RainODE: Continuous-Time Precipitation Forecasting with Latent Neural ODEs
2026-06-29 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors propose RainODE, a new method for predicting rain that treats precipitation changes continuously over time using a Neural Ordinary Differential Equation (ODE). This helps capture large-scale movement of rain systems more smoothly. To avoid overly simple predictions, they add a stochastic module based on Brownian Bridges that models smaller, random changes in rain intensity. Their combined approach can predict precipitation at any moment with sharper details and performs well on several weather datasets.
precipitation forecastingNeural ODEcontinuous-time dynamical systemadvective motionBrownian Bridgestochastic modelinglatent spacetemporal resolutionover-smoothingRadar-based precipitation dataset
Authors
Yeeun Seong, Doyi Kim, Minseok Seo, Changick Kim
Abstract
In precipitation forecasting, not only accuracy but also temporal resolution is critical. However, increasing temporal resolution is constrained by observational limitations and the computational cost of dense discrete modeling. To overcome this limitation, we reformulate precipitation forecasting as a continuous-time dynamical system and propose RainODE, a framework that models precipitation evolution in latent space using a Neural ODE. This formulation enables derivative-consistent temporal dynamics and captures the dominant large-scale advective motion of precipitation systems. Nevertheless, a purely deterministic ODE struggles to represent non-advective intensity changes such as localized growth, decay, and sub-grid variability, often leading to over-smoothed predictions. To address this issue, we introduce a stochastic source modeling module based on a Brownian Bridge formulation, which refines residual intensity variations and restores fine-grained structures while preserving advective consistency. By combining deterministic continuous dynamics with stochastic refinement, RainODE enables arbitrary-time inference while maintaining sharp predictions. Experiments on SEVIR and the newly introduced Radar-based Precipitation Integrated Dataset (RAPID) demonstrate consistent improvements across multiple temporal intervals and precipitation regimes. The code is available at https://github.com/SeongYE/RainODE.