# Precipitation Downscaling Using Foundation Model-Conditioned Diffusion

arXiv: https://arxiv.org/abs/2608.25858 · HTML: https://mlsanity.com/paper/2608.25858/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Flow matching, time series and science, one of 14 directions in Diffusion models.
- Builds on 21 of its 32 references that are in the map.
- First posted on arXiv 26 Aug 2026.

## Placed in

- Diffusion models / [Flow matching, time series and science](https://mlsanity.com/diffusion/flow-matching-time-series-and-science/)

## Builds on (most cited first, 21 of 21)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Image Super-Resolution via Iterative Refinement](https://mlsanity.com/paper/2104.07636/) (2021)
- [Unleashing Text-to-Image Diffusion Models for Visual Perception](https://mlsanity.com/paper/2303.02153/) (2023)
- [State of the Art on Diffusion Models for Visual Computing](https://mlsanity.com/paper/2310.07204/) (2023)
- [Residual Corrective Diffusion Modeling for Km-scale Atmospheric Downscaling](https://mlsanity.com/paper/2309.15214/) (2023)
- [ClimateLearn: Benchmarking Machine Learning for Weather and Climate Modeling](https://mlsanity.com/paper/2307.01909/) (2023)
- [AtmoRep: A stochastic model of atmosphere dynamics using large scale representation learning](https://mlsanity.com/paper/2308.13280/) (2023)
- [Diffusion Model with Cross Attention as an Inductive Bias for Disentanglement](https://mlsanity.com/paper/2402.09712/) (2024)
- [Intercomparison of Machine Learning Methods for Statistical Downscaling: The Case of Daily and Extreme Precipitation](https://mlsanity.com/paper/1702.04018/) (2017)
- [Dynamical-generative downscaling of climate model ensembles](https://mlsanity.com/paper/2410.01776/) (2024)
- [TRU-NET: A Deep Learning Approach to High Resolution Prediction of Rainfall](https://mlsanity.com/paper/2008.09090/) (2020)
- [Precipitation Downscaling with Spatiotemporal Video Diffusion](https://mlsanity.com/paper/2312.06071/) (2023)
- [Machine learning emulation of precipitation from km-scale UK regional climate simulations using a diffusion model](https://mlsanity.com/paper/2407.14158/) (2024)
- [DiffESM: Conditional Emulation of Temperature and Precipitation in Earth System Models with 3D Diffusion Models](https://mlsanity.com/paper/2409.11601/) (2024)
- [Can AI be enabled to dynamical downscaling? A Latent Diffusion Model to mimic km-scale COSMO5.0CLM9 simulations](https://mlsanity.com/paper/2406.13627/) (2024)
- [ORBIT-2: Scaling Exascale Vision Foundation Models for Weather and Climate Downscaling](https://mlsanity.com/paper/2505.04802/) (2025)
- [Downscaling weather forecasts from Low- to High-Resolution with Diffusion Models](https://mlsanity.com/paper/2604.03303/) (2026)

## Abstract (arXiv)

High-resolution precipitation fields are essential for hydrological impact assessment, yet global climate model outputs are too coarse and biased for direct use. AI-based statistical downscaling with diffusion models offers a promising approach, but the mechanism by which large-scale atmospheric predictors condition generation remains largely unexplored. We investigate three conditioning strategies for a denoising diffusion probabilistic model applied to daily precipitation downscaling: channel concatenation of upsampled coarse predictors, cross-attention conditioning with a learned convolutional encoder, and cross-attention conditioning with the frozen encoder of the pretrained Prithvi WxC weather foundation model. All strategies are evaluated against an unconditioned baseline under identical conditions using probabilistic, distributional, spectral, and extreme-event metrics for the Colorado River Basin. Concatenation conditioning achieves the lowest point-wise CRPS and MSE, but tends to produce over-smoothed fields that suppress high-intensity events. In contrast, cross-attention conditioning provides substantially better distributional realism and modest improvements in spectral fidelity. Improvements are greatest for extremes: the Prithvi-WxC conditioned model retains over half of >100mm/day events, although estimates are uncertain due to limited samples. When trained on the full dataset, the learned convolutional model performs similarly to the foundation model-conditioned approach while requiring lower computational resources. However, the Prithvi-WxC-conditioned model achieves comparable performance with only five years of training data. These results indicate that cross-attention conditioning offers advantages over simple concatenation for probabilistic precipitation downscaling, and that pre-trained foundation model representations may offer benefits in data-limited settings.