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
• 💻 Code
• 💬 Docs
• 📂 All ACE Models

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 for more details). An example of global downscaling is also provided in hiro_downscaling_ace2s_global_output.yaml.

5. 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.

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).