This record contains all experiment data for the manuskript "Exploring decomposition of temporal patterns to facilitate learning of neural networks for near-surface dma8eu ozone prediction" by L. H. Leufen, F. Kleinert and M. G. Schultz.

We provide the complete experiment folders of the best trained networks. These contain the data used (data), the forecasts created (forecasts), the neural network used (model), graphics about the data and the evaluation (plots), the exact results of the error analysis (latex_report) as well as the batches already split for the training (batch_data). In addition, each experiment folder contains a start script (start_script.txt), which could be used to start a new experiment, as well as a start script (start_script_no_train.txt), which can be used to restart the evaluation without overwriting or training the model.

All experiments were carried out with the software MLAir in version 1.4.0 . A detailed description is given in https://doi.org/10.5194/gmd-14-1553-2021 and the source code can be found at https://gitlab.jsc.fz-juelich.de/esde/machine-learning/mlair .

To rerun an experiment, (1) it is required to install MLAir according to the installation instructions provided in the source code repository, (2) unpack the experiment folder (3) adjust the placeholder in run_example.sh with the correct folder name, e.g. MBFCN_LT_ST_network_daily (4) either execute run_example.sh or copy it's content and call the python command directly.