dc.contributor.author | Tunkiel, Andrzej Tadeusz | |
dc.contributor.author | Sui, Dan | |
dc.contributor.author | Wiktorski, Tomasz | |
dc.date.accessioned | 2022-01-05T08:52:55Z | |
dc.date.available | 2022-01-05T08:52:55Z | |
dc.date.created | 2021-11-14T18:32:39Z | |
dc.date.issued | 2021-11 | |
dc.identifier.citation | Tunkiel, A.T., Sui, D., & Wiktorski, T. (2022) Impact of data pre-processing techniques on recurrent neural network performance in context of real-time drilling logs in an automated prediction framework. Journal of Petroleum Science and Engineering, 2008, part E, 109760 | en_US |
dc.identifier.issn | 0920-4105 | |
dc.identifier.uri | https://hdl.handle.net/11250/2836099 | |
dc.description.abstract | Recurrent neural networks (RNN), which are able to capture temporal natures of a signal, are becoming more common in machine learning applied to petroleum engineering, particularly drilling. With this technology come requirements and caveats related to the input data that play a significant role on resultant models. This paper explores how data pre-processing and attribute selection techniques affect the RNN models’ performance. Re-sampling and down-sampling methods are compared; imputation strategies, a problem generally omitted in published research, are explored and a method to select either last observation carried forward or linear interpolation is introduced and explored in terms of model accuracy. Case studies are performed on real-time drilling logs from the open Volve dataset published by Equinor. For a realistic evaluation, a semi-automated process is proposed for data preparation and model training and evaluation which employs a continuous learning approach for machine learning model updating, where the training dataset is being built continuously while the well is being made. This allows for accurate benchmarking of data pre-processing methods. Included is a previously developed and updated branched custom neural network architecture that includes both recurrent elements as well as row-wise regression elements. Source code for the implementation is published on GitHub. | en_US |
dc.language.iso | eng | en_US |
dc.publisher | Elsevier Ltd. | en_US |
dc.rights | Navngivelse 4.0 Internasjonal | * |
dc.rights.uri | http://creativecommons.org/licenses/by/4.0/deed.no | * |
dc.subject | petroleumsteknologi | en_US |
dc.subject | RNN | en_US |
dc.subject | maskinlæring | en_US |
dc.subject | boring | en_US |
dc.title | Impact of data pre-processing techniques on recurrent neural network performance in context of real-time drilling logs in an automated prediction framework | en_US |
dc.type | Peer reviewed | en_US |
dc.type | Journal article | en_US |
dc.description.version | publishedVersion | en_US |
dc.rights.holder | © 2021 The Authors | en_US |
dc.subject.nsi | VDP::Teknologi: 500::Berg‑ og petroleumsfag: 510::Petroleumsteknologi: 512 | en_US |
dc.source.volume | 2008 part E | en_US |
dc.source.journal | Journal of Petroleum Science and Engineering | en_US |
dc.identifier.doi | 10.1016/j.petrol.2021.109760 | |
dc.identifier.cristin | 1954369 | |
dc.source.articlenumber | 109760 | en_US |
cristin.ispublished | true | |
cristin.fulltext | postprint | |
cristin.qualitycode | 2 | |