6 papers
Scale-Recursive Rectified Flows for Few-Step Precipitation Ensembles
Shunya Nagashima, Takumi Bannai
Fine-resolution precipitation estimates support flood risk assessment and water management, but coarse satellite products cannot resolve rainfall within each grid cell. Generative…
Physics-Guided Flow-Map Matching for Precipitation Nowcasting
Shunya Nagashima, Takumi Bannai, Makoto Misaizu +3
Precipitation nowcasting, generating future radar fields from past observations, is critical for flood warning and disaster response. It is also a demanding benchmark for spatiotem…
Learning Where to Look: A Shared Relative-Alignment Module for Time-Series Forecasting and PPG-to-Vital-Sign Reconstruction
Ragamayi Puli, Shunya Nagashima
PPG-to-vital-sign reconstruction turns a wrist-worn photoplethysmogram into clinical waveforms such as the ECG. Long-horizon multivariate time-series forecasting underpins planning…
Neural Stochastic Processes for Satellite Precipitation Refinement
Shunya Nagashima, Takumi Bannai, Shuitsu Koyama +2
Accurate precipitation estimation is critical for flood forecasting, water resource management, and disaster preparedness. Satellite products provide global hourly coverage but con…
A Decomposition-based State Space Model for Multivariate Time-Series Forecasting
Shunya Nagashima, Shuntaro Suzuki, Shuitsu Koyama +1
Multivariate time series (MTS) forecasting is crucial for decision-making in domains such as weather, energy, and finance. It remains challenging because real-world sequences inter…
PENGUIN: General Vital Sign Reconstruction from PPG with Flow Matching State Space Model
Shuntaro Suzuki, Shuitsu Koyama, Shinnosuke Hirano +1
Photoplethysmography (PPG) plays a crucial role in continuous cardiovascular health monitoring as a non-invasive and cost-effective modality. However, PPG signals are susceptible t…