Gaussian Process Regression for Arctic Coastal Erosion Forecasting

Arctic coastal morphology is governed by multiple factors, many of which are affected by climatological changes. As the season length for shore-fast ice decreases and temperatures warm permafrost soils, coastlines are more susceptible to erosion from storm waves. Such coastal erosion is a concern si...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on geoscience and remote sensing 2019-03, Vol.57 (3), p.1256-1264
Main Authors: Kupilik, Matthew, Witmer, Frank D. W., MacLeod, Euan-Angus, Wang, Caixia, Ravens, Tom
Format: Article
Language:English
Subjects:
Arctic
Climate models
Climatology
Coastal erosion
Coastal morphology
Coastal processes
Coasts
Data
Data models
Decision making
Erosion mechanisms
Fast ice
Forecasting
Gaussian process
Gaussian process (GP)
Ice environments
Imagery
Infrastructure
Land use
Methods
Modelling
Morphology
Permafrost
Predictive models
Satellite imagery
Satellites
Sea measurements
Soil
Soil erosion
Spaceborne remote sensing
Storms
Temperature distribution
Temperature measurement
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Arctic coastal morphology is governed by multiple factors, many of which are affected by climatological changes. As the season length for shore-fast ice decreases and temperatures warm permafrost soils, coastlines are more susceptible to erosion from storm waves. Such coastal erosion is a concern since a large proportion of the population centers and infrastructure in the Arctic are located near the coasts. Stakeholders and decision makers increasingly need models capable of scenario-based predictions to assess and mitigate the effects of coastal morphology on infrastructure and land use. Our research uses Gaussian process (GP) models to forecast Arctic coastal erosion along the Beaufort Sea near Drew Point, AK, USA. GP regression is a data-driven modeling methodology capable of extracting patterns and trends from data-sparse environments such as remote Arctic coastlines. To train our model, we use annual coastline positions and near-shore summer temperature averages from existing data sets and extend these data by extracting additional coastlines from satellite imagery. We combine our calibrated models with future climate models to generate a range of plausible future erosion scenarios. Our results show that the GP methodology substantially improves yearly predictions compared to linear and nonlinear least squares methods and is capable of generating detailed forecasts suitable for the use by decision makers.
ISSN:0196-2892
1558-0644
DOI:10.1109/TGRS.2018.2865429