7th Prediction Science Seminar
- Date
- March 24th, 2022（Thu.）10:30-12:00 (JST)
- Language
- English
- Place
-
Zoom
To join the seminar, please contact the Prediction Science Seminar Office: prediction-seminar[remove here]@ml.riken.jp
Program
| Time | Content | Speaker |
|---|---|---|
| 10:30-11:30 | Detection of tropical cyclones and their precursors using deep convolutional neural networks | Dr. Daisuke Matsuoka (JAMSTEC) |
| 11:30-12:00 | Discussion | - |
Abstract
Detection of tropical cyclones and their precursors using deep convolutional neural networksDr. Daisuke Matsuoka (JAMSTEC)
Deep convolutional neural networks, an architecture of deep learning, is an effective method for object detection from images and image classification. We have conducted several studies on the detection of tropical cyclones (including their precursors) from simulation and satellite observation data. In this talk, we will introduce the following three topics. (1) tropical cyclone detection from simulation data, (2) improvement of detection performance through data science competitions, and (3) application to observation data. In addition, new methods that integrate simulation data and satellite observation data will also be discussed.
Organizer
- Prediction Science Laboratory (RIKEN CPR)
Co-organizer
- Data Assimilation Research Team (R-CCS)
- RIKEN Interdisciplinary Theoretical and Mathematical Sciences Program
- Environmental Metabolic Analysis Research Team (RIKEN CSRS)
- Computational Climate Science Research Team (R-CCS)
- Medical Data Deep Learning Team (R-IH)
- Medical Data Mathematical Reasoning Team (R-IH)
- Laboratory for Physical Biology (RIKEN BDR)