Gaussian Process Regression for Arctic Coastal Erosion Forecasting

Kupilik, Matthew; Witmer, Frank D. W.; MacLeod, Euan-Angus; Wang, Caixia; Ravens, Thomas M.

doi:10.1109/tgrs.2018.2865429

Cited by 14 publications

(12 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In general, however, next to OLS, machine learning methods are used much less frequently in this forecast model category. Of the 22 projection-based forecasting studies identified in this review, 15 were based on climate projections [78,85,130,131,134,142,[154][155][156][168][169][170]175,177,178], six on LULC projections [65,143,144,157,158,167], and one study on both [118].…”

Section: Categorization Of Forecasting Methodsmentioning

confidence: 99%

Forecasting Spatio-Temporal Dynamics on the Land Surface Using Earth Observation Data—A Review

Koehler

Kuenzer

2020

Remote Sensing

View full text Add to dashboard Cite

Reliable forecasts on the impacts of global change on the land surface are vital to inform the actions of policy and decision makers to mitigate consequences and secure livelihoods. Geospatial Earth Observation (EO) data from remote sensing satellites has been collected continuously for 40 years and has the potential to facilitate the spatio-temporal forecasting of land surface dynamics. In this review we compiled 143 papers on EO-based forecasting of all aspects of the land surface published in 16 high-ranking remote sensing journals within the past decade. We analyzed the literature regarding research focus, the spatial scope of the study, the forecasting method applied, as well as the temporal and technical properties of the input data. We categorized the identified forecasting methods according to their temporal forecasting mechanism and the type of input data. Time-lagged regressions which are predominantly used for crop yield forecasting and approaches based on Markov Chains for future land use and land cover simulation are the most established methods. The use of external climate projections allows the forecasting of numerical land surface parameters up to one hundred years into the future, while auto-regressive time series modeling can account for intra-annual variances. Machine learning methods have been increasingly used in all categories and multivariate modeling that integrates multiple data sources appears to be more popular than univariate auto-regressive modeling despite the availability of continuously expanding time series data. Regardless of the method, reliable EO-based forecasting requires high-level remote sensing data products and the resulting computational demand appears to be the main reason that most forecasts are conducted only on a local scale. In the upcoming years, however, we expect this to change with further advances in the field of machine learning, the publication of new global datasets, and the further establishment of cloud computing for data processing.

show abstract

Section: Categorization Of Forecasting Methodsmentioning

confidence: 99%

Forecasting Spatio-Temporal Dynamics on the Land Surface Using Earth Observation Data—A Review

Koehler

Kuenzer

2020

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…While the mean predictions from the GP predictor developed in this study using high-resolution lidar data of wave runup were accurate (RMSE = 0.18 m) and better than those provided by the Stockdon et al (2006) formula tested on the same data (RMSE = 0.36 m), the key advantage of the GP approach over deterministic approaches is that probabilistic predictions are output that is specifically derived from data and implicitly accounts for unresolved processes and uncertainty in runup predictions. Previous work has similarly used GPs for efficiently and accurately quantifying uncertainty in other environmental applications (e.g., Holman et al, 2014;Kupilik et al, 2018;Reggente et al, 2014). While alternative approaches are available for generating probabilistic predictions, such as Monte Carlo simulations (e.g., Callaghan et al, 2013), the GP approach offers a method of deriving uncertainty explicitly from data, requires no deterministic equations, and is computationally efficient (i.e., as discussed in Sect.…”

Section: Runup Predictorsmentioning

confidence: 99%

“…While many machine-learning algorithms and applications are often used to optimize deterministic predictions, a Gaussian process is a probabilistic machine-learning technique that directly captures model uncertainty from data (Rasmussen and Williams, 2006). Recent work has specif-ically used Gaussian processes to model coastal processes such as large-scale coastline erosion (Kupilik et al, 2018) and estuarine hydrodynamics (Parker et al, 2019).…”

mentioning

confidence: 99%

Ensemble models from machine learning: an example of wave runup and coastal dune erosion

Beuzen

Goldstein

Splinter

2019

Nat. Hazards Earth Syst. Sci.

View full text Add to dashboard Cite

Abstract. After decades of study and significant data collection of time-varying swash on sandy beaches, there is no single deterministic prediction scheme for wave runup that eliminates prediction error – even bespoke, locally tuned predictors present scatter when compared to observations. Scatter in runup prediction is meaningful and can be used to create probabilistic predictions of runup for a given wave climate and beach slope. This contribution demonstrates this using a data-driven Gaussian process predictor; a probabilistic machine-learning technique. The runup predictor is developed using 1 year of hourly wave runup data (8328 observations) collected by a fixed lidar at Narrabeen Beach, Sydney, Australia. The Gaussian process predictor accurately predicts hourly wave runup elevation when tested on unseen data with a root-mean-squared error of 0.18 m and bias of 0.02 m. The uncertainty estimates output from the probabilistic GP predictor are then used practically in a deterministic numerical model of coastal dune erosion, which relies on a parameterization of wave runup, to generate ensemble predictions. When applied to a dataset of dune erosion caused by a storm event that impacted Narrabeen Beach in 2011, the ensemble approach reproduced ∼85 % of the observed variability in dune erosion along the 3.5 km beach and provided clear uncertainty estimates around these predictions. This work demonstrates how data-driven methods can be used with traditional deterministic models to develop ensemble predictions that provide more information and greater forecasting skill when compared to a single model using a deterministic parameterization – an idea that could be applied more generally to other numerical models of geomorphic systems.

show abstract

“…While the mean predictions from the GP predictor developed in this study using high-resolution LIDAR data of wave runup were accurate (RMSE = 0.18 m) and better than those provided by the Stockdon et al (2006) formula tested on the same data (RMSE = 0.36 m), the key advantage of the GP approach over deterministic approaches is that probabilistic predictions are output that are specifically derived from data and implicitly account for unresolved processes and uncertainty in runup predictions. Previous work has similarly used GPs for efficiently and accurately quantifying uncertainty in other environmental applications (e.g., Holman et al, 2014;Kupilik et al, 2018;Reggente et al, 2014). While alternative approaches are available for generating probabilistic predictions, such as Monte Carlo simulations (e.g., Callaghan et al, 2013), the GP approach explicitly derives uncertainty from data, requires no deterministic equations, and is computationally efficient (i.e.,…”

Section: Runup Predictorsmentioning

confidence: 99%

“…While many machine learning algorithms and applications are often used to optimize deterministic predictions, a Gaussian process is a probabilistic machine learning technique that directly captures model uncertainty from data (Rasmussen and Williams, 2006). Recent work has specifically used Gaussian processes to understand coastal processes such as large scale coastline erosion (Kupilik et al, 2018). Nat.…”

Section: Introductionmentioning

confidence: 99%

Ensemble models from machine learning: an example of wave runup and coastal dune erosion

Beuzen¹,

Goldstein²,

Splinter³

2019

Preprint

View full text Add to dashboard Cite

Abstract. After decades of study and significant data collection of time-varying swash on sandy beaches, there is no single deterministic prediction scheme for wave runup that eliminates prediction error – even bespoke, locally tuned predictors present scatter when compared to observations. Scatter in runup prediction is meaningful and can be used to create probabilistic predictions of runup for a given wave climate and beach slope. This contribution demonstrates this using a data-driven Gaussian process predictor; a probabilistic machine learning technique. The runup predictor is developed using one year of hourly wave runup data (8328 observations) collected by a fixed LIDAR at Narrabeen Beach, Sydney, Australia. The Gaussian process predictor accurately predicts hourly wave runup elevation when tested on unseen data with a root mean-squared-error of 0.18 m and bias of 0.02 m. The uncertainty estimates output from the probabilistic GP predictor are then used practically in a deterministic numerical model of coastal dune erosion, which relies on a parameterization of wave runup, to generate ensemble predictions. When applied to a dataset of dune erosion caused by a storm event that impacted Narrabeen Beach in 2011, the ensemble approach reproduced ~ 85 % of the observed variability in dune erosion along the 3.5 km beach and provided clear uncertainty estimates around these predictions. This work demonstrates how data-driven methods can be used with traditional deterministic models to develop ensemble predictions that provide more information and greater forecasting skill when compared to a single model using a deterministic parameterization; an idea that could be applied more generally to other numerical models of geomorphic systems.

show abstract

Gaussian Process Regression for Arctic Coastal Erosion Forecasting

Cited by 14 publications

References 23 publications

Forecasting Spatio-Temporal Dynamics on the Land Surface Using Earth Observation Data—A Review

Forecasting Spatio-Temporal Dynamics on the Land Surface Using Earth Observation Data—A Review

Ensemble models from machine learning: an example of wave runup and coastal dune erosion

Ensemble models from machine learning: an example of wave runup and coastal dune erosion

Contact Info

Product

Resources

About