Multidisciplinary and Interdisciplinary (M)
Session Sub-category General Geosciences, Information Geosciences & Simulations(GI)
Session ID M-GI34
Title Data-driven approaches for weather and hydrological predictions
Short Title Data driven study in weather prediction
Main Convener Name Shunji Kotsuki
Affiliation Center for Environmental Remote Sensing, Chiba University
Co-Convener 1 Name Carolynne Hultquist
Affiliation University of Canterbury
Co-Convener 2 Name Yohei Sawada
Affiliation The University of Tokyo
Co-Convener 3 Name Ana Carolina Vaz
Affiliation Instituto Nacional de Pesquisas Oceanicas
Co-Convener 4 Name Thomas Sekiyama
Affiliation Meteorological Research Institute
Co-Convener 5 Name Yuki Yasuda
Affiliation Japan Agency for Marine-Earth Science and Technology
Session Language 
E
Scope 
In the digital era, data-driven techniques are transforming our understanding and prediction capabilities of complex earth systems. This session aims to explore the cutting-edge methodological and applicational studies for weather, climate and hydrological predictions. Key themes includes: (1) methodological studies to deepen data-driven approaches for geoscience problems, (2) machine/deep learning studies applied for extreme weather-related disasters, (3) climate predictive analysis to discern climate variability, trends, and anomalies, (4) integrating remote sensing and ground data to refine prediction models. This session aims to foster a rich dialogue among experts, highlighting both the advancements and challenges in data-driven environmental modeling. Participants will gain insights into current best practices and envision the future trajectory of this rapidly evolving domain.
Presentation Format Oral and Poster presentation
Time Presentation No Title Presenter
Oral Presentation May 25 AM1
9:00 - 9:15 MGI34-01 Spatio-Temporal Radar-Gauge Rainfall Data Assimilation for Extreme Events: A Case Study of Taipei Taiwan Sumriti Ranjan Patra
9:15 - 9:30 MGI34-02 Precipitation “Extremeness” Assessment Relative to the Environmental Field: Analysis of Linear Rainband Events Using Diffusion Models Yuki H. Takano
9:30 - 9:45 MGI34-03 Precipitation Downscaling via Knowledge-guided Mixture of Experts for Explicit Representation of Physical Mechanisms Takumi Bannai
9:45 - 10:00 MGI34-04 Downscaling emulator with Classifier Free Diffusion Guidance Model Ryo Kaneko
10:00 - 10:15 MGI34-05 Enhancing Ensemble Temperature Forecasts with CNN: Analyzing AI-based Post-processing through Forecast Information–Noise Error Decomposition Takuya Inoue
10:15 - 10:30 MGI34-06 Data-Driven Regional Weather Prediction for Japan: Exploring the Role of High-Resolution Reanalysis and Customized Loss Functions Hiroki Ikeuchi
Oral Presentation May 25 AM2
10:45 - 11:00 MGI34-07 Baecast: Visualizing Ground-Level Landscapes from Meteorological Conditions with Generative Models Daiko Kishikawa
11:00 - 11:15 MGI34-08 AMANE: A Suite of AI Foundation Models for Advanced Geostationary Satellite Analysis Hironobu Iwabuchi
11:15 - 11:30 MGI34-09 Robust gap-filling of coastal wind and wave records with pattern-based machine learning Nan-Jing Wu
11:30 - 11:45 MGI34-10 Influence of Training Data Dependence in Machine-Learning Front Detection on Long-Term Trends of Frontal Statistics Takumi Matsuda
11:45 - 12:00 MGI34-11 Koopman Analysis of Sea Surface Temperature with a Signature Kernel Nozomi Sugiura
12:00 - 12:15 MGI34-12 Spatiotemporal Prediction and Generation with Scale-Aware Diffusion via Renormalization Group Yuki Yasuda
Presentation No Title Presenter
Poster Presentation May 25 PM3
MGI34-P01 How Similar Is Similar Enough? Evaluating Machine Learning Model Transferability Across Forested Soil Sites with Comparable Properties Young gu Her
MGI34-P02 Data-driven forecasting of wind vectors over the Tohoku region by convolutional LSTM trained on AMeDAS observations with regional NWP inputs Keigo Sato
MGI34-P03 Estimating Hydraulic Conductivity of Fractured Rock Masses Using Deep Neural Networks: A Case Study from Taiwan Shih-Meng Hsu
MGI34-P04 Seasonal Amplification of Climate Extreme Influence on Inland Water Quality in South Korea Young Jun Kim