skip to main content

Title: Data-Driven Flood Alert System (FAS) Using Extreme Gradient Boosting (XGBoost) to Forecast Flood Stages
Heavy rainfall leads to severe flooding problems with catastrophic socio-economic impacts worldwide. Hydrologic forecasting models have been applied to provide alerts of extreme flood events and reduce damage, yet they are still subject to many uncertainties due to the complexity of hydrologic processes and errors in forecasted timing and intensity of the floods. This study demonstrates the efficacy of using eXtreme Gradient Boosting (XGBoost) as a state-of-the-art machine learning (ML) model to forecast gauge stage levels at a 5-min interval with various look-out time windows. A flood alert system (FAS) built upon the XGBoost models is evaluated by two historical flooding events for a flood-prone watershed in Houston, Texas. The predicted stage values from the FAS are compared with observed values with demonstrating good performance by statistical metrics (RMSE and KGE). This study further compares the performance from two scenarios with different input data settings of the FAS: (1) using the data from the gauges within the study area only and (2) including the data from additional gauges outside of the study area. The results suggest that models that use the gauge information within the study area only (Scenario 1) are sufficient and advantageous in terms of their accuracy in more » predicting the arrival times of the floods. One of the benefits of the FAS outlined in this study is that the XGBoost-based FAS can run in a continuous mode to automatically detect floods without requiring an external starting trigger to switch on as usually required by the conventional event-based FAS systems. This paper illustrates a data-driven FAS framework as a prototype that stakeholders can utilize solely based on their gauging information for local flood warning and mitigation practices. « less
; ; ;
Award ID(s):
Publication Date:
Journal Name:
Page Range or eLocation-ID:
Sponsoring Org:
National Science Foundation
More Like this
  1. 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 frommore »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.« less
  2. Abstract

    Flash flooding in the arid/semiarid southwestern United States is frequently associated with convective rainfall during the North American monsoon. In this study, we examine flood-producing storms in central Arizona based on analyses of dense rain gauge observations and stream gauging records as well as North American Regional Reanalysis fields. Our storm catalog consists of 102 storm events during the period of 1988–2014. Synoptic conditions for flood-producing storms are characterized based on principal component analyses. Four dominant synoptic modes are identified, with the first two modes explaining approximately 50% of the variance of the 500-hPa geopotential height. The transitional synoptic pattern from the North American monsoon regime to midlatitude systems is a critical large-scale feature for extreme rainfall and flooding in central Arizona. Contrasting spatial rainfall organizations and storm environment under the four synoptic modes highlights the role of interactions among synoptic conditions, mesoscale processes, and complex terrains in determining space–time variability of convective activities and flash flood hazards in central Arizona. We characterize structure and evolution properties of flood-producing storms based on storm tracking algorithms and 3D radar reflectivity. Fast-moving storm elements can be important ingredients for flash floods in the arid/semiarid southwestern United States. Contrasting storm properties formore »cloudburst storms highlight the wide spectrum of convective intensities for extreme rain rates in the arid/semiarid southwestern United States and exhibit comparable vertical structures to their counterparts in the eastern United States.

    « less
  3. Abstract

    The Mississippi River basin drains nearly one-half of the contiguous United States, and its rivers serve as economic corridors that facilitate trade and transportation. Flooding remains a perennial hazard on the major tributaries of the Mississippi River basin, and reducing the economic and humanitarian consequences of these events depends on improving their seasonal predictability. Here, we use climate reanalysis and river gauge data to document the evolution of floods on the Missouri and Ohio Rivers—the two largest tributaries of the Mississippi River—and how they are influenced by major modes of climate variability centered in the Pacific and Atlantic Oceans. We show that the largest floods on these tributaries are preceded by the advection and convergence of moisture from the Gulf of Mexico following distinct atmospheric mechanisms, where Missouri River floods are associated with heavy spring and summer precipitation events delivered by the Great Plains low-level jet, whereas Ohio River floods are associated with frontal precipitation events in winter when the North Atlantic subtropical high is anomalously strong. Further, we demonstrate that the El Niño–Southern Oscillation can serve as a precursor for floods on these rivers by mediating antecedent soil moisture, with Missouri River floods often preceded by a warmmore »eastern tropical Pacific (El Niño) and Ohio River floods often preceded by a cool eastern tropical Pacific (La Niña) in the months leading up peak discharge. We also use recent floods in 2019 and 2021 to demonstrate how linking flood hazard to sea surface temperature anomalies holds potential to improve seasonal predictability of hydrologic extremes on these rivers.

    « less
  4. Abstract. Floods are the product of complex interactions among processes includingprecipitation, soil moisture, and watershed morphology. Conventional floodfrequency analysis (FFA) methods such as design storms and discharge-basedstatistical methods offer few insights into these process interactions andhow they “shape” the probability distributions of floods. Understanding andprojecting flood frequency in conditions of nonstationary hydroclimate andland use require deeper understanding of these processes, some or all ofwhich may be changing in ways that will be undersampled in observationalrecords. This study presents an alternative “process-based” FFA approachthat uses stochastic storm transposition to generate large numbers ofrealistic rainstorm “scenarios” based on relatively short rainfall remotesensing records. Long-term continuous hydrologic model simulations are usedto derive seasonally varying distributions of watershed antecedentconditions. We couple rainstorm scenarios with seasonally appropriateantecedent conditions to simulate flood frequency. The methodology is appliedto the 4002 km2 Turkey River watershed in the Midwestern United States,which is undergoing significant climatic and hydrologic change. We show that,using only 15 years of rainfall records, our methodology can produce accurateestimates of “present-day” flood frequency. We found that shifts in theseasonality of soil moisture, snow, and extreme rainfall in the Turkey Riverexert important controls on flood frequency. We also demonstrate thatprocess-based techniques may be prone to errors due to inadequaterepresentationmore »of specific seasonal processes within hydrologic models. Ifsuch mistakes are avoided, however, process-based approaches can provide auseful pathway toward understanding current and future flood frequency innonstationary conditions and thus be valuable for supplementing existing FFApractices.« less
  5. Among the different types of natural disasters, floods are the most devastating, widespread, and frequent. Floods account for approximately 30% of the total loss caused by natural disasters. Accurate flood-risk mapping is critical in reducing such damages by correctly predicting the extent of a flood when coupled with rain and stage gage data, supporting emergency-response planning, developing land use plans and regulations with regard to the construction of structures and infrastructures, and providing damage assessment in both spatial and temporal measurements. The reliability and accuracy of such flood assessment maps is dependent on the quality of the digital elevation model (DEM) in flood conditions. This study investigates the quality of an Unmanned Aerial Vehicle (UAV)-based DEM for spatial flood assessment mapping and evaluating the extent of a flood event in Princeville, North Carolina during Hurricane Matthew. The challenges and problems of on-demand DEM production during a flooding event were discussed. An accuracy analysis was performed by comparing the water surface extracted from the UAV-derived DEM with the water surface/stage obtained using the nearby US Geologic Survey (USGS) stream gauge station and LiDAR data.