Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/norwegianseismicarray/urban-seismic-monitoring
Event detection and ML code developed in GeoByIT project. Will be made public as attachment to paper submitted to Seismica.
https://github.com/norwegianseismicarray/urban-seismic-monitoring
Last synced: 10 days ago
JSON representation
Event detection and ML code developed in GeoByIT project. Will be made public as attachment to paper submitted to Seismica.
- Host: GitHub
- URL: https://github.com/norwegianseismicarray/urban-seismic-monitoring
- Owner: NorwegianSeismicArray
- License: mit
- Created: 2023-11-27T13:43:01.000Z (about 1 year ago)
- Default Branch: master
- Last Pushed: 2024-02-23T08:58:09.000Z (11 months ago)
- Last Synced: 2024-02-23T09:44:20.899Z (11 months ago)
- Language: Python
- Size: 58.3 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE.txt
Awesome Lists containing this project
README
# Urban seismic monitoring
Code and examples related to the paper **Monitoring urban construction and quarry blasts with low-cost seismic sensors and machine learning tools in the city of Oslo, Norway**, accepted for publication in SEISMICA.
Seismic waveform data are available via FDSN server / EIDA node.
## Outlier detection with auto-encoder
To install requirements :
```
conda create -n urbanmon python=3.10 obspy cartopy pytest pytest-json
conda activate urbanmon
pip install tensorflow
pip install tslearn
pip install tqdm
pip install pandas
pip install keras-tuner
```
In case of library trouble :
ImportError: /lib64/libstdc++.so.6: version `CXXABI_1.3.9' not found
```
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/path-to-your-env/urbanmon/lib/
```
To train auto-encoder for outlier detection (edit scripts for different stations):
```
python create_training_data_AutoEncoder.py
python train_AutoEncoder.py
```
To run outlier detection (whole time period or two days):
```
python run_outlier_detection.py OSLN2 2022-06-01T00:00:00 2023-09-28T00:00:00 4.0 0.78
python run_outlier_detection.py OSLN2 2022-10-10T00:00:00 2022-10-12T00:00:00 4.0 0.78
```
To locate and plot outlier events:
```
python locate_events.py OSLN2 2022-10-10 outlier
```
To locate and plot sta/lta events:
```
python locate_events.py OSLN2 2022-10-10 stalta
```
## Supervised blast classification
To create training data for blast classification:
```
python create_training_data_BlastClassifier.py
```
To train blast classifier:
```
python train_BlastClassifier.py
```
To run the blast classifier:
```
python run_blast_classifier.py
```
To locate and plot blast classifications:
```
python locate_events.py OSLN2 2022-10-10 classifier
```
## License
See `LICENSE.txt` for more information.
## Contact
Andreas Köhler - [email protected] - [ORCID](https://orcid.org/0000-0002-1060-7637)
Erik B. Myklebust - [ORCID](https://orcid.org/0000-0002-3056-2544)
Project Link: [https://github.com/NorwegianSeismicArray/urban-seismic-monitoring](https://github.com/NorwegianSeismicArray/urban-seismic-monitoring)
## Acknowledgments
* Models are built with [TensorFLow](https://www.tensorflow.org/)