Microseismic
A machine learning model for identifying rockfall signals from microseismic data using waveform guidance.
Install / Use
/learn @yuxi-chenc/MicroseismicREADME
Intelligent Recognition Network for Microseismic Signals based on Waveform Attributes (SSD)
This repository provides a complete deep learning pipeline for seismic data processing, including label generation, model training, and event prediction, as presented in our corresponding research paper.
Features
- Label Generation: Scripts to process raw seismic data and generate various types of labels (e.g., event-based and attribute-based)
- Flexible Model Training: Training script supporting building models from scratch or fine-tuning pre-trained weights
- Universal Event Prediction: Prediction script to apply trained models on new, continuous seismic data
- Modular Workflow: Entire pipeline controlled through central runner script (
run.py)
Requirements
To run this project, first install necessary Python libraries (recommended in a virtual environment):
pip install tensorflow numpy obspy pandas scipy matplotlib pywavelets
How to Run
All functionalities are integrated into run.py. Modify the run_case variable at the top of the script:
run_case = "train"
Options for run_case:
eve : Generates event labels (Noise, Event Type) from raw seismic data
att : Generates attribute labels (e.g., SSD) from waveform data
pre_train: Pre-trains a model on attribute labels
train : Trains/fine-tunes main model on event labels
pred : Makes predictions on new data
Execution Steps
- Choose Task: Set run_case in run.py to desired task (e.g., run_case = "pred")
- Configure Parameters: Modify command-line parameters in corresponding if/elif block
- Run Script:
python run.py
Model
-Architectures: Defined in models.py and models_f.py -Pre-trained Weights: Provided in model/ directory
Dataset
All data and code are openly available.
- Curated datasets from paper (download and place in appropriate directory): Download Link: https://doi.org/YOUR_DOI_HERE
-Continuous Raw Data Sources Séchilienne Rockslide OMIV/RESIF Use day_datadown.py script https://doi.com/10.15778/RESIF.MT Illgraben Rockslide GFZ Data Services Manual download https://doi.com/10.5880/GFZ.2.4/2016.001.
Reference:
Bianchi, M., Evans, P. L., Heinloo, A., & Quinteros, J. (2015). Webdc3 web interface. GFZ Data Services. doi: 10.5880/GFZ.2.4/2016.001388 Helmstetter, A., & Garambois, S. (2010). Seismic monitoring of S´echilienne rockslide (French Alps): Analysis of seismic signals and their correlation with rainfalls. Journal of Geophysical Research: Earth Surface, 115 (F3). doi: 10.1029/2009JF001532409 French Landslide Observatory – Seismological Datacenter / RESIF. (2006). Observatoire Multi-disciplinaire des Instabilit´es de Versants (OMIV) [Data set]. RESIF - R´eseau French Landslide Observatory – Seismological Datacenter / RESIF. (2006). Observatoire Multi-disciplinaire des Instabilit´es de Versants (OMIV) [Data set]. RESIF - R´eseau
Related Skills
proje
Interactive vocabulary learning platform with smart flashcards and spaced repetition for effective language acquisition.
YC-Killer
2.7kA library of enterprise-grade AI agents designed to democratize artificial intelligence and provide free, open-source alternatives to overvalued Y Combinator startups. If you are excited about democratizing AI access & AI agents, please star ⭐️ this repository and use the link in the readme to join our open source AI research team.
best-practices-researcher
The most comprehensive Claude Code skills registry | Web Search: https://skills-registry-web.vercel.app
research_rules
Research & Verification Rules Quote Verification Protocol Primary Task "Make sure that the quote is relevant to the chapter and so you we want to make sure that we want to have it identifie
