Online Program Home
My Program

Abstract Details

Activity Number: 294 - SPEED: Statistical Learning and Data Science Speed Session 2, Part 1
Type: Contributed
Date/Time: Tuesday, July 30, 2019 : 8:30 AM to 10:20 AM
Sponsor: Section on Statistical Learning and Data Science
Abstract #307385 Presentation
Title: A Statistical Model for Tropical Cyclone Genesis and Assessing Its Differences Between Basins and Climates
Author(s): Arturo Fernandez*
Companies: University of California - Berkeley

Tropical cyclones (TCs) are important extreme weather phenomena that have significant negative impact on society. Simulations from global climate models (GCMs) are used to better understand how TC statistics change due to climate change. Although various studies have been conducted on the climatology of tropical cyclone genesis (TCG), their analyses are often limited in that they focus on basin-specific models, discard high resolution data in favor of aggregate measures, or bias their investigation towards pre-chosen variables.

Previous work has shown that a statistical model can accurately predict TCG in the Community Atmospheric Model (CAM) Version 5.1. L1-regularized logistic regression (L1LR) was successfully applied to distinguish between TCG events and non-developing storms with high accuracy. While the previous study focused primarily on surface level values, here we extend our framework by using three-dimensional information at various elevations. Moreover, we assess whether there exist differences in TCG between basins as well as between different climates.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2019 program