Dynamic detection of anomalous regions within distributed acoustic sensing data streams using locally stationary wavelet time series

TL;DR

This paper presents a computationally efficient online method for detecting anomalous regions in distributed acoustic sensing data streams, improving well performance modeling in oil and gas production.

Contribution

It extends locally stationary wavelet time series classification to an online setting, enabling real-time anomaly detection in multivariate acoustic data.

Findings

Accurately identifies anomalous regions in real-time data streams

Enhances well performance modeling by detecting 'stripes' anomalies

Provides a scalable solution for large-volume acoustic data analysis

Abstract

Distributed acoustic sensing technology is increasingly being used to support production and well management within the oil and gas sector, for example to improve flow monitoring and production profiling. This sensing technology is capable of recording substantial data volumes at multiple depths within an oil well, giving unprecedented insights into production behaviour. However the technology is also prone to recording periods of anomalous behaviour, where the same physical features are concurrently observed at multiple depths. Such features are called `stripes' and are undesirable, detrimentally affecting well performance modelling. This paper focuses on the important challenge of developing a principled approach to identifying such anomalous periods within distributed acoustic signals. We extend recent work on classifying locally stationary wavelet time series to an online setting and, in so doing, introduce a computationally-efficient online procedure capable of accurately identifying anomalous regions within multivariate time series.