Framework for seismic waveform polarity picking with unified APIs
Project description
SeisPolarity
A comprehensive framework for seismic first-motion polarity picking with unified APIs.
Documentation
Full documentation is available at: https://seispolarity.readthedocs.io/
Build documentation locally:
cd docs
make html
Installation
Install via pip (Recommended)
pip install seispolarity
From Source
git clone https://github.com/Chuan1937/SeisPolarity.git
cd SeisPolarity
pip install -e .
Features
- Unified Data Interface: Support for SCSN, Txed, DiTing, Instance, PNW datasets with automatic download
- Multiple Models: Ross, Eqpolarity, APP, DiTingMotion, CFM, RPNet, PolarCAP with pre-trained weights
- Flexible Data Loading: RAM/Disk streaming for datasets of any size
- High-level Inference:
Predictorclass with auto-download from Hugging Face/ModelScope - Data Augmentation: Comprehensive augmentation pipeline with balanced sampling
- Unified Training:
Trainerwith checkpointing, early stopping, and logging - Cross-platform Support: Works on Linux, macOS, and Windows
Supported Datasets
| Dataset | Description | Samples | Auto-download |
|---|---|---|---|
| SCSN | Southern California Seismic Network | 100k+ | Yes |
| Txed | Texas Earthquake Data | 50k+ | Yes |
| DiTing | Chinese seismic network | 80k+ | No(must apply) |
| Instance | Instance-based dataset | 30k+ | Yes |
| PNW | Pacific Northwest | 20k+ | Yes |
Supported Models
| Model | Input Length | Classes |
|---|---|---|
| Ross (SCSN) | 400 | 3 (U/D/N) |
| Eqpolarity | 600 | 2 (U/D) |
| DiTingMotion | 128 | 3 (U/D/N) |
| CFM | 160 | 2 (U/D) |
| RPNet | 400 | 2 (U/D) |
| PolarCAP | 64 | 2 (U/D) |
| APP | 400 | 3 (U/D/N) |
Model Zoo
Pre-trained models are automatically downloaded from:
- Hugging Face: https://huggingface.co/chuanjun1978/SeisPolarity-Model
- ModelScope: https://modelscope.cn/models/chuanjun1978/SeisPolarity-Model
Examples
See the examples/ directory for complete notebooks:
- Dataset API Usage - Dataset loading and usage examples
- Predict API Usage - Model inference examples
- Model API Usage - Model architecture and initialization
- Train API Usage - Training pipeline examples
Contributing
We welcome contributions! Please see our Contributing Guide for details.
- Fork the repository
- Create a feature branch
- Make your changes
- Add tests if applicable
- Submit a pull request
Citation
Paper will come soon...
License
This project is licensed under the BSD 3-Clause License - see the LICENSE file for details.
Acknowledgments
- SeisBench framework for inspiration
- Hugging Face and ModelScope for model hosting
- All dataset providers
Links
- GitHub: https://github.com/Chuan1937/SeisPolarity
- Hugging Face: https://huggingface.co/chuanjun1978/SeisPolarity-Model
- ModelScope: https://modelscope.cn/models/chuanjun1978/SeisPolarity-Model
- Documentation: https://seispolarity.readthedocs.io/
Contact
For questions and support, please open an issue on GitHub or contact: [chuanjun1978@gmail.com]
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file seispolarity-0.1.4.tar.gz.
File metadata
- Download URL: seispolarity-0.1.4.tar.gz
- Upload date:
- Size: 81.3 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.10.19
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
a5079f69dacecccf63dcd6bd38a0b548aaa0f970cbc33f554f1eb3f72df965e5
|
|
| MD5 |
12f571beaf380568a54b4f663cb384e2
|
|
| BLAKE2b-256 |
3d3865f71e896a5863bb01bc538124e1a96f2697d8a0bdf8dbe1e47840dcbf44
|
File details
Details for the file seispolarity-0.1.4-py3-none-any.whl.
File metadata
- Download URL: seispolarity-0.1.4-py3-none-any.whl
- Upload date:
- Size: 96.8 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.10.19
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
cec3d99140d7288fbc97d3a09e8fd713a0c1a9de5e7f1e3915d270ba0e6429d7
|
|
| MD5 |
31f71fae8d46cca4e29a647872184a26
|
|
| BLAKE2b-256 |
36724de4a8888d467b567b781d9eb169cdf95b183dfd1583aa613f98d338ce5d
|