Probabilistic Super-Resolution for Urban Micrometeorology via a Schrödinger Bridge

2025/10/14 by Yuki Yasuda, Yasuda, Yuki, Ryo Onishi +1
Engineering · Environmental Science · #Advanced Image Fusion Techniques #Atmospheric and Oceanic Physics (physics.ao-ph) #FOS: Computer and information sciences #FOS: Physical sciences #Machine Learning (cs.LG) #Remote Sensing and LiDAR Applications #Remote Sensing in Agriculture

paper · pdf · doi:10.48550/arxiv.2510.12148

openalex publication_date 2025/10/14 · openalex created_date 2025/10/17 · openalex updated_date 2026/07/28

Abstract

This study employs a neural network that represents the solution to a Schrödinger bridge problem to perform super-resolution of 2-m temperature in an urban area. Schrödinger bridges generally describe transformations between two data distributions based on diffusion processes. We use a specific Schrödinger-bridge model (SM) that directly transforms low-resolution data into high-resolution data, unlike denoising diffusion probabilistic models (simply, diffusion models; DMs) that generate high-resolution data from Gaussian noise. Low-resolution and high-resolution data were obtained from separate numerical simulations with a physics-based model under common initial and boundary conditions. Compared with a DM, the SM attains comparable accuracy at one-fifth the computational cost, requiring 50 neural-network evaluations per datum for the DM and only 10 for the SM. Furthermore, high-resolution samples generated by the SM exhibit larger variance, implying superior uncertainty quantification relative to the DM. Owing to the reduced computational cost of the SM, our results suggest the feasibility of real-time ensemble micrometeorological prediction using SM-based super-resolution.

Citations

• Zero-Shot Super-Resolution from Unstructured Data Using a Transformer-Based Neural Operator for Urban Micrometeorology
• A Generative Framework for Probabilistic, Spatiotemporally Coherent Downscaling of Climate Simulation
• Speed-accuracy relations for diffusion models: Wisdom from nonequilibrium thermodynamics and optimal transport
• Can AI be enabled to dynamical downscaling? A Latent Diffusion Model to mimic km-scale COSMO5.0_CLM9 simulations
• Flow map matching with stochastic interpolants: A mathematical framework for consistency models
• Probabilistic Forecasting with Stochastic Interpolants and Föllmer Processes
• Understanding Diffusion Models by Feynman's Path Integral
• Implicit Image-to-Image Schrodinger Bridge for Image Restoration
• Fast, Scale-Adaptive, and Uncertainty-Aware Downscaling of Earth System Model Fields with Generative Machine Learning
• Diffusion Model-based Probabilistic Downscaling for 180-year East Asian Climate Reconstruction
• Stochastic interpolants with data-dependent couplings
• Kaushikreddym/CasCorrDiff: CasCorrDiff v1.0.0
• Fourier neural operator for real-time simulation of 3D dynamic urban microclimate
• Stochastic Interpolants: A Unifying Framework for Flows and Diffusions
• PIGNN-CFD: A physics-informed graph neural network for rapid predicting urban wind field defined on unstructured mesh
• Flow Matching for Generative Modeling
• Elucidating the Design Space of Diffusion-Based Generative Models
• Palette: Image-to-Image Diffusion Models
• Likelihood Training of Schrödinger Bridge using Forward-Backward SDEs Theory
• Diffusion Schr "odinger Bridge with Applications to Score-Based\n Generative Modeling
• Image Super-Resolution via Iterative Refinement
• Fast and accurate learned multiresolution dynamical downscaling for precipitation
• Score-Based Generative Modeling through Stochastic Differential Equations
• Denoising Diffusion Implicit Models
• Denoising Diffusion Probabilistic Models
• FiLM: Visual Reasoning with a General Conditioning Layer
• Attention Is All You Need
• Accurate Image Super-Resolution Using Very Deep Convolutional Networks
• Deep Unsupervised Learning using Nonequilibrium Thermodynamics
• A Connection Between Score Matching and Denoising Autoencoders
• Super-resolution image reconstruction: a technical overview

Related

• Super-Resolution of Near-Surface Temperature Utilizing Physical Quantities for Real-Time Prediction of Urban Micrometeorology
• Zero-Shot Super-Resolution from Unstructured Data Using a Transformer-Based Neural Operator for Urban Micrometeorology
• Enhancing Weather Predictions: Super-Resolution via Deep Diffusion Models
• Super-Resolution of Three-Dimensional Temperature and Velocity for Building-Resolving Urban Micrometeorology Using Physics-Guided Convolutional Neural Networks with Image Inpainting Techniques
• Two-Stage Super-Resolution Simulation Method of Three-Dimensional Street-Scale Atmospheric Flows for Real-Time Urban Micrometeorology Prediction