- Prepare data for training a seisbench model detecting P and S waves (i.e. transform mseeds into [SeisBench data format](https://seisbench.readthedocs.io/en/stable/pages/data_format.html)), check the [notebook](utils/Transforming%20mseeds%20from%20Bogdanka%20to%20Seisbench%20format.ipynb) and the [script](utils/mseeds_to_seisbench.py)
- [to update] Explore available data, check the [notebook](notebooks/Explore%20igf%20data.ipynb)
- Train various cnn models available in seisbench library and compare their performance of detecting P and S waves, check the [script](scripts/pipeline.py)
Please download and install [Mambaforge](https://github.com/conda-forge/miniforge#mambaforge) following the [official guide](https://github.com/conda-forge/miniforge#install).
To utilize functionality of Seisbench library, data need to be transformed to [SeisBench data format](https://seisbench.readthedocs.io/en/stable/pages/data_format.html)). If your data is in the MSEED format, you can use the prepared script `mseeds_to_seisbench.py` to perform the transformation. Please make sure that your data has the same structure as the data used in this project.
The script assumes that:
* the data is stored in the following directory structure:
`input_path/year/station_network_code/station_code/trace_channel.D` e.g.
If you want to run the script on a cluster, you can use the script `convert_data.sh` as a template (adjust the grant name, computing name and paths) and send the job to queue using sbatch command on login node of e.g. Ares:
```
cd utils
sbatch convert_data.sh
```
If your data has a different structure or format, use the notebooks to gain an understanding of the Seisbench format and what needs to be done to transform your data:
* [Seisbench example](https://colab.research.google.com/github/seisbench/seisbench/blob/main/examples/01a_dataset_basics.ipynb) or
* [Transforming mseeds from Bogdanka to Seisbench format](utils/Transforming mseeds from Bogdanka to Seisbench format.ipynb) notebook
This step utilizes the Weights & Biases platform to perform the hyperparameters search (called sweeping) and track the training process and store the results.
Weights and training logs can be downloaded from the platform.
Additionally, the most important data are saved locally in `weights/<dataset_name>_<model_name>/ ` directory:
* Weights of the best checkpoint of each model are saved as `<dataset_name>_<model_name>_sweep=<sweep_id>-run=<run_id>-epoch=<epoch_number>-val_loss=<val_loss>.ckpt`
* Metrics and hyperparams are saved in <run_id> folders
* Uses the best performing model of each type to generate predictions. The predictons are saved in the `scripts/pred/<dataset_name>_<model_name>/<run_id>` directory.
* Evaluates the performance of each model by comparing the predictions with the evaluation targets.
The results are saved in the `scripts/pred/results.csv` file.
The default settings are saved in config.json file. To change the settings, edit the config.json file or pass the new settings as arguments to the script.
For example, to change the sweep configuration file for GPD model, run: