Modernizing Aerial Patrol - Real Life Remote Sensing for Liquid Leak and Threat Detection Along the Right of Way: First Detection Demonstrations of a Real Pipeline Seeper Leak, Encroachments, and Exposed Pipes Using a Traditional Aerial Patrol Plane
Abstract Since the end of 2022, Marathon Pipe Line LLC (MPL) has been using and testing Flyscan Systems’ (Flyscan) remote sensing technology over their liquid pipeline right of way (ROW) to benchmark and validate the use of machine learning (ML) algorithms, photogrammetry, and hyperspectral imaging to perform real-time threat detection, liquid leak detection of crude oil and refined products, as well as other advanced imaging features related to geo-hazards. This paper presents scientific approaches and real-life results from over 200 aerial patrols between November 2022 and December 2023, covering over 50,000 miles and identifying more than 3,000 potential threats over ROWs in diverse landscapes across the United States — from the subpolar forests of Alaska to the shrublands of Texas. To the best of our knowledge, this paper also describes a reported finding where a hyperspectral system was used to detect a real underground seeper diesel leak during a ROW aerial patrol flight. Further examples noted in the paper include the detection of contaminated soils from third-party activity, the detection of real encroachment, and massive documentation of various types of objects in the ROW. Finally, examples of new imaging capabilities are discussed, including detection of exposed pipes after serious weather events, vegetation analysis, and erosion monitoring for Depth of Cover (DOC).
Authors
- Éric Bergeron (ORCID: https://orcid.org/0000-0003-3398-8628)
- Alexandre Thibeault
- Joshua Beard
- Paige Chenevey
Institutions
- Marathon Oil (United States) (US)
- Microscan Systems (United States) (US)
Publication Details
- Journal
- Volume 3: Operations, Monitoring, and Maintenance; Materials and Joining
- Published
- 2024-09-23
- DOI
- https://doi.org/10.1115/ipc2024-123410
- Primary Topic
- Fire Detection and Safety Systems
- Type
- article
- Field-Weighted Citation Impact
- 0.00