Aurora
Version: 3
Aurora is a machine learning model that can predict general environmental variables, such as temperature and wind speed.
It is a foundation model, which means that it was first generally trained on a lot of data,
and then can be adapted to specialised environmental forecasting tasks with relatively little data.
We provide four such specialised versions:
one for medium-resolution weather prediction,
one for high-resolution weather prediction,
one for air pollution prediction,
and one for ocean wave prediction.
Please see the documentation of the
Aurora Foundry Python API . Please email AIWeatherClimate@microsoft.com
if you are interested in using Aurora for commercial applications.
For research-related questions or technical support with the open-source version of the model,
please open an issue in the GitHub repository
or reach out to the authors of the paper.
It is a foundation model, which means that it was first generally trained on a lot of data,
and then can be adapted to specialised environmental forecasting tasks with relatively little data.
We provide four such specialised versions:
one for medium-resolution weather prediction,
one for high-resolution weather prediction,
one for air pollution prediction,
and one for ocean wave prediction.
Please see the documentation of the
Aurora Foundry Python API . Please email AIWeatherClimate@microsoft.com
if you are interested in using Aurora for commercial applications.
For research-related questions or technical support with the open-source version of the model,
please open an issue in the GitHub repository
or reach out to the authors of the paper.
Resources
- Documentation of the Aurora Foundry Python API
- A full-fledged example that runs the model on Foundry .
- Implementation of the Aurora model
- Documentation of the Aurora implementation
- Paper with detailed evaluation
Quickstart
First install the model:pip install microsoft-aurora
from aurora import Batch
from aurora.foundry import BlobStorageChannel, FoundryClient, submit
initial_condition = Batch(...) # Create initial condition for the model.
for pred in submit(
initial_condition,
model_name="aurora-0.25-finetuned",
num_steps=4, # Every step predicts six hours ahead.
foundry_client=FoundryClient(
endpoint="https://endpoint/",
token="ENDPOINT_TOKEN",
),
# Communication with the endpoint happens via an intermediate blob storage container. You
# will need to create one and generate an URL with a SAS token that has both read and write
# rights.
channel=BlobStorageChannel(
"https://storageaccount.blob.core.windows.net/container?<READ_WRITE_SAS_TOKEN>"
),
):
pass # Do something with `pred`, which is a `Batch`.
License
This model and the associated model weights are released under the MIT licence .Security
See SECURITY .Responsible AI Transparency Documentation
An AI system includes not only the technology, but also the people who will use it, the people who will be affected by it, and the environment in which it is deployed.Creating a system that is fit for its intended purpose requires an understanding of how the technology works, its capabilities and limitations, and how to achieve the best performance.
Microsoft has a broad effort to put our AI principles into practice. To find out more, see Responsible AI principles from Microsoft .
Limitations
Although Aurora was trained to accurately predict future weather, air pollution, and ocean waves,Aurora is based on neural networks, which means that there are no strict guarantees that predictions will always be accurate.
Altering the inputs, providing a sample that was not in the training set,
or even providing a sample that was in the training set but is simply unlucky may result in arbitrarily poor predictions.
In addition, even though Aurora was trained on a wide variety of data sets,
it is possible that Aurora inherits biases present in any one of those data sets.
A forecasting system like Aurora is only one piece of the puzzle in a weather prediction pipeline,
and its outputs are not meant to be directly used by people or businesses to plan their operations.
A series of additional verification tests are needed before it can become operationally useful.
Data
The models included in the code have been trained on a variety of publicly available data.A description of all data, including download links, can be found in Supplementary C of the paper .
The checkpoints include data from ERA5, CMCC, IFS-HR, HRES T0, GFS T0, and GFS forecasts.
Trademarks
This project may contain trademarks or logos for projects, products, or services.Authorized use of Microsoft trademarks or logos is subject to and must follow Microsoft's Trademark & Brand Guidelines .
Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship.
Any use of third-party trademarks or logos are subject to those third-party's policies.
All versions of Aurora were extensively evaluated by evaluating predictions on data not seen during training.
These evaluations not only compare measures of accuracy, such as the root mean square error and anomaly correlation coefficient,
but also look at the behaviour in extreme situations, like extreme heat and cold, and rare events, like Storm Ciarán in 2023.
These evaluations are the main topic of the paper . Note: The documentation included here is for informational purposes only and is not intended to supersede the applicable license terms.
These evaluations not only compare measures of accuracy, such as the root mean square error and anomaly correlation coefficient,
but also look at the behaviour in extreme situations, like extreme heat and cold, and rare events, like Storm Ciarán in 2023.
These evaluations are the main topic of the paper . Note: The documentation included here is for informational purposes only and is not intended to supersede the applicable license terms.
Model Specifications
LicenseMit
Last UpdatedApril 2025
Input TypeData
Output TypeData
PublisherMicrosoft
Languages1 Language