https://github.com/sarvandani/deep_learning_classification_time_serie_data_seismic

https://github.com/sarvandani/deep_learning_classification_time_serie_data_seismic

deep deep-learning keras matplotlib numpy sklearn tensorflow

Last synced: 3 months ago
JSON representation

• Host: GitHub
• URL: https://github.com/sarvandani/deep_learning_classification_time_serie_data_seismic
• Owner: Sarvandani
• License: mit
• Created: 2025-06-28T14:47:54.000Z (about 1 year ago)
• Default Branch: main
• Last Pushed: 2025-06-28T15:06:35.000Z (about 1 year ago)
• Last Synced: 2025-06-28T15:38:19.847Z (about 1 year ago)
• Topics: deep, deep-learning, keras, matplotlib, numpy, sklearn, tensorflow
• Language: Jupyter Notebook
• Homepage:
• Size: 0 Bytes
• Stars: 0
• Watchers: 0
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# Deep_learning_classification_Time_serie_data_seismic

# Seismic Signal Classification Using CNN

This project demonstrates how to generate synthetic seismic signals (earthquake and noise), train a 1D Convolutional Neural Network (CNN) to classify signal windows, and visualize classification results on a long mixed seismic signal.

---

## **Overview**

Seismic signals often contain noise and earthquake events that must be distinguished for monitoring and analysis. This repository provides a complete pipeline to:

- **Generate synthetic seismic signals** simulating earthquake bursts and noise.

- **Visualize sample signals** to understand class characteristics.

- **Train a CNN model** to classify fixed-length windows of seismic data as earthquake or noise.

- **Apply the trained model** to a long mixed signal and visualize the classification over time.

---

## **Features**

- Synthetic data generation with controlled noise and earthquake bursts.

- Labeled visualization of example earthquake and noise signals.

- 1D CNN architecture tailored for time-series classification.

- Model training with validation and test splits.

- Window-by-window classification of long seismic signals.

- Visualization of classification results with color-coded plots (red = earthquake, blue = noise).