Real-time Tropical Cyclone Intensity Estimation by Handling Temporally Heterogeneous Satellite Data

TL;DR

This paper introduces a hybrid GAN-CNN framework that leverages heterogeneous satellite data to estimate tropical cyclone intensity more frequently and accurately in real-time, reducing estimation intervals from 3 hours to under 15 minutes.

Contribution

The novel framework effectively combines generative adversarial networks with CNNs to utilize all available satellite data during training and only high-frequency data during prediction, enhancing real-time TC intensity estimation.

Findings

Achieves comparable accuracy to state-of-the-art models.

Increases maximum estimation frequency from 3 hours to less than 15 minutes.

Demonstrates effective handling of temporally heterogeneous satellite data.

Abstract

Analyzing big geophysical observational data collected by multiple advanced sensors on various satellite platforms promotes our understanding of the geophysical system. For instance, convolutional neural networks (CNN) have achieved great success in estimating tropical cyclone (TC) intensity based on satellite data with fixed temporal frequency (e.g., 3 h). However, to achieve more timely (under 30 min) and accurate TC intensity estimates, a deep learning model is demanded to handle temporally-heterogeneous satellite observations. Specifically, infrared (IR1) and water vapor (WV) images are available under every 15 minutes, while passive microwave rain rate (PMW) is available for about every 3 hours. Meanwhile, the visible (VIS) channel is severely affected by noise and sunlight intensity, making it difficult to be utilized. Therefore, we propose a novel framework that combines generative adversarial network (GAN) with CNN. The model utilizes all data, including VIS and PMW information, during the training phase and eventually uses only the high-frequent IR1 and WV data for providing intensity estimates during the predicting phase. Experimental results demonstrate that the hybrid GAN-CNN framework achieves comparable precision to the state-of-the-art models, while possessing the capability of increasing the maximum estimation frequency from 3 hours to less than 15 minutes.