MLAir (v1.0.0) - a tool to enable fast and flexible machine learning on air data time series - Source Code

DOI

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.

Current developments can be tracked in the gitlab repository: https://gitlab.version.fz-juelich.de/toar/mlair

This resource contains the MLAir version 1.0.0 in a zip archive (MLAir - v1.0.0.zip), as well the requirements (requirements.txt), a readme (README.md), and distribution file (mlair-1.0.0-py3-none-any.whl) for easy installation using the package installer for python (pip). Instructions on the installation von MLAir can be found in the readme file. If an installation is not preferred, the docker version of MLAir (mlair_docker_v1.0.0.tar.gz) is a possible alternative. A short guide on how to use it can be found in INSTRUCTIONS_mlair_docker_v1.0.0.md. Please note that the docker version does not provide GPU acceleration.

Identifier
DOI https://doi.org/10.34730/5a6c3533512541a79c5c41061743f5e3
Source https://b2share.fz-juelich.de/records/5a6c3533512541a79c5c41061743f5e3
Metadata Access https://b2share.fz-juelich.de/api/oai2d?verb=GetRecord&metadataPrefix=eudatcore&identifier=oai:b2share.fz-juelich.de:b2rec/5a6c3533512541a79c5c41061743f5e3
Provenance
Creator Leufen, Lukas Hubert; Kleinert, Felix; Schultz, Martin Georg
Publisher EUDAT B2SHARE
Publication Year 2021
Rights The MIT License (MIT); info:eu-repo/semantics/openAccess
OpenAccess true
Contact l.leufen(at)fz-juelich.de
Representation
Language English
Resource Type Software
Format txt; whl; gz; md; zip
Size 934.5 MB; 6 files
Version v1.0.0
Discipline 3.3.14 → Earth sciences → Meteorology; 4.1.17.1.2.1 → Machine learning → Artificial neural network; 4.1.13 → Computer sciences → Software engineering