Tropical Cyclone Intensity Estimation Using Multi-Dimensional Convolutional Neural Networks from Geostationary Satellite Data

Abstract

For a long time, researchers have tried to find a way to analyze tropical cyclone (TC) intensity in real-time. Since there is no standardized method for estimating TC intensity and the most widely used method is a manual algorithm using satellite-based cloud images, there is a bias that varies depending on the TC center and shape. In this study, we adopted convolutional neural networks (CNNs) which are part of a state-of-art approach that analyzes image patterns to estimate TC intensity by mimicking human cloud pattern recognition. Both two dimensional-CNN (2D-CNN) and three-dimensional-CNN (3D-CNN) were used to analyze the relationship between multi-spectral geostationary satellite images and TC intensity. Our best-optimized model produced a root mean squared error (RMSE) of 8.32 kts, resulting in better performance (~35%) than the existing model using the CNN-based approach with a single channel image. Moreover, we analyzed the characteristics of multi-spectral satellite-based TC images according to intensity using a heat map, which is one of the visualization means of CNNs. It shows that the stronger the intensity of the TC, the greater the influence of the TC center in the lower atmosphere. This is consistent with the results from the existing TC initialization method with numerical simulations based on dynamical TC models. Our study suggests the possibility that a deep learning approach can be used to interpret the behavior characteristics of TCs.

Impacts of the Tropical Cyclone Idai in Mozambique: A Multi-Temporal Landsat Satellite Imagery Analysis

“…Tropical cyclones are among the most devastating natural disasters owing to their great potential for loss of human life, significant economic decline and severe environmental damage [1][2][3]. The Southwestern Indian Ocean is one of the main tropical cyclone areas 2012 to 2019; (ii) to investigate how the distance to Idai's trajectory related to vegetation damage, and (iii) to determine the degree of damage caused by the cyclone on different LULC classes.…”

Resilient distribution system leveraging distributed generation and microgrids: a review

“…In [63 ], a multi‐layer neural network is proposed and trained to forecast the track of cyclones based on satellite images. The deep convolutional neural network (CNN) is employed to estimate the intensity of tropical cyclones based on satellite images in [64, 65 ]. It should be noted that AI systems estimate the tracks and intensity of hurricanes through mimicking human cloud pattern recognition.…”

Domain knowledge integration into deep learning for typhoon intensity classification

“…They concluded that their best model was competitive with existing methods such as the advanced Dvorak technique (ADT 32 ) and Satellite Consensus (SATCON 33 ). Lee et al 27 used a two-dimensional CNN (2D-CNN) and a three-dimensional CNN (3D-CNN) to analyze the relationship between multispectral geostationary satellite images and TC intensity. Their optimal model exhibited better performance (35%) than the existing model using the CNN-based approach with a single channel image.…”