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.


Title: Application of Neural Networks for Hydrologic Process Understanding at a Midwestern Watershed
The Shell Creek Watershed (SCW) is a rural watershed in Nebraska with a history of chronic flooding. Beginning in 2005, a variety of conservation practices have been employed in the watershed. Those practices have since been credited with attenuating flood severity and improving water quality in SCW. This study investigated the impacts of 13 different controlling factors on flooding at SCW by using an artificial neural network (ANN)-based rainfall-runoff model. Additionally, flood frequency analysis and drought severity analysis were conducted. Special emphasis was placed on understanding how flood trends change in light of conservation practices to determine whether any relation exists between the conservation practices and flood peak attenuation, as the strategic conservation plan implemented in the watershed provides a unique opportunity to examine the potential impacts of conservation practices on the watershed. The ANN model developed in this study showed satisfactory discharge–prediction performance, with a Kling–Gupta Efficiency (KGE) value of 0.57. It was found that no individual controlling variable used in this study was a significantly better predictor of flooding in SCW, and therefore all 13 variables were used as inputs, which resulted in the satisfactory ANN model discharge–prediction performance. Furthermore, it was observed that after conservation planning was implemented in SCW, the magnitude of anomalous peak flows increased, while the magnitude of annual peak flows decreased. However, more comprehensive assessment is necessary to identify the relative impacts of conservation practices on flooding in the basin.  more » « less
Award ID(s):
1950597
PAR ID:
10398293
Author(s) / Creator(s):
; ; ; ; ;
Date Published:
Journal Name:
Hydrology
Volume:
10
Issue:
2
ISSN:
2306-5338
Page Range / eLocation ID:
27
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. null (Ed.)
    Las Vegas valley has undergone significant development, thus increasing urban flooding. This study analyzes the impacts of urban development on urban flooding in the Flamingo watershed by using a watershed model. The input data includes precipitation, soil characteristics, elevation, and land cover. Urban development is incorporated through increasing percent impervious. Sub-watersheds and streamlines were delineated in ArcGIS using digital elevation model (DEM) dataset. Natural Resources Conservation Service (NRCS) curve-number method was used for the calculation of runoff. The Hydrologic Engineering Center-Hydrologic Management System (HEC-HMS) was used to estimate the discharge hydrograph. The model was calibrated through changing the curve number of the sub-basins. Two urbanization scenarios created with a 5% and 10% increase in impervious surfaces were generated. The results showed that peak discharge occurred earlier due to increase in impervious surfaces. Moreover, the total discharge volume and peak discharge for a given storm event were increasing due to increased imperviousness from urbanization. This study provides useful insight into a hydrological response to urban development that can be helpful in flood remediation. 
    more » « less
  2. null (Ed.)
    Flooding during extreme weather events damages critical infrastructure, property, and threatens lives. Hurricane María devastated Puerto Rico (PR) on 20 September 2017. Sixty-four deaths were directly attributable to the flooding. This paper describes the development of a hydrologic model using the Gridded Surface Subsurface Hydrologic Analysis (GSSHA), capable of simulating flood depth and extent for the Añasco coastal flood plain in Western PR. The purpose of the study was to develop a numerical model to simulate flooding from extreme weather events and to evaluate the impacts on critical infrastructure and communities; Hurricane María is used as a case study. GSSHA was calibrated for Irma, a Category 3 hurricane, which struck the northeastern corner of the island on 7 September 2017, two weeks before Hurricane María. The upper Añasco watershed was calibrated using United States Geological Survey (USGS) stream discharge data. The model was validated using a storm of similar magnitude on 11–13 December 2007. Owing to the damage sustained by PR’s WSR-88D weather radar during Hurricane María, rainfall was estimated in this study using the Weather Research Forecast (WRF) model. Flooding in the coastal floodplain during Hurricane María was simulated using three methods: (1) Use of observed discharge hydrograph from the upper watershed as an inflow boundary condition for the coastal floodplain area, along with the WRF rainfall in the coastal flood plain; (2) Use of WRF rainfall to simulate runoff in the upper watershed and coastal flood plain; and (3) Similar to approach (2), except the use of bias-corrected WRF rainfall. Flooding results were compared with forty-two values of flood depth obtained during face-to-face interviews with residents of the affected communities. Impacts on critical infrastructure (water, electric, and public schools) were evaluated, assuming any structure exposed to 20 cm or more of flooding would sustain damage. Calibration equations were also used to improve flood depth estimates. Our model included the influence of storm surge, which we found to have a minimal effect on flood depths within the study area. Water infrastructure was more severely impacted by flooding than electrical infrastructure. From these findings, we conclude that the model developed in this study can be used with sufficient accuracy to identify infrastructure affected by future flooding events. 
    more » « less
  3. null (Ed.)
    Compound flooding is a physical phenomenon that has become more destructive in recent years. Moreover, compound flooding is a broad term that envelops many different physical processes that can range from preconditioned, to multivariate, to temporally compounding, or spatially compounding. This research aims to analyze a specific case of compound flooding related to tropical cyclones where the compounding effect is on coastal flooding due to a combination of storm surge and river discharge. In recent years, such compound flood events have increased in frequency and magnitude, due to a number of factors such as sea-level rise from warming oceans. Therefore, the ability to model such events is of increasing urgency. At present, there is no holistic, integrated modeling system capable of simulating or forecasting compound flooding on a large regional or global scale, leading to the need to couple various existing models. More specifically, two more challenges in such a modeling effort are determining the primary model and accounting for the effect of adjacent watersheds that discharge to the same receiving water body in amplifying the impact of compound flooding from riverine discharge with storm surge when the scale of the model includes an entire coastal line. In this study, we investigated the possibility of using the Advanced Circulation (ADCIRC) model as the primary model to simulate the compounding effects of fluvial flooding and storm surge via loose one-way coupling with gage data through internal time-dependent flux boundary conditions. The performance of the ADCIRC model was compared with the Hydrologic Engineering Center- River Analysis System (HEC-RAS) model both at the watershed and global scales. Furthermore, the importance of including riverine discharges and the interactions among adjacent watersheds were quantified. Results showed that the ADCIRC model could reliably be used to model compound flooding on both a watershed scale and a regional scale. Moreover, accounting for the interaction of river discharge from multiple watersheds is critical in accurately predicting flood patterns when high amounts of riverine flow occur in conjunction with storm surge. Particularly, with storms such as Hurricane Harvey (2017), where river flows were near record levels, inundation patterns and water surface elevations were highly dependent on the incorporation of the discharge input from multiple watersheds. Such an effect caused extra and longer inundations in some areas during Hurricane Harvey. Comparisons with real gauge data show that adding internal flow boundary conditions into ADCIRC to account for river discharge from multiple watersheds significantly improves accuracy in predictions of water surface elevations during coastal flooding events. 
    more » « less
  4. From June 10-13 of 2022, an atmospheric river delivered heavy rain to high elevations around northern Yellowstone National Park (YNP), resulting in extreme flooding in the Yellowstone River basin below Yellowstone Lake. The extreme 2022 flood was only one of several historical events caused by high June temperatures and rapid snowmelt, with a variable component of rain on snow. Large and extreme floods on the Yellowstone River (YR) also occurred in June 1996 and 1918, allowing comparison of their magnitude, duration, and mechanisms of generation for the YR and its Lamar River and Soda Butte Creek tributaries. In 2022, peak discharge on the YR at Corwin Springs was 1550 m3/s, the flood of record and 170% of the 1996 peak, and Lamar River peak discharge was 172% of 1996 peak. In 1918, gaged discharge is only available for the YR at Corwin Springs, with significant uncertainty. On Soda Butte Creek, however, overbank gravels and indirect discharge estimates indicate that the 1918 peak discharge was conservatively 240% higher than 1996 and 127% higher than 2022. In 2022, flood duration above 700 m3/s at the YR Corwin Springs gage was only 2 days, compared to 9 days in 1996 and 14 days in 1918. In early June 1918 and 1996, snowpack was above average, and anomalously warm weather combined with relatively minor rainfall to produce long-duration flooding. In early June 2022, similarly high temperatures occurred, but snowpack was less than in 1918; early May snowpack in 2022 was 64% that of 1996. The June 10-13 atmospheric river released 5-10 cm of rain across northern YNP that added to snowmelt, producing a short duration but extremely high peak discharge. The 2022 flood caused major bank erosion especially in confined reaches but resulted in less floodplain disruption and overbank gravel deposition than in 1918 on the Lamar River and Soda Butte Creek. The potential exists for an even larger peak discharge than in 2022 if atmospheric river rainfall as in 2022 is superimposed on rapid melting of a deep snowpack, caused by the kind of unseasonable warmth that occurred in 1997 and 1918. Anthropogenic climate change is likely to increase the probability of extreme floods in YNP, as higher temperatures increase snowmelt rates, shift late-spring precipitation from snow to rain, and promote widespread intense rainfall including that from atmospheric rivers. 
    more » « less
  5. In June of 2022 an extreme atmospheric river flood caused extensive bank erosion and infrastructure damage in northern Yellowstone National Park (YNP). On the lower Lamar River, peak discharge was 170% of the next highest peak of 1996 (gaged since 1923) and resulted in widespread overbank gravel deposition and channel change. In June 1918, however, flooding on the Lamar system produced similar peak flows, as shown by indirect discharge estimates and tree-ring dating. In 2022, peak discharges and flood effects varied considerably in northern YNP. The upper Lamar River had a peak discharge significantly less than 1918, likely the result of less precipitation and snowmelt in the relatively low elevations of the upper Lamar drainage in the Absaroka Range. The high flows experienced by the lower Lamar River, however, were the result of extreme discharges in tributaries that drain the Beartooth Range where Soda Butte Creek and Pebble Creek had discharges similar or greater than 1918 and discharge on Slough Creek produced extensive mid channel bar deposition greater than 2 m. In western YNP, the Gallatin River experienced little bank erosion or bed material transport, although some reaches showed minor channel scour and gravel bar deposition on glacial outwash substrates. In central YNP, the Gardiner River experienced minimal bank erosion on upper reaches, however, there was extensive bank erosion, landslides, and sediment deposition in the Gardner River Canyon where the steep, confined channel focused stream power along the valley margins. Flood magnitudes differed markedly between the Gallatin and Beartooth drainages despite similar amounts of rainfall and snowmelt. The Gallatin River drainage, dominated by highly fractured and macroporous limestone and extensive thick colluvium with gentler range flanks allows for greater infiltration and reduced peak flows. In contrast, basins in the Beartooth Range drain steeper slopes of low-permeability laharic volcaniclastic rocks, with more exposed bedrock and relief up to 900 m, which promotes rapid runoff and extreme flooding. The frequency and magnitude of rain-on-snow floods is likely increasing in YNP because of anthropogenic warming, as the high-elevation snowpack becomes more susceptible to rapid melting and late spring precipitation shifts from snow to rain. 
    more » « less