Tropical Cyclone-Following Dataset for Limited-Area Machine Learning Applications
Minh-Khanh Luong, Chanh Kieu
Abstract
This work presents a lightweight dataset of tropical cyclone (TC)-following meteorological variables to facilitate the development and application of machine learning (ML) methods in TC research. Using outputs from our previous climate downscaling and idealized simulations, the dataset is constructed as multichannel video sequences that track TC centers throughout their lifetimes. To demonstrate the dataset utility, we present an application in which a regional ML model is trained to predict TC intensity with explicit incorporation of lateral boundary conditions. Our results highlight the importance of lateral boundary information for predicting TC intensity with ML models inside a limited-area domain, underscoring the need to properly account for lateral boundaries when developing regional ML models for TC intensity forecast.
Create a lesson
Related papers
From Sea Surface Height to Velocity - A Machine Learning Approach
Yaswanth Reddy Yaradoddi, Jinbo Wang, Elyes Serghine
Can LLM Agents Improve Imperfect Earth System Model Parameterizations?
Kara D. Lamb
Six-hourly Probabilistic Precipitation Forecasts Created From Hourly Probabilities
Thomas M Hamill
New Wine in an Old Bottle -- NeuralPOM: A Hybrid Ocean Forecast Model with Differentiable Dynamics and Staged Learning
Ruiqi Shu, Guangliang Liu, Ruijian Gou et al.
Jovian Polar Vortex Generation in a Shallow-Water Model with Quasi-Stochastic Convection
Yuhang Ruan, Hao Fu, Cheng Li et al.
An all-weather microwave-based AI retrieval of pan-Arctic melt pond fraction
Sara Aparício, Simon Driscoll, Mark R. Drinkwater et al.