Joint Research on Precipitation Estimation to Be Presented at AGU26
Joint research on precipitation estimation will be presented as a poster at AGU26, the annual meeting of the American Geophysical Union (AGU).
The presentation is based on joint research by Takumi Bannai of the Strategic Business Division, Data Lead Business Department at LTS, Inc. (Representative Director of ME-Lab Japan, Inc.), Yuki Kita, Representative Director of Gaia Vision Inc., and Shunya Nagashima, Director and CTO of Neurogica Inc.
Research Overview
This research proposes a method for applying an AI model trained in regions with extensive radar observations to regions where radar observations are limited. By adapting the model using only local rain-gauge data, the study aims to estimate fine-scale precipitation distributions without using local radar data for training.
This research was conducted with support from the Ministry of Land, Infrastructure, Transport and Tourism's FY2022 Small and Medium-sized Enterprise Innovation Creation Promotion Program (SBIR Phase 3).
Presentation Title
From Radar-Rich to Radar-Sparse Regions: Gauge-Only Adaptation of a Probabilistic Precipitation Downscaler without Local Radar Supervision
Presentation Details
| Item | Details |
|---|---|
| Meeting | AGU26 (American Geophysical Union Annual Meeting) |
| Dates | December 7–11, 2026 |
| Venue | Moscone Center, San Francisco, USA, and online |
| Presenter | Takumi Bannai |
| Format | Poster presentation |
| Presentation time | December 10, 2026, 8:30 a.m.–12:00 p.m. (PST) |
| Session | H41T: Space-Based Precipitation Observations: Innovations for Science and Applications III Poster |
Official meeting website: AGU26