https://github.com/jameshgrn/based_api
This is the backend for the BASED streamlit app
https://github.com/jameshgrn/based_api
geomorphology hydrology machine-learning sedimentology streamlit xgboost
Last synced: about 2 months ago
JSON representation
This is the backend for the BASED streamlit app
- Host: GitHub
- URL: https://github.com/jameshgrn/based_api
- Owner: jameshgrn
- Created: 2023-02-13T22:14:33.000Z (over 3 years ago)
- Default Branch: master
- Last Pushed: 2024-12-14T17:16:16.000Z (over 1 year ago)
- Last Synced: 2024-12-14T17:27:07.507Z (over 1 year ago)
- Topics: geomorphology, hydrology, machine-learning, sedimentology, streamlit, xgboost
- Language: Python
- Homepage: https://based-estimator.streamlit.app/
- Size: 2.71 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# BASED: Boost-Assisted Stream Estimator for Depth
[](https://www.python.org/downloads/)
[](https://opensource.org/licenses/MIT)
BASED is an XGBoost regressor deployed using Streamlit, designed for predicting channel depth using channel width, slope, and discharge.
## Features
- 🌊 Accurate channel depth predictions
- 🚀 Fast inference using XGBoost
- 🖥️ User-friendly Streamlit interface
- 📊 Built-in error benchmarks and validation
## Quick Start
1. Clone the repository:
```
git clone https://github.com/JakeGearon/based-api.git
cd based-api
```
2. Install dependencies:
```
poetry install
```
3. Run the Streamlit app:
```
poetry run streamlit run st_app.py
```
4. Input values for slope, discharge, and width to predict channel depth.
## Model Performance
- Mean Absolute Error (MAE): 28 cm
- Root Mean Square Error (RMSE): 94 cm
- R-squared (R²): 0.84
- Mean Absolute Percentage Error (MAPE): 15.6%
*Image source: Gearon, J.H. et al. Rules of river avulsion change downstream. Nature 634, 91–95 (2024). https://doi.org/10.1038/s41586-024-07964-2*
## Citation
If you use BASED in your research, please either cite the paper it came from (above) or the software itself as follows:
```
Gearon, J. (2024). Boost-Assisted Stream Estimator for Depth (BASED) [Computer software]. Version 1.0.0. https://github.com/JakeGearon/based-api
```
## License
This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
## Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
## Contact
Jake Gearon - jake.gearon@gmail.com
Project Link: [https://based-estimator.streamlit.app/](https://based-estimator.streamlit.app/)