| --- |
| license: apache-2.0 |
| library_name: fme |
| --- |
| <img src="ACE-logo.png" alt="Logo for the ACE Project" style="width: auto; height: 50px;"> |
|
|
| # HiRO-ACEv2 |
|
|
| The HiRO-ACEv2 framework enables efficient generation of 3 km precipitation, 10 m eastward and northward winds, and sea level pressure 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 HiROv2 checkpoint included in this model generates 6-hourly averaged surface precipitation rates at 3 km resolution, and instantaneous 10 m eastward and northward winds and sea level pressure at 6-hour frequency. 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 HiROv2 downscaling model, we include a checkpoint for ACE2S-X-SHiELD. For more details, please see the accompanying HiRO-ACEv2 paper linked below. |
|
|
| ### Quick links |
|
|
| - 📃 [Paper](http://arxiv.org/abs/2610.17693) |
| - 💻 [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. Install code dependencies with `pip install fme`. |
|
|
| 3. Update paths in the ACE inference config file `ace2s_inference_config_global.yaml`. Specifically, update `experiment_dir`, `checkpoint_path`, `initial_condition.path` and `forcing_loader.dataset.path`. |
|
|
| 4. Update paths in the HiROv2 downscaling inference config file `hiro_downscaling_ace2s_pnw_output.yaml`. Specifically, update `experiment_dir`, `model.checkpoint_path`, and `data.coarse`. The directory path in `data.coarse` should point to the same ACE inference `experiment_dir` from step 3. Optionally, if you wish to change the region and/or time selection of the area(s) to downscale you may edit those in the downscaling config (see [downscaling inference docs](https://ai2-climate-emulator.readthedocs.io/en/latest/downscaling_inference.html) for more details). An example of global downscaling is also provided in `hiro_downscaling_ace2s_global_output.yaml`. |
|
|
| 4. Run the script `run-hiro-ace.sh`. |
|
|
|
|
| ### Strengths and weaknesses |
|
|
| #### ACE2S-X-SHiELD |
| The strengths of ACE2S-X-SHiELD 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 relative to the 10-year training data available |
| - compatible with HiRO model with no observed degradation |
| - similar tropical cyclone generation to X-SHiELD |
|
|
| Some known weaknesses of ACE2S-X-SHiELD 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., past/future SSTs and CO2) |
| - may not produce statistically independent and representative samples of the base X-SHiELD model when run for significantly longer than 9 years |
| - 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) |
| - 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 |
|
|
| #### HiROv2 |
| The strengths of HiROv2 are: |
| - Quickly generates surface precipitation rate, 10 m eastward and northward winds, and sea level almost anywhere on the globe analogous to X-SHiELD 3 km output |
| - Reproduces surface precipitation rate, 10 m winds, and sea level pressure distribution of X-SHiELD out to the 99.9999th percentile and generates realistic fields for snapshots of events with high regional impacts (ex. tropical cyclones, downscaled winds, atmospheric rivers) |
| - Low time-mean biases against X-SHiELD |
| - Recovers time-mean characteristics of precipitation related to topography |
| - Stochastic for easy ensemble generation of small-scale variability |
|
|
| Some known weaknesses of HiROv2 are: |
| - Not expected to generalize to climates outside of the 10-year training dataset |
| - Only produces precipitation, wind, and pressure features representative of X-SHiELD data, not observations |
| - Not trained or tested outside of 66S -- 70N, and cannot run outside of 88S or 88N |
| - Downscaling regions larger than the 16x16 1-degree patch size used for training will have discontinuities for patch overlaps of 0 or some blending artifacting from averaging in the overlap region for overlaps > 0 |
|
|
| ## 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). |
|
|
|
|
| ## Attribution |
| This model is trained using data processed from X-SHIELD (eXperimental System for High-resolution prediction on Earth-to-Local Domains) provided by the Geophysical Fluid Dynamics Laboratory (GFDL). |
|
|
