EGU General Assembly 2020
© Author(s) 2021. This work is distributed under
the Creative Commons Attribution 4.0 License.

Big Data Assimilation: Real-time Workflow for 30-second-update Forecasting and Perspectives toward DA-AI Integration

Takemasa Miyoshi1, Takmi Honda1, Shigenori Otsuka1, Arata Amemiya1, Yasumitsu Maejima1, Yoshihiro Ishikawa2, Hiromu Seko3, Yoshito Yoshizaki4, Naonori Ueda5, Hirofumi Tomita1, Yutaka Ishikawa1, Shinsuke Satoh6, Tomoo Ushio7, Kana Koike8, and Yasuhiko Nakada9
Takemasa Miyoshi et al.
  • 1RIKEN Center for Computational Science, Kobe, Japan (
  • 2Japan Meteorological Agency, Tokyo, Japan
  • 3Meteorological Research Institute, Tsukuba, Japan
  • 4Meteorological Satellite Center, Kiyose, Japan
  • 5RIKEN Center for Advanced Intelligence Project, Tokyo, Japan
  • 6National Institute of Information and Communications Technology, Koganei, Japan
  • 7Osaka University, Suita, Japan
  • 8MTI Ltd., Tokyo, Japan
  • 9Tokyo Electric Power Company Holdings, Tokyo, Japan

The Japan’s Big Data Assimilation (BDA) project started in October 2013 and ended its 5.5-year period in March 2019. The direct follow-on project was accepted and started in April 2019 under the Japan Science and Technology Agency (JST) AIP (Advanced Intelligence Project) Acceleration Research, with emphases on the connection with AI technologies, in particular, an integration of DA and AI with high-performance computation (HPC). The BDA project aimed to fully take advantage of “big data” from advanced sensors such as the phased array weather radar (PAWR) and Himawari-8 geostationary satellite, which provide two orders of magnitude more data than the previous sensors. We have achieved successful case studies with newly-developed 30-second-update, 100-m-mesh numerical weather prediction (NWP) system based on the RIKEN’s SCALE model and local ensemble transform Kalman filter (LETKF) to assimilate PAWR in Osaka and Kobe. We have been actively developing the workflow for real-time weather forecasting in Tokyo in summer 2020. In addition, we developed two precipitation nowcasting systems with the every-30-second PAWR data: one with an optical-flow-based system, the other with a deep-learning-based system. We chose the convolutional Long Short Term Memory (Conv-LSTM) as a deep learning algorithm, and found it effective for precipitation nowcasting. The use of Conv-LSTM would lead to an integration of DA and AI with HPC. This presentation will include an overview of the BDA project toward a DA-AI-HPC integration under the new AIP Acceleration Research scheme, and recent progress of the project.

How to cite: Miyoshi, T., Honda, T., Otsuka, S., Amemiya, A., Maejima, Y., Ishikawa, Y., Seko, H., Yoshizaki, Y., Ueda, N., Tomita, H., Ishikawa, Y., Satoh, S., Ushio, T., Koike, K., and Nakada, Y.: Big Data Assimilation: Real-time Workflow for 30-second-update Forecasting and Perspectives toward DA-AI Integration, EGU General Assembly 2020, Online, 4–8 May 2020, EGU2020-2483,, 2020.


Display file

Comments on the display

AC: Author Comment | CC: Community Comment | Report abuse

displays version 1 – uploaded on 08 May 2020, no comments