README.md

metadata

license: apache-2.0

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
• 💻 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. 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.