College
College of Engineering & Technology (Batten)
Department
Civil & Environmental Engineering
Graduate Level
Doctoral
Presentation Type
Poster Presentation
Abstract
With the increasing impact of climate change and relative sea level rise, low-lying coastal communities face growing risks from extreme storm tides and recurrent nuisance flooding. Thus, timely and reliable predictions of coastal water levels are critical to resilience in vulnerable coastal areas. Over the past decade, enormous efforts have been made to utilize machine learning (ML) based data-driven models for the emulation and prediction of storm tides. However, flood advisory systems still rely on running computationally demanding real-time hydrodynamic models. because developing highly reliable ML-based models suitable for real-time forecasting and capable of capturing any surge levels is challenging. While ML-based models are very fast, challenges lie in ensuring reliability and ability to capture any surge level. In this research, we develop a deep neural network for spatiotemporal prediction of water levels in coastal areas. Our model relies on data from numerical weather prediction models as the atmospheric input and astronomical tide levels, while its outputs are time series of predicted water levels at several tide gauge locations. We utilized a CNN-LSTM setting as the architecture of the model. The CNN part extracts the features from an hourly sequence of gridded wind fields and fuses its output to several independent LSTM units. The LSTM units concatenate the atmospheric features with respective astronomical tide levels and produce water level time series. As an effort to fill a knowledge gap, we prioritized physical relation in the model by maintaining a high analogy to hydrodynamic modeling, either in the network architecture or in the selection of predictors and predictands. The results show that, with an average RMSE of 10.6cm, this setting yields a strong performance in predicting storm tides from minor to major levels.
Keywords
Storm Surge Prediction, Nuisance Flooding, Machine Learning, Deep Learning, CNN, LSTM
Rapid Prediction of Coastal Flooding with Deep Neural Networks
With the increasing impact of climate change and relative sea level rise, low-lying coastal communities face growing risks from extreme storm tides and recurrent nuisance flooding. Thus, timely and reliable predictions of coastal water levels are critical to resilience in vulnerable coastal areas. Over the past decade, enormous efforts have been made to utilize machine learning (ML) based data-driven models for the emulation and prediction of storm tides. However, flood advisory systems still rely on running computationally demanding real-time hydrodynamic models. because developing highly reliable ML-based models suitable for real-time forecasting and capable of capturing any surge levels is challenging. While ML-based models are very fast, challenges lie in ensuring reliability and ability to capture any surge level. In this research, we develop a deep neural network for spatiotemporal prediction of water levels in coastal areas. Our model relies on data from numerical weather prediction models as the atmospheric input and astronomical tide levels, while its outputs are time series of predicted water levels at several tide gauge locations. We utilized a CNN-LSTM setting as the architecture of the model. The CNN part extracts the features from an hourly sequence of gridded wind fields and fuses its output to several independent LSTM units. The LSTM units concatenate the atmospheric features with respective astronomical tide levels and produce water level time series. As an effort to fill a knowledge gap, we prioritized physical relation in the model by maintaining a high analogy to hydrodynamic modeling, either in the network architecture or in the selection of predictors and predictands. The results show that, with an average RMSE of 10.6cm, this setting yields a strong performance in predicting storm tides from minor to major levels.
