An official website of the United States government
Abstract Compound floods are often thought of as large, infrequent floods during which extremes of coastal sea level and/or river flow combine with each other or additional factors (e.g., tides and rainfall) to induce major flooding. However, little is known about the potentially compound nature of more frequent, lower‐level floods. Here, we introduce the term “compound minor floods” to define minor floods composed of two or more water‐level sources. We use the Delaware River Estuary as a case study to investigate the prevalence and composition of these minor compound floods along the extent of a tidal river. We apply multiple linear regression to a 22‐year time series of coastal water levels and river discharge to establish the contributions of tides, nontidal open‐ocean effects, and river discharge to minor flood events at eight locations along the tidal Delaware River. We find that most minor flood events are compound in nature, requiring at least two components (e.g., tides and river discharge) to initiate flooding. We identify spatial structure in the relative importance of oceanographic and riverine contributions to minor flooding along the tidal reach of the estuary. These results suggest that incorporating fluvial components into minor flooding assessments is important to fully characterize flood risk along tidal rivers and estuaries.
more »
« less
This content will become publicly available on April 11, 2026
FIDLAR: Forecast-Informed Deep Learning Architecture for Flood Mitigation
In coastal river systems, floods, often during major storms or king tides, severely threaten lives and property. However, hydraulic structures such as dams, gates, pumps, and reservoirs exist in these river systems, and these floods can be mitigated or even prevented by strategically releasing water before extreme weather events. A standard approach used by local water management agencies is the “rule-based” method, which specifies predetermined water prereleases based on historical human experience, but which tends to result in excessive or inadequate water release. Iterative optimization methods that rely on detailed physics-based models for prediction are an alternative approach. Whereas, such methods tend to be computationally intensive, requiring hours or even days to solve the problem optimally. In this paper, we propose a Forecast Informed Deep Learning Architecture, FIDLAR, to achieve rapid and near-optimal flood management with precise water prereleases. FIDLAR seamlessly integrates two neural network modules: one called the Flood Manager, which is responsible for generating water pre-release schedules, and another called the Flood Evaluator, which evaluates those generated schedules. The Evaluator module is pre-trained separately, and its gradient-based feedback is utilized to train the Manager model, ensuring near-optimal water pre-releases. We have conducted experiments with a flood-prone coastal area in South Florida. Results show that FIDLAR is several orders of magnitude faster than currently used physics-based approaches while outperforming baseline methods with improved water pre-release schedules.
more »
« less
- Award ID(s):
- 2118329
- PAR ID:
- 10637210
- Publisher / Repository:
- PKP Publishing Services Network
- Date Published:
- Journal Name:
- Proceedings of the AAAI Conference on Artificial Intelligence
- Volume:
- 39
- Issue:
- 27
- ISSN:
- 2159-5399
- Page Range / eLocation ID:
- 28377 to 28385
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract Compound flooding, characterized by the co‐occurrence of multiple flood mechanisms, is a major threat to coastlines across the globe. Tropical cyclones (TCs) are responsible for many compound floods due to their storm surge and intense rainfall. Previous efforts to quantify compound flood hazard have typically adopted statistical approaches that may be unable to fully capture spatio‐temporal dynamics between rainfall‐runoff and storm surge, which ultimately impact total water levels. In contrast, we pose a physics‐driven approach that utilizes a large set of realistic TC events and a simplified physics‐based rainfall model and simulates each event within a hydrodynamic model framework. We apply our approach to investigate TC flooding in the Cape Fear River, NC. We find TC approach angle, forward speed, and intensity are relevant for compound flood potential, but rainfall rate and time lag between the centroid of rainfall and peak storm tide are the strongest predictors of compounding magnitude. Neglecting rainfall underestimates 100‐year flood depths across 28% of the floodplain, and taking the maximum of each hazard modeled separately still underestimates 16% of the floodplain. We find the main stem of the river is surge‐dominated, upstream portions of small streams and pluvial areas are rainfall dominated, but midstream portions of streams are compounding zones, and areas close to the coastline are surge dominated for lower return periods but compounding zones for high return periods (100 years). Our method links joint rainfall‐surge occurrence to actual flood impacts and demonstrates how compound flooding is distributed across coastal catchments.more » « less
-
Inundation mapping is a critical task for damage assessment, emergency management, and prioritizing relief efforts during a flooding event. Remote sensing has been an effective tool for interpreting and analyzing water bodies and detecting floods over the past decades. In recent years, deep learning algorithms such as convolutional neural networks (CNNs) have demonstrated promising performance for remote sensing image classification for many applications, including inundation mapping. Unlike conventional algorithms, deep learning can learn features automatically from large datasets. This research aims to compare and investigate the performance of two state-of-the-art methods for 3D inundation mapping: a deep learning-based image analysis and a Geomorphic Flood Index (GFI). The first method, deep learning image analysis involves three steps: 1) image classification to delineate flood boundaries, 2) integrate the flood boundaries and topography data to create a three-dimensional (3D) water surface, and 3) compare the 3D water surface with pre-flood topography to estimate floodwater depth. The second method, i.e., GFI, involves three phases: 1) calculate a river basin morphological information, such as river height (hr) and elevation difference (H), 2) calibrate and measure GFI to delineate flood boundaries, and 3) calculate the coefficient parameter ( α ), and correct the value of hr to estimate inundation depth. The methods were implemented to generate 3D inundation maps over Princeville, North Carolina, United States during hurricane Matthew in 2016. The deep learning method demonstrated better performance with a root mean square error (RMSE) of 0.26 m for water depth. It also achieved about 98% in delineating the flood boundaries using UAV imagery. This approach is efficient in extracting and creating a 3D flood extent map at a different scale to support emergency response and recovery activities during a flood event.more » « less
-
Abstract Natural levees form through sediment delivery from channels, dispersal onto floodplains, and storage at channel margins. When levees breach, they release water and sediment onto the floodplain, occasionally causing river avulsions. Despite their significance, levee growth remains poorly understood, and no existing models capture the dynamic channel‐levee evolution systems. A common assumption is that levee and channel bed aggradation rates are coupled or equal; however, this cannot be true because levees do not accumulate everywhere along aggrading channel belts. Using a one‐dimensional numerical model, we investigate levee growth decoupled from channel bed aggradation under flood scenarios wherein the flooded level: (a) exceeds the levee crest height (i.e., front loading); or (b) is lower than the levee crest partially inundating distal levee deposits (i.e., back loading). Front loading events initially aggrade the levee crest, which confines the channel, increases bankfull depth, and reduces flooding. During confinement, levee growth restricts flooding, and minor back loading events are more common. Over this period, the channel bed aggrades until bankfull depth decreases sufficiently to trigger larger floods. This channel‐releasing process increases flood likelihood and enhances overbank accumulation, promoting front loading and re‐confining the channel. Our findings suggest aggradational channels may experience confined‐release phases characterized by episodic levee growth and fluctuating bankfull depth. Rapid in‐channel aggradation increases flood frequency and variability with more confined‐release cycles. These results imply that river avulsions and associated floods might preferentially occur when the channel bed aggrades faster than adjacent levees, whereby the channel becomes shallower and destabilized.more » « less
-
ABSTRACT The Northeast United States exhibits significant spatial heterogeneity in flood seasonality, with spring snowmelt‐driven floods historically dominating northern areas, while other regions show more varied flood seasonality. While it is well documented that since 1996 there has been a marked increase in extreme precipitation across this region, the response of flood seasonality to these changes in extreme precipitation and the spatial distribution of these effects remain uncertain. Here we show that, historically, snowmelt‐dominated northern regions were relatively insensitive to changes in extreme precipitation. However, with climate warming, the dominance of snowmelt floods is decreasing and thus the extreme flood regimes in northern regions are increasingly susceptible to changes in extreme precipitation. While extreme precipitation increased everywhere in the Northeastern United States in 1996, it has since returned to near pre‐1996 levels in the coastal north while remaining elevated in the inland north. Thus, the inland north region has and continues to experience the greatest changes in extreme flooding seasonality, including a substantial rise in floods outside the historical spring flood season, particularly in smaller watersheds. Further analysis reveals that while early winter floods are increasingly common, the magnitude of cold season floods (Nov‐May) have remained unchanged over time. In contrast, warm season floods (June‐Oct), historically less significant, are now increasing in both frequency and magnitude in the inland north. Our results highlight that treating the entire Northeast as a uniform hydroclimatic region conceals significant regional variations in extreme discharge trends and, more generally, climate warming will likely increase the sensitivity of historically snowmelt dominated watersheds to extreme precipitation. Understanding this spatial variability in increased extreme precipitation and increased sensitivity to extreme precipitation is crucial for enhancing disaster preparedness and refining water management strategies in affected regions.more » « less
