2018 Paper on “A Convolutional Neural Network Approach for Estimating Tropical Cyclone Intensity Using Satellite-based Infrared Images”
Abstract |
Existing techniques for satellite-based tropical cyclone (TC) intensity estimation involve an explicit feature extraction step to model TC intensity on a set of relevant TC features or patterns such as eye formation and cloud organization. However, crafting such a feature set is often time-consuming and requires expert knowledge. In this paper, a convolutional neural network (CNN) approach, which eliminates explicit feature extraction, for estimating the intensity of tropical cyclones is proposed. Utilizing a Visual Geometry Group 19-1ayer CNN (VGG19) model pre-trained on ImageNet, transfer learning experiments were performed using grayscale IR images of TCs obtained from various geostationary satellites in the Western North Pacific region (1996 – 2016) to estimate TC intensity. The model re-trained on TC images achieved a root-mean-square error (RMSE) of 13.23 knots – a performance comparable to existing feature-based approaches (RMSE ranging from 12 to 20 knots). Moreover, the model was able to learn generic TC features that were previously identified in feature-based approaches as important indicators of TC intensity. |
Authors |
Jeffrey A. Aborot Mr. Aborot is currently a researcher at DOST-ASTI’s Computer Software Division (CSD). As a researcher at CSD, he does applicative research on Artificial Intelligence in relation to satellite-captured images, legal texts, plants, and computing facility performance. He also supervises software engineering projects that has requirement for data analytics component where he oversees a software engineering team and programs core components of the software. Mr. Aborot is a Bachelor’s degree graduate of the University of the Philippines Baguio. He is also currently a graduate student at the Department of Computer Science of the University of the Philippines Diliman. He is taking up a Master of Computer Science degree and is doing his research under the Algorithms and Complexity Laboratory. His research interest is Quantum Computing. |
Jay Samuel L. Combinido |
|
John Robert T. Mendoza |
|
Published on |
29 November 2018 |
Presented in |
2018 24th International Conference on Pattern Recognition (ICPR) |
Published at |
IEEE Xplore Digital Library |
Link to Publication |
https://ieeexplore.ieee.org/document/8545593 |