Table of Contents
This is the repository to reproduce the experiments presented in QuakeSet: A Dataset and Low-Resource Models to Monitor Earthquakes through Sentinel-1 accepted at ISCRAM 2024.
The dataset is available on HuggingFace or TorchGeo.
PrePrint: https://arxiv.org/abs/2403.18116
REPOSITORY IN CONSTRUCTION: SOME FILES COULD BE MISSING
The project is built upon:
- SkLearn
- PyTorch Lightning
- Hydra
- Timm
- Transformers
The experiments for classical machine learning models can be reproduced with classical_main.py. The experiments with deep learning models can be done with main.py.
You can change the parameters in the configs folder or through the command line.
The original setup of this repository is by Daniele Rege Cambrin.
For a full list of all authors and contributors, see the contributors page.
This project is licensed under the Apache 2.0 license.
See LICENSE for more information.