Welcome to MLAir’s documentation!¶
This is the documentation of the MLAir package.

MLAir Logo¶
MLAir (Machine Learning on Air data) is an environment that simplifies and accelerates the creation of new machine learning (ML) models for the analysis and forecasting of meteorological and air quality time series.
Contents:
- Install MLAir
- Getting started with MLAir
- Default Workflow
- Custom Model
- Data Handler
- Customised Run Module and Workflow
- Defaults
- Changelog
- v2.4.0 - 2023-06-30- IFS data and bias-corrected evaluation
- v2.3.0 - 2022-11-25 - new models and plots
- v2.2.0 - 2022-08-16 - new data sources and python3.9
- v2.1.0 - 2022-06-07 - new evaluation metrics and improved training
- v2.0.0 - 2022-04-08 - tf2 usage, new model classes, and improved uncertainty estimate
- v1.5.0 - 2021-11-11 - new uncertainty estimation
- v1.4.0 - 2021-07-27 - new model classes and data handlers, improved usability and transparency
- v1.3.0 - 2021-02-24 - competitors and improved transformation
- v1.2.1 - 2021-02-08 - bug fix for recursive import error
- v1.2.0 - 2020-12-18 - parallel preprocessing and improved data handlers
- v1.1.0 - 2020-11-18 - hourly resolution support and new data handlers
- v1.0.0 - 2020-10-08 - official release of new version 1.0.0
- v0.12.2 - 2020-10-01 - HDFML support
- v0.12.1 - 2020-09-28 - examples in notebook
- v0.12.0 - 2020-09-21 - Documentation and Bugfixes
- v0.11.0 - 2020-08-24 - Advanced Data Handling for MLAir
- v0.10.0 - 2020-07-15 - MLAir is official name, Workflows, easy Model plug-in
- v0.9.0 - 2020-04-15 - faster bootstraps, extreme value upsamling
- API Reference