hudson Bay ◽  
Native Communities ◽  
Hudson Bay Lowlands ◽  
Short Period

We document the rapid transformation of one of the Earth's last remaining Arctic refugia, a change that is being driven by global warming. In stark contrast to the amplified warming observed throughout much of the Arctic, the Hudson Bay Lowlands (HBL) of subarctic Canada has maintained cool temperatures, largely due to the counteracting effects of persistent sea ice. However, since the mid-1990s, climate of the HBL has passed a tipping point, the pace and magnitude of which is exceptional even by Arctic standards, exceeding the range of regional long-term variability. Using high-resolution, palaeolimnological records of algal remains in dated lake sediment cores, we report that, within this short period of intense warming, striking biological changes have occurred in the region's freshwater ecosystems. The delayed and intense warming in this remote region provides a natural observatory for testing ecosystem resilience under a rapidly changing climate, in the absence of direct anthropogenic influences. The environmental repercussions of this climate change are of global significance, influencing the huge store of carbon in the region's extensive peatlands, the world's southern-most polar bear population that depends upon Hudson Bay sea ice and permafrost for survival, and native communities who rely on this landscape for sustenance.

Long-term successional changes in peatlands of the Hudson Bay Lowlands, Canada inferred from the ecological dynamics of multiple proxies

The Holocene ◽  
2014 ◽  
Vol 25 (1) ◽  
pp. 92-107 ◽  
Author(s):  
Kathryn E Hargan ◽  
Kathleen M Rühland ◽  
Andrew M Paterson ◽  
James Holmquist ◽  
Glen M MacDonald ◽  
...  
Keyword(s):  
Hudson Bay ◽  
Ecological Dynamics ◽  
Hudson Bay Lowlands

Holocene hydro-climatic change and effects on carbon accumulation inferred from a peat bog in the Attawapiskat River watershed, Hudson Bay Lowlands, Canada

2012 ◽  
Vol 78 (2) ◽  
pp. 275-284 ◽  
Author(s):  
Joan Bunbury ◽  
Sarah A. Finkelstein ◽  
Jörg Bollmann
Keyword(s):  
Carbon Accumulation ◽  
Testate Amoeba ◽  
Hudson Bay ◽  
Pollen Record ◽  
Medieval Climate Anomaly ◽  
Northern Ontario ◽  
Peat Core ◽  
Hudson Bay Lowlands ◽  
Isostatic Rebound

AbstractMultiple proxies from a 319-cm peat core collected from the Hudson Bay Lowlands, northern Ontario, Canada were analyzed to determine how carbon accumulation has varied as a function of paleohydrology and paleoclimate. Testate amoeba assemblages, analysis of peat composition and humification, and a pollen record from a nearby lake suggest that isostatic rebound and climate may have influenced peatland growth and carbon dynamics over the past 6700 cal yr BP. Long-term apparent rates of carbon accumulation ranged between 8.1 and 36.7 g C m− 2 yr− 1 (average = 18.9 g C m− 2 yr− 1). The highest carbon accumulation estimates were recorded prior to 5400 cal yr BP when a fen existed at this site, however following the fen-to-bog transition carbon accumulation stabilized. Carbon accumulation remained relatively constant through the Neoglacial period after 2400 cal yr BP when pollen-based paleoclimate reconstructions from a nearby lake (McAndrews et al., 1982) and reconstructions of the depth to the water table derived from testate amoeba data suggest a wetter climate. More carbon accumulated per unit time between 1000 and 600 cal yr BP, coinciding in part with the Medieval Climate Anomaly.

Sign in / Sign up

Export Citation Format

Share Document