Abstract | ||
---|---|---|
Tracking and predicting extreme events in large-scale spatio-temporal climate data are long standing challenges in climate science. In this paper, we propose Convolutional LSTM (ConvLSTM)-based spatio-temporal models to track and predict hurricane trajectories from large-scale climate data; namely, pixel-level spatio-temporal history of tropical cyclones. To address the tracking problem, we model time-sequential density maps of hurricane trajectories, enabling to capture not only the temporal dynamics but also spatial distribution of the trajectories. Furthermore, we introduce a new trajectory prediction approach as a problem of sequential forecasting from past to future hurricane density map sequences. Extensive experiment on actual 20 years record shows that our ConvLSTM-based tracking model significantly outperforms existing approaches, and that the proposed forecasting model achieves successful mapping from predicted density map to ground truth. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/WACV.2019.00192 | 2019 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV) |
Field | DocType | ISSN |
Meteorology,Computer vision,Extreme events,Climate science,Computer science,Ground truth,Artificial intelligence,Trajectory,Tropical cyclone | Conference | 2472-6737 |
Citations | PageRank | References |
1 | 0.43 | 0 |
Authors | ||
7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Sookyung Kim | 1 | 2 | 0.77 |
Hyojin Kim | 2 | 22 | 2.66 |
Joonseok Lee | 3 | 15 | 3.40 |
Sangwoong Yoon | 4 | 1 | 0.43 |
Samira Ebrahimi Kahou | 5 | 462 | 28.90 |
Karthik Kashinath | 6 | 11 | 2.71 |
Prabhat | 7 | 456 | 34.79 |