VI Seminar #83: Time Series Monitoring Using Vision Language Models

Presented by Håkon Nese, Data Scientist at Aker BP

Abstract

In the oil and gas industry, identifying anomalies in daily time series data can be critical for maintaining the performance and integrity of a petroleum production system. Previously numerous attempts have shown that statistical and machine learning approaches can provide a means to detect and identify the types of anomalies that may occur on a given set of monitored equipment. The recent advances in leveraging generative pre-trained Large Language Models (LLMs) have been shown to be extendable to tasks on time series data by treating the data as a series of textual characters. In this work we investigate the capability of so-called Vision-Language Models (VLMs) for anomaly detection in time series data from production wells and present the time series data as a plot instead of treating the data as a series of textual characters.

In this talk, I will present how VLMs work and how they can be used for time series anomaly detection. I will show some of our findings on what works well, limitations and the benefits and drawbacks of using VLMs for petroleum production system monitoring