ASSESSING THE USE OF SENTINEL-2 FOR EVALUATION OF ARCTIC COASTAL EROSION: Potential and Limitations (Beaufort Sea Coast, Canada)
Bibliographic record
Abstract
Permafrost is a crucial element in the cryosphere and an essential climate variable (ECV) of the Global Climate Observation System (GCOS). The Arctic represents 34% of the global coastlines (Lantuit, 2012). In the context of the RCP 8.5 scenario for 2040-2060, the IPCC projects for the Arctic an average increase of the annual air temperature of 7 ºC compared to 1880-1920 (Guyet al., 2021). Hence, the Arctic is one of the most vulnerable regions to climate change in the world. The Arctic is undergoing rapid transformations (Nielsen et al., 2020). This tendency will grow with the increasing frequency and magnitude of coastal erosion events, as processes are enhanced by reduction of sea ice extent, subsiding and warming permafrost landscapes, along with increasing open water periods, storminess, air and sea surface temperatures, absolute and relative sea level rise, and warmer ocean (Irrgang et al., 2018). The main focus of this study is to evaluate the applicability of Sentinel-2 multispectral data for the delineation of Arctic coastlines and subsequent calculation of shoreline change rates. Recently, several methods have been proposed and are being developed for the automatic delineation of shorelines. However, the nature of Arctic coasts, with high cloudiness, high variability in turbidity, sea-ice, snow banks, variable cliff heights and increased shading due to low solar altitude, poses significant challenges to automatic algorithms. We compare the application of different automatic shoreline delineation algorithms with validation data based on the manual identification of the shorelines. The latter is done on the Sentinel-2 images and using very high-resolution Pleiades (CNES/Airbus) imagery. The study area is located on the Beaufort Sea coast stretching from the Alaska-Yukon border to Banks Island. The manual and automatic shoreline delineation with Sentinel-2 imagery comprise two years: 2016 and 2020. Pleiades analysis was done for 2018, 2020 and 2021. The automatic methods that were tested are the WaterDetect (Cordeiro et al., 2021) and XGBoost (Chen et al., 2016) methods. The results from the performance assessment of the automatic methods and identification of the limiting factors and errors associated with sea and atmosphere conditions will be used to create recommendations for improving the development of automatic coastal classification algorithms for Arctic coasts. This research is part of the Nunataryuk project. Funding under the European Union's Horizon 2020 Research and Innovation Program under grant agreement no. 773421 and from the Climate Change Preparedness in the North Program (Government of Canada). Further funding has been received through the European Space Agency Polar Science Cluster Program (project EO4PAC). Access to Pleiades imagery is promoted by the WMO Polar Space Task Group.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.007 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.002 | 0.003 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".