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: JOHAN: A Joint Online Hurricane Trajectory and Intensity Forecasting Framework
Hurricanes are one of the most catastrophic natural forces with potential to inflict severe damages to properties and loss of human lives from high winds and inland flooding. Accurate long-term forecasting of the trajectory and intensity of advancing hurricanes is therefore crucial to provide timely warnings for civilians and emergency responders to mitigate costly damages and their life-threatening impact. In this paper, we present a novel online learning framework called JOHAN that simultaneously predicts the trajectory and intensity of a hurricane based on outputs produced by an ensemble of dynamic (physical) hurricane models. In addition, JOHAN is designed to generate accurate forecasts of the ordinal-valued hurricane intensity categories to ensure that their severity level can be reliably communicated to the public. The framework also employs exponentially-weighted quantile loss functions to bias the algorithm towards improving its prediction accuracy for high category hurricanes approaching landfall. Experimental results using real-world hurricane data demonstrated the superiority of JOHAN compared to several state-of-the-art learning approaches.  more » « less
Award ID(s):
2006633
PAR ID:
10358745
Author(s) / Creator(s):
;
Date Published:
Journal Name:
KDD '21: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining
Page Range / eLocation ID:
1677 to 1685
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; (, American Meteorological Society)
    Hurricanes have been the most expensive natural catastrophe in the United States causing significant damages and disastrous floods. Considering the increased projected destructiveness of future hurricanes due to global warming, a reliable hurricane forecasting model is a national priority. Despite significant enhancement in weather prediction models, hurricane-induced flood forecasts are not sufficiently accurate yet. This inadequacy could be attributed to inaccurate hurricane intensity and track forecasts which can be due to improper physical parameterizations of unique hurricane dynamics. Previous studies have shown that remarkable differences exist in the dynamics of hurricanes compared to regular atmospheric boundary layers (Momen et al. 2021; Li et al. 2023; Matak and Momen 2023). These differences are due to strong rotational effects in hurricanes that are not represented in current turbulence and planetary boundary layer (PBL) parameterization schemes (Romdhani et al. 2022). These discrepancies in different physical schemes can cause improper hurricane structure, trajectory, intensity, and precipitation; ultimately leading to inaccurate hurricane-induced flood forecasts. It is not well known how adjusting PBL dynamics can influence hydro-meteorological forecasts in hurricanes. In this talk, we seek to bridge this knowledge gap by coupling Advanced Weather Research and Forecasting (WRF-ARW) with the hydrological model WRF-Hydro to simulate multiple hurricanes in the US. We will first show the impacts of various PBL, microphysics, and cumulus parameterizations on the accuracy of real hurricane intensity, track, and flood forecasts. All these runs will be conducted coupled with the WRF-Hydro model, which is extensively calibrated for three coastal regions in the US using multiple USGS gauges. The best-performing parameterizations will then be determined through a comprehensive sensitivity test. We will next present new adjustments to the default PBL schemes of WRF that enhance hurricane intensity forecasts. Following (Matak and Momen 2023), the default vertical diffusion of WRF is reduced to enhance hurricane intensification. Then, the impacts of these adjustments and hurricane dynamics improvements on hurricane-induced flood forecasts are quantified. For example, the attached figure shows an example of our simulations. By reducing the default diffusion, the intensity of hurricanes increases, and their size decreases compared to the default model. This remarkably influences hurricane precipitation rate and aerial distribution. Intensified hurricanes were shown to generate more intense and localized precipitation. This improved representation of hurricane dynamics led to better flood forecasts for the considered hurricanes. In total, we found that by reducing the vertical diffusion, hurricane intensity forecasts were enhanced by ~40% on average compared to the default models. This led to ~16% and 34% improvements in streamflow bias and correlation forecasts, respectively. This research provides new insights into the effects of PBL dynamics on hurricane streamflow forecasts. These new adjustments play a vital role in improving the hurricane and streamflow forecasts in coupled hydro-meteorological models. References: Li, M., J. A. Zhang, L. Matak, and M. Momen, 2023: The Impacts of Adjusting Momentum Roughness Length on Strong and Weak Hurricane Forecasts: A Comprehensive Analysis of Weather Simulations and Observations. Mon Weather Rev, 151, 1287–1302, https://doi.org/10.1175/MWR-D-22-0191.1. Matak, L., and M. Momen, 2023: The Role of Vertical Diffusion Parameterizations in the Dynamics and Accuracy of Simulated Intensifying Hurricanes. Boundary Layer Meteorol, https://doi.org/10.1007/s10546-023-00818-w. Momen, M., M. B. Parlange, and M. G. Giometto, 2021: Scrambling and Reorientation of Classical Atmospheric Boundary Layer Turbulence in Hurricane Winds. Geophys Res Lett, 48, https://doi.org/10.1029/2020GL091695. Romdhani, O., J. A. Zhang, and M. Momen, 2022: Characterizing the Impacts of Turbulence Closures on Real Hurricane Forecasts: A Comprehensive Joint Assessment of Grid Resolution, Horizontal Turbulence Models, and Horizontal Mixing Length. J Adv Model Earth Syst, 14, https://doi.org/10.1029/2021ms002796. 
    more » « less
  2. ; ; (, Frontiers in Climate)
    null (Ed.)
    In this study, a novel framework was developed to provide a holistic damage assessment caused by severe hydrologic events whether individually or as a compound event. The novel framework uses a developed hurricane-specific water quality model, Environmental Fluid Dynamic Code-Storm Surge model (EFDC-SS) and an ArcGIS-based framework, the Facility Economic Damage and Environmental Release Planning (FEDERAP) to assess damages to the built and natural environment. The developed framework could be used to compare different hurricanes and storms with a focus on land inundation, spill destination in both land and water and their associated risks, as well as economic loss including both physical and secondary losses. The results showed different spreading mechanisms during surge and rainfall-based hurricanes. While storm surge pushed contaminants (from spills) upstream, the rainfall-based hurricane caused a larger footprint of contamination on land. Though different in spreading patterns, spills during both hurricane types can widely spread miles away from the release location in a very short period of time. The FEDERAP economic loss model showed that facility area, average land elevation, the number of storage tanks and process units at the facility, and daily production are key drivers in the calculated total losses for a given hydrologic event. 
    more » « less
  3. ; ; ; ; ; ; (, Journal of Arid Environments)
    Tropical cyclones (e.g., hurricanes and tropical storms), are considered one of the world's most destructive climatological forces, causing substantial damage especially in urban areas. However, for some arid ecosystems, tropical cyclones represent natural disturbance events, providing important sources of fresh water that support ecosystem functioning. For subsistence populations living in these regions, it is unclear whether they experience these events negatively due to the associated damages or positively within a predictable disturbance regime. Here, we assess these phenomena with traditional ranchers from Baja California Sur, Mexico, following Hurricane Kay (September 2022). We find that despite significant damage caused by the hurricane, nearly the entire sample perceived this tropical cyclone event as a net positive on their lives. This traditional ranching population has a culture that is adapted to the seasonal tropical cyclone disturbance regime, and expects extreme rain events annually to support ecosystem functioning, and therefore their economic livelihoods. To these ranchers, the climate shock is not when the hurricanes come, but rather, when hurricanes do not come. We situate our results within a disturbance ecology framework, highlighting the role of increasing aridity and probability of drought in the North American Arid West. 
    more » « less
  4. ; ; (, IISE Annual Conference)
    null (Ed.)
    The total cost for weather-related disasters in the US increases over time, and hurricanes usually create the most damage. One of the challenges, which is present in almost every major hurricane event, is the patient evacuation mission. We propose a comprehensive modeling and methodological framework for a large-scale patient evacuation problem when an area is faced with a forecasted disaster such as a hurricane. In this work, we integrate a hurricane scenario generation scheme using publicly available surge level forecasting software and a scenario-based stochastic integer program to make decisions on patient movements, staging area locations and positioning of emergency medical vehicles with an objective of minimizing the total expected cost of evacuation and the setup cost of staging areas. The hurricane scenario generation scheme incorporates the uncertainties in the hurricane intensity, direction, forward speed and tide level. To demonstrate the modeling approach, we apply real-world data from the Southeast Texas region in our experiments. We highlight the importance of operation time limits, the number of available resources and an accurate forecast on forthcoming hurricanes in determining the locations of staging areas and patient evacuation decisions. 
    more » « less
  5. ; (, American Meteorological Society)
    Forecasting hurricanes is critically important for mitigating their devastating impacts caused by wind damage, storm surges, and flooding. Despite remarkable advancements in numerical weather prediction (NWP) models, such as the Weather Research and Forecasting (WRF) model, accurate hurricane forecasts remain challenging likely due to inaccurate physical parameterizations of complex dynamics of these storms. One major issue of these models is related to their Planetary Boundary Layer (PBL) schemes, which are not typically designed for hurricane flows with strong rotation. Previous studies have shown that the existing PBL schemes of hurricane simulations are often overly dissipative, leading to underestimations of the storm intensity (Matak and Momen 2023; Romdhani et al. 2022). Our recent research (Khondaker and Momen 2024) demonstrated that reducing diffusion in these models improved the hurricane’s intensity and size forecasts by more than ~30% on average in four considered major hurricanes. This reduced diffusion is due to the strong rotational nature of hurricanes, which suppresses turbulence and produces smaller eddies compared to regular PBLs (Momen et al. 2021). While prior studies showed that decreasing the vertical diffusion significantly improves major hurricane intensity forecasts, they mostly relied on simplified and often invariable adjustments of vertical diffusion such as multiplying it by a constant coefficient. The objective of this study is to address this issue by introducing a rotation-based variable adjustment of diffusion to account for the strong rotational nature of tropical cyclone (TC) dynamics. To this end, we will present multiple real strong and weak hurricane simulations using the Advanced Research WRF (ARW) model in the US. We modified the vertical eddy diffusivity based on the relative vorticity to accommodate the rotational dynamics of TCs in PBL schemes. While the default model significantly underpredicts hurricane intensity, our new adjustments outperform the default schemes for these strong hurricanes (see, e.g., attached fig. a), with notable improvements in track and minimum sea level pressure accuracy. This modification also remarkably increases the inflow in hurricanes compared to default models and leads to the intensification of the TC vortex (see, e.g., attached fig. b,c). Our newly adjusted model matched more closely with dropsonde, and satellite observations compared to the default WRF’s PBL schemes. These modifications to the PBL schemes make them more physics-based adjustments compared to previous treatments, offering valuable insights for improving hurricane forecasts in NWP models. References: Khondaker, M. H., and M. Momen, 2024: Improving hurricane intensity and streamflow forecasts in coupled hydro-meteorological simulations by analyzing precipitation and boundary layer schemes. J Hydrometeorol, https://doi.org/10.1175/JHM-D-23-0153.1. Matak, L., and M. Momen, 2023: The Role of Vertical Diffusion Parameterizations in the Dynamics and Accuracy of Simulated Intensifying Hurricanes. Boundary Layer Meteorology, https://doi.org/10.1007/s10546-023-00818-w. Momen, M., M. B. Parlange, and M. G. Giometto, 2021: Scrambling and Reorientation of Classical Atmospheric Boundary Layer Turbulence in Hurricane Winds. Geophysical Research Letters, 48, https://doi.org/10.1029/2020GL091695. Romdhani, O., J. A. Zhang, and M. Momen, 2022: Characterizing the Impacts of Turbulence Closures on Real Hurricane Forecasts: A Comprehensive Joint Assessment of Grid Resolution, Horizontal Turbulence Models, and Horizontal Mixing Length. Journal of Advanced Modeling Earth System, 14, https://doi.org/10.1029/2021ms002796. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email