An intercomparison of generative machine learning methods for downscaling precipitation at fine spatial scales
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912767567462400 |
|---|---|
| author | Ward-Leikis, Bryn Rampal, Neelesh Koh, Yun Sing Gibson, Peter B. Liu, Hong-Yang Kitsios, Vassili Meyers, Tristan Adie, Jeff Juntao, Yang Sherwood, Steven C. |
| author_facet | Ward-Leikis, Bryn Rampal, Neelesh Koh, Yun Sing Gibson, Peter B. Liu, Hong-Yang Kitsios, Vassili Meyers, Tristan Adie, Jeff Juntao, Yang Sherwood, Steven C. |
| contents | Machine learning (ML) offers a computationally efficient approach for generating large ensembles of high-resolution climate projections, but deterministic ML methods often smooth fine-scale structures and underestimate extremes. While stochastic generative models show promise for predicting fine-scale weather and extremes, few studies have compared their performance under present-day and future climates. This study compares a previously developed conditional Generative Adversarial Network (cGAN) with an intensity constraint against different configurations of diffusion models for downscaling daily precipitation from a regional climate model (RCM) over Aotearoa New Zealand. Model skill is comprehensively assessed across spatial structure, distributional metrics, means, extremes, and their respective climate change signals. Both generative approaches outperform the deterministic baseline across most metrics and exhibit similar overall skill. Diffusion models better predict the fine-scale spatial structure of precipitation and the length of dry spells, but underestimate climate change signals for extreme precipitation compared to the ground truth RCMs. In contrast, cGANs achieve comparable skill for most metrics while better predicting the overall precipitation distribution and climate change responses for extremes at a fraction of the computational cost. These results demonstrate that while diffusion models can readily generate predictions with greater visual "realism", they do not necessarily better preserve climate change responses compared to cGANs with intensity constraints. At present, incorporating constraints into diffusion models remains challenging compared to cGANs, but may represent an opportunity to further improve skill for predicting climate change responses. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_13987 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | An intercomparison of generative machine learning methods for downscaling precipitation at fine spatial scales Ward-Leikis, Bryn Rampal, Neelesh Koh, Yun Sing Gibson, Peter B. Liu, Hong-Yang Kitsios, Vassili Meyers, Tristan Adie, Jeff Juntao, Yang Sherwood, Steven C. Atmospheric and Oceanic Physics Machine learning (ML) offers a computationally efficient approach for generating large ensembles of high-resolution climate projections, but deterministic ML methods often smooth fine-scale structures and underestimate extremes. While stochastic generative models show promise for predicting fine-scale weather and extremes, few studies have compared their performance under present-day and future climates. This study compares a previously developed conditional Generative Adversarial Network (cGAN) with an intensity constraint against different configurations of diffusion models for downscaling daily precipitation from a regional climate model (RCM) over Aotearoa New Zealand. Model skill is comprehensively assessed across spatial structure, distributional metrics, means, extremes, and their respective climate change signals. Both generative approaches outperform the deterministic baseline across most metrics and exhibit similar overall skill. Diffusion models better predict the fine-scale spatial structure of precipitation and the length of dry spells, but underestimate climate change signals for extreme precipitation compared to the ground truth RCMs. In contrast, cGANs achieve comparable skill for most metrics while better predicting the overall precipitation distribution and climate change responses for extremes at a fraction of the computational cost. These results demonstrate that while diffusion models can readily generate predictions with greater visual "realism", they do not necessarily better preserve climate change responses compared to cGANs with intensity constraints. At present, incorporating constraints into diffusion models remains challenging compared to cGANs, but may represent an opportunity to further improve skill for predicting climate change responses. |
| title | An intercomparison of generative machine learning methods for downscaling precipitation at fine spatial scales |
| topic | Atmospheric and Oceanic Physics |
| url | https://arxiv.org/abs/2512.13987 |