skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: A deep-learning model for rapid spatiotemporal prediction of coastal water levels
With the increasing impact of climate change and relative sea level rise, low-lying coastal communities face growing risks from recurrent nuisance flooding and storm tides. Thus, timely and reliable predictions of coastal water levels are critical to resilience in vulnerable coastal areas. Over the past decade, there has been increasing interest in utilizing machine learning (ML) based models for emulation and prediction of coastal water levels. However, flood advisory systems still rely on running computationally demanding hydrodynamic models. To alleviate the computational burden, these physics-based models are either run at small scales with high resolution or at large scales with low resolution. While ML-based models are very fast, they face challenges in terms of ensuring reliability and ability to capture any surge levels. In this paper, we develop a deep neural network for spatiotemporal prediction of water levels in coastal areas of the Chesapeake Bay in the U.S. 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 across the Chesapeake Bay. We utilized a CNN-LSTM setting as the architecture of the model. The CNN part extracts the features from a 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. The novel contribution of the present work is in spatiotemporality and in prioritization of the physical relationships in the model to maintain a high analogy to hydrodynamic modeling, either in the network architecture or in the selection of predictors and predictands. The results show that this setting yields a strong performance in predicting coastal water levels that cause flooding from minor to major levels. We also show that the model stands up successfully to the rigorous comparison with a high-fidelity ADCIRC model, yielding mean RMSE and correlation coefficient of 14.3 cm and 0.94, respectively, in two extreme cases, versus 12.30 cm and 0.96 for the ADCIRC model. The results highlight the practical feasibility of employing fast yet inexpensive data-driven models for resilient coastal management.  more » « less
Award ID(s):
1951745
PAR ID:
10529651
Author(s) / Creator(s):
;
Publisher / Repository:
Elsevier
Date Published:
Journal Name:
Coastal Engineering
Volume:
190
Issue:
C
ISSN:
0378-3839
Page Range / eLocation ID:
104504
Subject(s) / Keyword(s):
Storm surge prediction Nuisance flooding Machine learning Deep learning CNN LSTM
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; (, Frontiers in Climate)
    Extreme storm surges can overwhelm many coastal flooding protection measures in place and cause severe damages to private communities, public infrastructure, and natural ecosystems. In the US Mid-Atlantic, a highly developed and commercially active region, coastal flooding is one of the most significant natural hazards and a year-round threat from both tropical and extra-tropical cyclones. Mean sea levels and high-tide flood frequency has increased significantly in recent years, and major storms are projected to increase into the foreseeable future. We estimate extreme surges using hourly water level data and harmonic analysis for 1980–2019 at 12 NOAA tide gauges in and around the Delaware and Chesapeake Bays. Return levels (RLs) are computed for 1.1, 3, 5, 10, 25, 50, and 100-year return periods using stationary extreme value analysis on detrended skew surges. Two traditional approaches are investigated, Block Maxima fit to General Extreme Value distribution and Points-Over-Threshold fit to Generalized Pareto distribution, although with two important enhancements. First, the GEV r -largest order statistics distribution is used; a modified version of the GEV distribution that allows for multiple maximum values per year. Second, a systematic procedure is used to select the optimum value for r (for the BM/GEVr approach) and the threshold (for the POT/GP approach) at each tide gauge separately. RLs have similar magnitudes and spatial patterns from both methods, with BM/GEVr resulting in generally larger 100-year and smaller 1.1-year RLs. Maximum values are found at the Lewes (Delaware Bay) and Sewells Point (Chesapeake Bay) tide gauges, both located in the southwest region of their respective bays. Minimum values are found toward the central bay regions. In the Delaware Bay, the POT/GP approach is consistent and results in narrower uncertainty bands whereas the results are mixed for the Chesapeake. Results from this study aim to increase reliability of projections of extreme water levels due to extreme storms and ultimately help in long-term planning of mitigation and implementation of adaptation measures. 
    more » « less
  2. ; ; (, Frontiers in Climate)
    Coastal flooding poses the greatest threat to human life and is often the most common source of damage from coastal storms. From 1980 to 2020, the top 6, and 17 of the top 25, costliest natural disasters in the U.S. were caused by coastal storms, most of these tropical systems. The Delaware and Chesapeake Bays, two of the largest and most densely populated estuaries in the U.S. located in the Mid-Atlantic coastal region, have been significantly impacted by strong tropical cyclones in recent decades, notably Hurricanes Isabel (2003), Irene (2011), and Sandy (2012). Current scenarios of future climate project an increase in major hurricanes and the continued rise of sea levels, amplifying coastal flooding threat. We look at all North Atlantic tropical cyclones (TC) in the International Best Track Archive for Climate Stewardship (IBTrACS) database that came within 750 km of the Delmarva Peninsula from 1980 to 2019. For each TC, skew surge and storm tide are computed at 12 NOAA tide gauges throughout the two bays. Spatial variability of the detrended and normalized skew surge is investigated through cross-correlations, regional storm rankings, and comparison to storm tracks. We find Hurricanes Sandy (2012) and Isabel (2003) had the largest surge impact on the Delaware and Chesapeake Bay, respectively. Surge response to TCs in upper and lower bay regions are more similar across bays than to the opposing region in their own bay. TCs that impacted lower bay more than upper bay regions tended to stay offshore east of Delmarva, whereas TCs that impacted upper bay regions tended to stay to the west of Delmarva. Although tropical cyclones are multi-hazard weather events, there continues to be a need to improve storm surge forecasting and implement strategies to minimize the damage of coastal flooding. Results from this analysis can provide insight on the potential regional impacts of coastal flooding from tropical cyclones in the Mid-Atlantic. 
    more » « less
  3. ; ; (, Journal of Applied Meteorology and Climatology)
    Abstract Coastal flooding is one of the most costly and deadly natural hazards facing the U.S. mid-Atlantic region today. Impacts in this heavily populated and economically significant region are caused by a combination of the location’s exposure and natural forcing from storms and sea level rise. Tropical cyclones (TCs) and midlatitude (ML) weather systems each have caused extreme coastal flooding in the region. Skew surge was computed over each tidal cycle for the past 40 years (1980–2019) at several tide gauges in the Delaware and Chesapeake Bays to compare the meteorological component of surge for each weather type. Although TCs cause higher mean surges, ML weather systems can produce surges just as severe and occur much more frequently, peaking in the cold season (November–March). Of the top 10 largest surge events, TCs account for 30%–45% in the Delaware and upper Chesapeake Bays and 40%–45% in the lower Chesapeake Bay. This percentage drops to 10%–15% for larger numbers of events in all regions. Mean sea level pressure and 500-hPa geopotential height (GPH) fields of the top 10 surge events from ML weather systems show a low pressure center west-southwest of “Delmarva” and a semistationary high pressure center to the northeast prior to maximum surge, producing strong easterly winds. Low pressure centers intensify under upper-level divergence as they travel eastward, and the high pressure centers are near the GPH ridges. During lower-bay events, the low pressure centers develop farther south, intensifying over warmer coastal waters, with a south-shifted GPH pattern relative to upper-bay events. Significance Statement Severe coastal flooding is a year-round threat in the U.S. mid-Atlantic region, and impacts are projected to increase in magnitude and frequency. Research into the meteorological contribution to storm surge, separate from mean sea level and tidal phase, will increase the scientific understanding and monitoring of changing atmospheric conditions. Tropical cyclones and midlatitude weather systems both significantly impact the mid-Atlantic region during different times of year. However, climate change may alter the future behavior of these systems differently. Understanding the synoptic environment and quantifying the surge response and subbay geographic variability of each weather system in this region will aid in public awareness, near-term emergency preparation, and long-term planning for coastal storms. 
    more » « less
  4. ; ; ; ; ; ; ; ; ; (, Journal of Advances in Modeling Earth Systems)
    Abstract This study showcases a global, heterogeneously coupled total water level system wherein salinity and temperature outputs from a coarser‐resolution (12 km) ocean general circulation model are used to calculate density‐driven terms within a global, higher‐resolution (2.5 km) depth‐averaged total water level model. We demonstrate that the inclusion of baroclinic forcing in the barotropic model requires modification of the internal wave drag term to prevent excess degradation of tidal results compared to the barotropic model. By scaling the internal tide dissipation by an easy to calculate dissipation ratio, the resulting heterogeneously coupled model has complex root mean square errors (RMSE) of 2.27 cm in the deep ocean and 12.16 cm in shallow waters for the tidal constituent. While this represents a 10%–20% deterioration as compared to the barotropic model, the improvements in total water level prediction more than offset this degradation. Global median RMSE compared to observations of total water levels, 30‐day sea levels, and non‐tidal residuals improve by 1.86 (18.5%), 2.55 (42.5%), and 0.36 (5.3%) cm respectively. The drastic improvement in model performance highlights the importance of including density‐driven effects within global hydrodynamic models and will help to improve the results of both hindcasts and forecasts in modeling extreme and nuisance flooding. With only an 11% increase in model run time compared to the fully barotropic total water level model, this approach paves the way for high resolution coastal water level and flood models to be used alongside climate models, improving operational forecasting of total water levels. 
    more » « less
  5. ; ; ; (, NSF Arctic Data Center)
    As part of NSF Project 1848542, we assessed the impacts of Bering Sea storms on western Alaskan communities, focusing on Goodnews Bay and St. Paul Island. Field campaigns collected high-resolution coastal datasets to document storm-driven flooding and shoreline change. Cross-shore profiles were surveyed using a Trimble real-time kinematic global navigation satellite system (RTK-GNSS), extending from upland features to the waterline and repeated over time to capture coastal change. High-water marks (HWMs) were also recorded, providing elevation data for present and historic flooding events, including detailed measurements of Typhoon Merbok impacts in 2022. Indicators such as debris lines, seed lines, foam lines, and wet/dry lines were used to approximate total water levels, which integrate astronomical tide, storm surge, and wave runup. This dataset contains supporting tables and measurements from these surveys, which complement a broader assessment of storm flooding impacts on regional infrastructure. We encourage researchers to contact us with questions or requests for additional data. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email