Tropical cyclone eye fix using genetic algorithm with temporal information

Authors:
Ka Yan Wong;Chi Lap Yip
Affiliations:
Dept. of Computer Science, The University of Hong Kong, Hong Kong;Dept. of Computer Science, The University of Hong Kong, Hong Kong
Venue:
KES'05 Proceedings of the 9th international conference on Knowledge-Based Intelligent Information and Engineering Systems - Volume Part I
Year:
2005

Citing 2
Cited 3

Extraction of Singular Points from Dense Motion Fields: An Analytic Approach

Journal of Mathematical Imaging and Vision
Automatic Template Matching Method for Tropical Cyclone Eye Fix

ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 3 - Volume 03

Automatic tropical cyclone eye fix using genetic algorithm

Expert Systems with Applications: An International Journal
Automatic identification of weather systems from numerical weather prediction data using genetic algorithm

Expert Systems with Applications: An International Journal
Comparison of squall line positioning methods using radar data

KES'06 Proceedings of the 10th international conference on Knowledge-Based Intelligent Information and Engineering Systems - Volume Part III

Quantified Score

Hi-index	0.00

Visualization

Abstract

Tropical cyclones (TCs) are weather systems with vast destructive power. To give early TC warnings, accurate location of their circulation centers, or “eyes”, is required. The pattern matching solution to this TC eye fix problem works by analyzing individual remote sensing images as if they are independent. Temporal information is ignored in such approach and results from individual image are only smoothed afterwards. In this paper, a TC eye fix method using genetic algorithm (GA) with temporal information is proposed. This method gives an improvement of 35% in speed and 20% in accuracy compared to the one without the use of temporal information. Our proposed method can process 6 minutes of radar data in about 10 seconds on a notebook computer, meeting practical real time constraints. It gives an average accuracy within 0.107 to 0.156 degrees in latitude/longitude on the Mercator projected map, well within the relative error of about 0.3 degrees given by different TC warning centers.