A Visual-Analytical Approach for Automatic Detection of Cyclonic Events in Satellite Observations

TL;DR

This paper presents a data-driven, image-based method for rapid detection and intensity estimation of cyclones in satellite imagery, replacing slower physics-based models with a novel CNN-LSTM approach.

Contribution

It introduces a two-stage detection and intensity estimation framework using only satellite images, combining CNN and LSTM architectures for improved speed and accuracy.

Findings

Effective cyclone localization in satellite images.

Accurate intensity estimation using CNN-LSTM model.

Faster inference compared to traditional physics-based methods.

Abstract

Estimating the location and intensity of tropical cyclones holds crucial significance for predicting catastrophic weather events. In this study, we approach this task as a detection and regression challenge, specifically over the North Indian Ocean (NIO) region where best tracks location and wind speed information serve as the labels. The current process for cyclone detection and intensity estimation involves physics-based simulation studies which are time-consuming, only using image features will automate the process for significantly faster and more accurate predictions. While conventional methods typically necessitate substantial prior knowledge for training, we are exploring alternative approaches to enhance efficiency. This research aims to focus specifically on cyclone detection, intensity estimation and related aspects using only image input and data-driven approaches and will lead to faster inference time and automate the process as opposed to current NWP models being utilized at SAC. In context to algorithm development, a novel two stage detection and intensity estimation module is proposed. In the first level detection we try to localize the cyclone over an entire image as captured by INSAT3D over the NIO (North Indian Ocean). For the intensity estimation task, we propose a CNN-LSTM network, which works on the cyclone centered images, utilizing a ResNet-18 backbone, by which we are able to capture both temporal and spatial characteristics.