Abstract
To improve coastal adaptation and management, it is critical to better understand and predict the characteristics of sea levels. Here, we explore the capabilities of artificial intelligence, from four deep learning methods to predict the surge component of sea-level variability based on local atmospheric conditions. We use an Artificial Neural Networks, Convolutional Neural Network, Long Short-Term Memory layer (LSTM) and a combination of the latter two (ConvLSTM), to construct ensembles of Neural Network (NN) models at 736 tide stations globally. The NN models show similar patterns of performance, with much higher skill in the mid-latitudes. Using our global model settings, the LSTM generally outperforms the other NN models. Furthermore, for 15 stations we assess the influence of adding complexity more predictor variables. This generally improves model performance but leads to substantial increases in computation time. The improvement in performance remains insufficient to fully capture observed dynamics in some regions. For example, in the tropics only modelling surges is insufficient to capture intra-annual sea level variability. While we focus on minimising mean absolute error for the full time series, the NN models presented here could be adapted for use in forecasting extreme sea levels or emergency response.
Highlights
At ungauged locations, applying such methods can lead to similar or better results than local hydrodynamic models
A positive CRPSS indicates that the NN model has better predictive skill compared to our reference model, i.e. the probabilistic climatology ensemble
For the first time, a quantitative assessment of the role of the network complexity, the number of predictor variables considered and the spatial extent considered around each location with respect to the model performance
Summary
At ungauged locations, applying such methods can lead to similar or better results than local hydrodynamic models. Bruneau et al.[11] were, to our knowledge, the first to use ANN models to predict hourly non-tidal residual levels at tide stations. They used as predictor variables wind, mean sea level pressure, accumulated precipitation, and wave height from the climate reanalysis dataset E RA528. Notwithstanding the differences between the models applied in Tadesse et al.[10] and Bruneau et al.[11], the role of the number of predictor variables considered and the spatial extent around each location in the model’s performance and ability to learn remains unclear. We show the capability of the four NN types to gain skill when adding complexity to their respective network architecture
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
