Machine Learning For Distributed Acoustic Sensors, Classic versus Image and Deep Neural Networks Approach

TL;DR

This paper compares classic machine learning and deep learning image-based methods for event detection in distributed acoustic sensing, showing deep learning's superior speed and efficiency.

Contribution

It introduces and evaluates a novel deep learning approach for DAS event detection, demonstrating significant performance improvements over traditional methods.

Findings

Deep learning reduces detection delay sixfold.

Deep learning decreases execution time twelvefold.

Both methods achieve acceptable performance.

Abstract

Distributed Acoustic Sensing (DAS) using fiber optic cables is a promising new technology for pipeline monitoring and protection. In this work, we applied and compared two approaches for event detection using DAS: Classic machine learning approach and the approach based on image processing and deep learning. Although with both approaches acceptable performance can be achieved, the preliminary results show that image based deep learning is more promising approach, offering six times lower event detection delay and twelve times lower execution time.