Skip to main content
OSTI.GOVU.S. Department of Energy Office of Scientific and Technical Information
U.S. Department of Energy
Office of Scientific and Technical Information
 

Improving tropical cyclone rapid intensification forecasts with satellite measurements of sea surface salinity and calibrated machine learning

Journal Article · · Environmental Research Letters
 [1];  [2];  [1];  [2];  [3];  [3];  [4];  [5];  [2];  [6];  [6]
  1. California Institute of Technology (CalTech), Pasadena, CA (United States)
  2. Hong Kong University of Science and Technology (HKUST) (Hong Kong)
  3. Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)
  4. Ewha Womans University, Seoul (Korea, Republic of)
  5. Hong Kong Observatory (HKO) (China)
  6. Colorado State University, Fort Collins, CO (United States)
+ Show Author Affiliations

Forecasting rapid intensification (RI) of tropical cyclones (TC) is a mission known for large errors. One under-researched factor that affects TC intensification is salinity, which is important for density stratification in certain ocean regions and can affect the surface enthalpy flux under a strengthening hurricane. To investigate the impact and efficacy of using salinity information in state-of-the-art forecasting, we use a statistical model consisting of a variety of machine learning (ML) methods. For salinity data, we use satellite measurements of pre-storm sea surface salinity (SSS) as a proxy for the salinity stratification. We train and test the model on various ocean basins, including the Atlantic, eastern North Pacific and western North Pacific. A calibrator is trained on top of the ML models to correct and enhance probability forecasts. The calibrator significantly improves probability forecasts relative to recent works. The ML model performance is improved with the addition of SSS in the Eastern North Pacific, western North Pacific, and the Caribbean subregion of the North Atlantic, and the overall model performance is better than previous studies. SSS decreases model skill for a model trained on the full Atlantic basin. In the Indian Ocean, SSS is also notably correlated with RI occurrence, but the TC samples are not sufficient to train ML models.

Research Organization:
Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)
Sponsoring Organization:
USDOE Office of Science (SC), Biological and Environmental Research (BER); National Science Foundation (NSF); National Aeronautics and Space Administration (NASA)
Grant/Contract Number:
AC05-76RL01830
OSTI ID:
2569572
Report Number(s):
PNNL-SA--211557
Journal Information:
Environmental Research Letters, Journal Name: Environmental Research Letters Journal Issue: 3 Vol. 20; ISSN 1748-9326
Publisher:
IOP PublishingCopyright Statement
Country of Publication:
United States
Language:
English

References (36)

Dynamic Potential Intensity: An improved representation of the ocean's impact on tropical cyclones journal August 2015
Haline hurricane wake in the Amazon/Orinoco plume: AQUARIUS/SACD and SMOS observations journal October 2012
Applying Satellite Observations of Tropical Cyclone Internal Structures to Rapid Intensification Forecast With Machine Learning journal August 2020
Thermodynamic control of hurricane intensity journal October 1999
Ocean barrier layers' effect on tropical cyclone intensification journal August 2012
Predicting good probabilities with supervised learning conference January 2005
Adjusting the Outputs of a Classifier to New a Priori Probabilities: A Simple Procedure journal January 2002
Sea Surface Temperature Variability in Hurricanes: Implications with Respect to Intensity Change journal August 2003
On Summary Measures of Skill in Rare Event Forecasting Based on Contingency Tables journal December 1990
Large-Scale Characteristics of Rapidly Intensifying Tropical Cyclones in the North Atlantic Basin journal December 2003
The Response of Balanced Hurricanes to Local Sources of Heat and Momentum journal February 1982
Upper Ocean Response to a Hurricane journal February 1981
Real-Case Simulations of Hurricane–Ocean Interaction Using A High-Resolution Coupled Model: Effects on Hurricane Intensity journal April 2000
Advances and Challenges at the National Hurricane Center journal April 2009
Visualizing Multiple Measures of Forecast Quality journal April 2009
A Revised Tropical Cyclone Rapid Intensification Index for the Atlantic and Eastern North Pacific Basins journal February 2010
Quantifying Environmental Control on Tropical Cyclone Intensity Change journal August 2010
Rapid Intensification of a Sheared Tropical Storm journal October 2010
The Joint Hurricane Test Bed: Its First Decade of Tropical Cyclone Research-To-Operations Activities Reviewed journal March 2012
The Hurricane Forecast Improvement Project journal March 2013
Is Tropical Cyclone Intensity Guidance Improving? journal March 2014
Will Global Warming Make Hurricane Forecasting More Difficult? journal March 2017
Pronounced impact of salinity on rapidly intensifying tropical cyclones journal April 2020
On the Rapid Intensification of Hurricane Wilma (2005). Part II: Convective Bursts and the Upper-Level Warm Core journal January 2013
A Numerical Study on Rapid Intensification of Typhoon Vicente (2012) in the South China Sea. Part II: Roles of Inner-Core Processes journal January 2018
Tropical Cyclone Intensification from Asymmetric Convection: Energetics and Efficiency journal October 2007
The Relationship between Tropical Cyclone Intensity Change and the Strength of Inner-Core Convection journal April 2012
The Convective Evolution and Rapid Intensification of Hurricane Earl (2010) journal November 2014
Multiscale Structure and Evolution of Hurricane Earl (2010) during Rapid Intensification journal February 2015
Evaluating Environmental Impacts on Tropical Cyclone Rapid Intensification Predictability Utilizing Statistical Models journal October 2015
Deep Learning Experiments for Tropical Cyclone Intensity Forecasts journal June 2021
Predicting Rapid Intensification in North Atlantic and Eastern North Pacific Tropical Cyclones Using a Convolutional Neural Network journal August 2022
Machine learning algorithm validation with a limited sample size journal November 2019
SMOTE: Synthetic Minority Over-sampling Technique journal January 2002
Tropical Cyclone Track Forecasting Using Fused Deep Learning From Aligned Reanalysis Data journal January 2020
Operational Forecasting of Tropical Cyclone Rapid Intensification at the National Hurricane Center journal May 2021

Similar Records

Pronounced Impact of Salinity on Rapidly Intensifying Tropical Cyclones
Journal Article · Tue Sep 01 00:00:00 EDT 2020 · Bulletin of the American Meteorological Society · OSTI ID:1773425
Increasing Magnitude of Hurricane Rapid Intensification in the Central and Eastern Tropical Atlantic: Hurricanes and Rapid Intesnification
Journal Article · Thu May 03 00:00:00 EDT 2018 · Geophysical Research Letters · OSTI ID:1559277

Related Subjects

hurricane
machine learning
rapid intensification
salinity
satellite
tropical cyclone