{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T06:08:22Z","timestamp":1788761302391,"version":"build-2803163510"},"reference-count":28,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T00:00:00Z","timestamp":1788739200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>Wellbore trajectory deviation remains one of the major operational challenges encountered during directional and extended-reach drilling because even small departures from the planned well path can lead to poor reservoir placement, wellbore instability, increased non-productive time, and significant drilling costs. In most field operations, trajectory monitoring depends on periodic directional surveys together with threshold-based diagnostics. Although these methods are widely used, they often identify deviations only after they have become operationally noticeable, limiting the opportunity for timely corrective action. To overcome the limitations of conventional monitoring, the present study proposes an unsupervised deep learning framework capable of identifying the early onset of trajectory deviation by analyzing integrated well-log and geo-mechanical data without relying on labeled deviation events. The proposed framework combines Depth, Gamma Ray (GR), Shale Volume (Vsh), Resistivity, Sonic Transit Time (\u0394T), P-wave Velocity (Vp), S-wave Velocity (Vs), Bulk Density, Calculated Density, Neutron Porosity (NPHI), Density Porosity (DPHI), and Poisson's Ratio to capture the lithological and mechanical characteristics that influence drilling behavior and trajectory stability. An LSTM Autoencoder (LSTM-AE) is employed to learn the normal temporal evolution of drilling parameters and identify anomalous behavior through reconstruction error. To complement the sequential learning capability of the autoencoder, a Graph Neural Network (GNN) is developed to represent the physical and geological relationships among the measured parameters, allowing complex multivariate interactions to be analyzed without requiring labeled datasets. The performance of both models is evaluated by comparing their ability to distinguish normal drilling behavior from progressively unstable operating conditions. The obtained results demonstrate that the LSTM-AE effectively learns the sequential characteristics of stable drilling and provides reliable early warning through changes in reconstruction error, whereas the GNN offers improved discrimination of trajectory-related anomalies by modeling the underlying relationships between geological and geo-mechanical variables. Collectively, these complementary approaches enableearlier recognition of developing trajectory deviations while reducing false alarms compared with conventional monitoring techniques. The findings demonstrate that integrating temporal sequence modeling with graph-based relational learning provides a practical and scalable solution for intelligent wellbore trajectory monitoring, supporting improved wellbore stability assessment, safer drilling operations, and more informed decision-making in complex subsurface environments.<\/jats:p>","DOI":"10.3389\/frai.2026.1942787","type":"journal-article","created":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T05:34:39Z","timestamp":1788759279000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Unsupervised deep learning framework for early detection of wellbore trajectory deviation in drilling operations"],"prefix":"10.3389","volume":"9","author":[{"given":"Prabhat","family":"Singh","sequence":"first","affiliation":[{"name":"School of Chemical Engineering, Vellore Institute of Technology, Vellore","place":["Tamil Nadu, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bushitha","family":"Vickram","sequence":"additional","affiliation":[{"name":"School of Chemical Engineering, Vellore Institute of Technology, Vellore","place":["Tamil Nadu, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Annmaria","family":"Benny","sequence":"additional","affiliation":[{"name":"School of Chemical Engineering, Vellore Institute of Technology, Vellore","place":["Tamil Nadu, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kadeeja","family":"Mariyam","sequence":"additional","affiliation":[{"name":"School of Chemical Engineering, Vellore Institute of Technology, Vellore","place":["Tamil Nadu, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sudakshina","family":"Dan","sequence":"additional","affiliation":[{"name":"School of Chemical Engineering, Vellore Institute of Technology, Vellore","place":["Tamil Nadu, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"R.","family":"Harishwaran","sequence":"additional","affiliation":[{"name":"School of Chemical Engineering, Vellore Institute of Technology, Vellore","place":["Tamil Nadu, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"B. Naveen","family":"Kumar","sequence":"additional","affiliation":[{"name":"School of Chemical Engineering, Vellore Institute of Technology, Vellore","place":["Tamil Nadu, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"M. Aslam","family":"Abdullah","sequence":"additional","affiliation":[{"name":"School of Chemical Engineering, Vellore Institute of Technology, Vellore","place":["Tamil Nadu, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,7]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-47578-3","author":"Aggarwal","year":"2017","journal-title":"Outlier Analysis"},{"key":"B2","doi-asserted-by":"publisher","first-page":"785","DOI":"10.1016\/j.petrol.2018.12.079","article-title":"A review of reactive transport modeling in wellbore integrity problems","volume":"175","author":"Ajayi","year":"2019","journal-title":"J. Pet. Sci. Eng"},{"key":"B3","doi-asserted-by":"publisher","first-page":"3935","DOI":"10.1007\/s13202-021-01291-2","article-title":"Geomechanical model and wellbore stability analysis utilizing acoustic impedance and reflection coefficient in a carbonate reservoir","volume":"11","author":"Bagheri","year":"2021","journal-title":"J. Pet. Explor. Prod. Technol"},{"key":"B4","doi-asserted-by":"publisher","first-page":"111146","DOI":"10.1016\/j.petrol.2022.111146","article-title":"The thermoporoelastic coupling analysis of wellbore stability in shale formation under supercritical CO2 drilling conditions","volume":"220","author":"Bai","year":"2023","journal-title":"J. Pet. Sci. Eng"},{"key":"B5","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1049\/ip-vis:19941330","article-title":"Novelty detection and neural network validation","volume":"141","author":"Bishop","year":"1994","journal-title":"IEE Proc. Vis. Image Signal Process"},{"key":"B6","volume-title":"Pattern Recognition and Machine Learning","author":"Bishop","year":"2006"},{"key":"B7","doi-asserted-by":"crossref","DOI":"10.2118\/217333-MS","article-title":"\u201cOptimizing the wellbore trajectory of directional wells considering wellbore stability subjected to the non-independence and uncertainty of geomechanical parameters. SPE-217333-MS,\u201d","volume-title":"Proceedings of the Asia Pacific Unconventional Resources Symposium","author":"Chen","year":"2023"},{"key":"B8","doi-asserted-by":"publisher","first-page":"213085","DOI":"10.1016\/j.geoen.2024.213085","article-title":"Optimizing the wellbore trajectory of directional wells considering wellbore stability subjected to the non-independence and uncertainty of geomechanical parameters","volume":"241","author":"Chen","year":"2024","journal-title":"Geoenergy Sci. Eng"},{"key":"B9","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1016\/B978-0-12-817236-0.00014-5","article-title":"\u201cPore pressure and wellbore instability,\u201d","author":"de Souza","year":"2021","journal-title":"Applied Techniques to Integrated Oil and Gas Reservoir Characterization: A Problem-Solution Discussion with Geoscience Experts"},{"key":"B10","volume-title":"Deep Learning","author":"Goodfellow","year":"2016"},{"key":"B11","article-title":"Inductive representation learning on large graphs","author":"Hamilton","year":"2017","journal-title":"Adv. Neural. Inf. Process. Syst"},{"key":"B12","doi-asserted-by":"publisher","first-page":"735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural. Comput"},{"key":"B13","article-title":"\u201cSemi-supervised classification with graph convolutional networks,\u201d","author":"Kipf","year":"2017","journal-title":"International Conference on Learning Representations (ICLR 2017)"},{"key":"B14","doi-asserted-by":"publisher","first-page":"1630","DOI":"10.3390\/pr13061630","article-title":"Wellhead stability during development process of hydrate reservoir in the Northern South China Sea: sensitivity analysis","volume":"13","author":"Li","year":"","journal-title":"Processes"},{"key":"B15","doi-asserted-by":"publisher","first-page":"3180","DOI":"10.3390\/en19133180","article-title":"Multivariate coupling model and reservoir characteristics of enhanced geothermal reservoirs","volume":"19","author":"Li","year":"2026","journal-title":"Energies"},{"key":"B16","doi-asserted-by":"publisher","first-page":"4049","DOI":"10.3390\/pr13124049","article-title":"Analysis of sedimentation behaviour and influencing factors of solid particles in CO2 fracturing fluid","volume":"13","author":"Li","year":"","journal-title":"Processes"},{"key":"B17","doi-asserted-by":"publisher","first-page":"205","DOI":"10.32604\/fdmp.2023.030645","article-title":"Finite element method simulation of wellbore stability under different operating and geomechanical conditions","volume":"20","author":"Liu","year":"2024","journal-title":"Fluid Dyn. Mater. Process"},{"key":"B18","doi-asserted-by":"publisher","first-page":"212298","DOI":"10.1016\/j.geoen.2023.212298","article-title":"The wellbore instability mechanism in hot dry rock drilling","volume":"231","author":"Liu","year":"2023","journal-title":"Geoenergy Sci. Eng"},{"key":"B19","doi-asserted-by":"publisher","first-page":"1483285","DOI":"10.3389\/feart.2024.1483285","article-title":"A theoretical analysis of the logging-while-drilling dipole acoustic reflection measurement","volume":"12","author":"Li","year":"2024","journal-title":"Front. Earth Sci"},{"key":"B20","doi-asserted-by":"publisher","first-page":"106653","DOI":"10.1016\/j.petrol.2019.106653","article-title":"Loss circulation in drilling and well construction: the significance of applications of crosslinked polymers in wellbore strengthening: a review","volume":"185","author":"Magzoub","year":"2020","journal-title":"J. Pet. Sci. Eng"},{"key":"B21","first-page":"89","article-title":"\u201cLong short term memory networks for anomaly detection in time series,\u201d","volume-title":"proceedings of the European Symposium on artificial neural networks, computational intelligence and machine learning (ESANN)","author":"Malhotra","year":"2015"},{"key":"B22","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1145\/2689746.2689747","article-title":"\u201cAnomaly detection using autoencoders with nonlinear dimensionality reduction,\u201d","author":"Sakurada","year":"2014"},{"key":"B23","doi-asserted-by":"publisher","first-page":"1823401","DOI":"10.3389\/fbuil.2026.1823401","article-title":"Unsupervised learning for real-time detection of pre-bit pressure variations in drilling operations","volume":"12","author":"Singh","year":"2026","journal-title":"Front. Built Environ"},{"key":"B24","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1016\/j.ngib.2021.08.019","article-title":"Deep and ultra-deep oil and gas well drilling technologies: Progress and prospect","volume":"9","author":"Wang","year":"2022","journal-title":"Nat. Gas Ind. B"},{"key":"B25","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1109\/TNNLS.2020.2978386","article-title":"A comprehensive survey on graph neural networks","volume":"32","author":"Wu","year":"2021","journal-title":"IEEE Trans. Neural Netw. Learn. Syst"},{"key":"B26","doi-asserted-by":"publisher","first-page":"212409","DOI":"10.1016\/j.geoen.2023.212409","article-title":"Application of machine learning in wellbore stability prediction: a review","volume":"232","author":"Xu","year":"2024","journal-title":"Geoenergy Sci. Eng"},{"key":"B27","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1016\/j.aiopen.2021.01.001","article-title":"Graph neural networks: a review of methods and applications","volume":"1","author":"Zhou","year":"2020","journal-title":"AI Open"},{"key":"B28","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1016\/j.petrol.2014.07.027","article-title":"Evaluate the borehole condition to reduce drilling risk and avoid potential well bore damages by using image logs","volume":"122","author":"Zohreh","year":"2014","journal-title":"J. Pet. Sci. Eng"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1942787\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T05:34:41Z","timestamp":1788759281000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1942787\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,7]]},"references-count":28,"alternative-id":["10.3389\/frai.2026.1942787"],"URL":"https:\/\/doi.org\/10.3389\/frai.2026.1942787","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,7]]},"article-number":"1942787"}}