# IceDiff: High Resolution and High-Quality Sea Ice Forecasting with Generative Diffusion Prior

arXiv: https://arxiv.org/abs/2410.09111 · HTML: https://mlsanity.com/paper/2410.09111/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Flow matching, time series and science, one of 14 directions in Diffusion models.
- Builds on 15 of its 33 references that are in the map.
- First posted on arXiv 10 Oct 2024.

## 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, 15 of 15)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Swin Transformer V2: Scaling Up Capacity and Resolution](https://mlsanity.com/paper/2111.09883/) (2021)
- [Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation](https://mlsanity.com/paper/2105.05537/) (2021)
- [Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation](https://mlsanity.com/paper/2003.13659/) (2020)
- [Generative Diffusion Prior for Unified Image Restoration and Enhancement](https://mlsanity.com/paper/2304.01247/) (2023)
- [A Deep Journey into Super-resolution: A survey](https://mlsanity.com/paper/1904.07523/) (2019)
- [Stochastic Super-Resolution for Downscaling Time-Evolving Atmospheric Fields with a Generative Adversarial Network](https://mlsanity.com/paper/2005.10374/) (2020)
- [SwinVRNN: A Data-Driven Ensemble Forecasting Model via Learned Distribution Perturbation](https://mlsanity.com/paper/2205.13158/) (2022)
- [SwinRDM: Integrate SwinRNN with Diffusion Model towards High-Resolution and High-Quality Weather Forecasting](https://mlsanity.com/paper/2306.03110/) (2023)
- [Unsupervised Real Image Super-Resolution via Generative Variational AutoEncoder](https://mlsanity.com/paper/2004.12811/) (2020)
- [Sea Ice Forecasting using Attention-based Ensemble LSTM](https://mlsanity.com/paper/2108.00853/) (2021)
- [MT-IceNet -- A Spatial and Multi-Temporal Deep Learning Model for Arctic Sea Ice Forecasting](https://mlsanity.com/paper/2308.04511/) (2023)
- [Taming Generative Diffusion Prior for Universal Blind Image Restoration](https://mlsanity.com/paper/2408.11287/) (2024)

## Built on by (most cited first, 3 of 3)

- [SIFM: A Foundation Model for Multi-granularity Arctic Sea Ice Forecasting](https://mlsanity.com/paper/2410.14732/) (2024)
- [MODS: Multi-source Observations Conditional Diffusion Model for Meteorological State Downscaling](https://mlsanity.com/paper/2506.14798/) (2025)
- [Earth Science Foundation Models: From Perception to Reasoning and Discovery](https://mlsanity.com/paper/2605.12542/) (2026)

## Abstract (arXiv)

Variation of Arctic sea ice has significant impacts on polar ecosystems, transporting routes, coastal communities, and global climate. Tracing the change of sea ice at a finer scale is paramount for both operational applications and scientific studies. Recent pan-Arctic sea ice forecasting methods that leverage advances in artificial intelligence has made promising progress over numerical models. However, forecasting sea ice at higher resolutions is still under-explored. To bridge the gap, we propose a two-staged deep learning framework, IceDiff, to forecast sea ice concentration at finer scales. IceDiff first leverages an independently trained vision transformer to generate coarse yet superior forecasting over previous methods at a regular 25km x 25km grid. This high-quality sea ice forecasting can be utilized as reliable guidance for the next stage. Subsequently, an unconditional diffusion model pre-trained on sea ice concentration maps is utilized for sampling down-scaled sea ice forecasting via a zero-shot guided sampling strategy and a patch-based method. For the first time, IceDiff demonstrates sea ice forecasting with the 6.25km x 6.25km resolution. IceDiff extends the boundary of existing sea ice forecasting models and more importantly, its capability to generate high-resolution sea ice concentration data is vital for pragmatic usages and research.