|
|
--- |
|
|
license: apache-2.0 |
|
|
--- |
|
|
|
|
|
<img src="ACE-logo.png" alt="Logo for the ACE Project" style="width: auto; height: 50px;"> |
|
|
|
|
|
# HiRO-ACE |
|
|
|
|
|
The HiRO-ACE framework enables efficient generation of 3 km precipitation fields over decades of simulated climate and arbitrary regions of the globe. |
|
|
HiRO (High Resolution Output) is a diffusion model which generates downscaled fields at 3 km resolution from 100 km resolution inputs. The HiRO checkpoint included in this model generates 6-hourly averaged surface precipitation rates at 3 km resolution. The Ai2 Climate Emulator (ACE) is a family of models designed to simulate atmospheric variability from the time scale of days to centuries. For usage with the HiRO downscaling model, we include a checkpoint for ACE2S. Compared to previous ACE models, ACE2S uses an updated training procedure and can generate stochastic predictions. For more details, please see the accompanying HiRO-ACE paper linked below. |
|
|
|
|
|
### Quick links |
|
|
|
|
|
- 📃 [Paper](https://arxiv.org/pdf/2512.18224) |
|
|
- 💻 [Code](https://github.com/ai2cm/ace) |
|
|
- 💬 [Docs](https://ai2-climate-emulator.readthedocs.io/en/stable/) |
|
|
- 📂 [All ACE Models](https://huggingface.co/collections/allenai/ace-67327d822f0f0d8e0e5e6ca4) |
|
|
|
|
|
|
|
|
### Inference quickstart |
|
|
|
|
|
1. Download this repository. Optionally, you can just download a subset of the `forcing_data` and `initial_conditions` for the period you are interested in. |
|
|
|
|
|
2. Update paths in the `inference_config.yaml`. Specifically, update `experiment_dir`, `checkpoint_path`, `initial_condition.path` and `forcing_loader.dataset.path`. |
|
|
|
|
|
3. Install code dependencies with `pip install fme`. |
|
|
|
|
|
4. Run ACE inference with `python -m fme.ace.inference inference_config.yaml`. |
|
|
|
|
|
5. Update paths in the `downscaling_config.yaml`. Specifically, update `experiment_dir`, `model.checkpoint_path`, and `data.coarse`. `data.coarse` data path(s) should point to the saved ACE inference output from step 4. |
|
|
|
|
|
|
|
|
### Strengths and weaknesses |
|
|
|
|
|
#### ACE2S |
|
|
The strengths of ACE2S are: |
|
|
- stochastic (generative) emulator of 100km coarsened X-SHiELD |
|
|
- improved small scale variability compared to deterministic ACE2 (especially surface precipitation) |
|
|
- exact conservation of global dry air mass and moisture |
|
|
- low time-mean biases for most variables |
|
|
- compatible with HiRO model with no observed degradation |
|
|
|
|
|
Some known weaknesses of ACE2S are: |
|
|
- trained only on 9 years of X-SHiELD (2014-2022) |
|
|
- not expected to generalize outside of the limited forcing conditions used during training (e.g., SSTs and CO2) |
|
|
- not suitable for weather forecasting (e.g., not trained on reanalysis data only climate model output) |
|
|
- model was not tested as rigorously as ACE2-ERA5 (e.g., cannot comment on stratospheric variability, etc) |
|
|
- overestimation of tropical cyclone generation compared to X-SHiELD |
|
|
- some aspects of the pre-training and fine-tuning methodologies did not have ablations |
|
|
- exactly pre-training and fine-tuning methodologies are subject to potential significant changes for future versions |
|
|
|
|
|
## License |
|
|
|
|
|
This model is licensed under Apache 2.0. It is intended for research and educational use in accordance with Ai2's [Responsible Use Guidelines](https://allenai.org/responsible-use). |
|
|
|
|
|
|
