Forecasting the Fury: A Deep Learning Approach to Predicting Cyclone Intensity

Abstract

Cyclones are considered one of the most catastrophic natural calamities that result in severe destruction and numerous casualties each year. To ensure prompt and efficient disaster management and response, it is imperative to estimate the intensity of cyclones with precision and timeliness. In this research article, a deep learning technique is suggested for cyclone intensity evaluation utilizing INSAT-3D IR imagery. Our proposed method uses a pre-trained convolutional neural network (CNN) such as ResNet-50 and Inception-V3 to learn features from INSAT-3D IR imagery and estimate the cyclone's intensity. We train the model on a dataset of cyclones with known intensities and evaluate its performance on a separate test set. To analyze the significance of various elements in our proposed approach, we perform an ablation study, including the CNN architecture and input image preprocessing. The results show how well our suggested strategy works and shed light on the mechanisms that underlie it. In our deep learning model, we have used CNN, Inception, and Resnet50. We have calculated the Mean Squared Error, Mean absolute error, R-squared score, and Root mean squared error. We have considered the RMSE value for results which are for CNN is 13.77, Inception_V3 is 15.77 and Resnet50 is 11.69. This indicates that Resnet50 is giving better results in comparison to Inception_V3 and CNN. Overall, our deep learning-based approach offers a promising solution for accurate and timely cyclone intensity estimation, which can aid in disaster management and response efforts. © 2023 IEEE.