Ensemble models from machine learning: an example of wave runup and coastal dune erosion
-
Published:2019-10-22
Issue:10
Volume:19
Page:2295-2309
-
ISSN:1684-9981
-
Container-title:Natural Hazards and Earth System Sciences
-
language:en
-
Short-container-title:Nat. Hazards Earth Syst. Sci.
Author:
Beuzen Tomas, Goldstein Evan B.ORCID, Splinter Kristen D.
Abstract
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.
Funder
Australian Research Council
Publisher
Copernicus GmbH
Subject
General Earth and Planetary Sciences
Reference63 articles.
1. Atkinson, A. L., Power, H. E., Moura, T., Hammond, T., Callaghan, D. P., and
Baldock, T. E.: Assessment of runup predictions by empirical models on non-truncated beaches on the south-east Australian coast, Coast. Eng., 119, 15–31, 2017. 2. Bauer, P., Thorpe, A., and Brunet, G.: The quiet revolution of numerical weather prediction, Nature, 525, 47–55, 2015. 3. Berner, J., Achatz, U., Batté, L., Bengtsson, L., Cámara, A. D. L.,
Christensen, H. M., Colangeli, M., Coleman, D. R., Crommelin, D., Dolaptchiev, S. I., and Franzke, C. L.: Stochastic parameterization: Toward a new view of weather and climate models, B. Am. Meteorol. Soc., 98, 565–588, 2017. 4. Beuzen, T. and Goldstein, E. B.: TomasBeuzen/BeuzenEtAl_2019_NHESS_GP_runup_model: First
release of repo (Version 0.1), Zenodo, https://doi.org/10.5281/zenodo.3401739, 2019. 5. Beuzen, T., Splinter, K. D., Turner, I. L., Harley, M. D., and Marshall, L.: Predicting storm erosion on sandy coastlines using a Bayesian
network, in: Proceedings of Australasian Coasts & Ports: Working with Nature, 21–23 June 2017, Cairns, Australia, 102–108, 2017.
Cited by
26 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
|
|