{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T14:09:54Z","timestamp":1782482994645,"version":"3.54.5"},"reference-count":16,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2023,6,21]],"date-time":"2023-06-21T00:00:00Z","timestamp":1687305600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Imaging"],"abstract":"<jats:p>In this paper, we considered one of the problems that arise during drilling automation, namely the automation of lithology identification from drill cuttings images. Usually, this work is performed by experienced geologists, but this is a tedious and subjective process. Drill cuttings are the cheapest source of rock formation samples; therefore, reliable lithology prediction can greatly reduce the cost of analysis during drilling. To predict the lithology content from images of cuttings samples, we used a convolutional neural network (CNN). For training a model with an acceptable generalization ability, we applied dataset-cleaning techniques, which help to reveal bad samples, as well as samples with uncertain labels. It was shown that the model trained on a cleaned dataset performs better in terms of accuracy. Data cleaning was performed using a cross-validation technique, as well as a clustering analysis of embeddings, where it is possible to identify clusters with distinctive visual characteristics and clusters where visually similar samples of rocks are attributed to different lithologies during the labeling process.<\/jats:p>","DOI":"10.3390\/jimaging9070126","type":"journal-article","created":{"date-parts":[[2023,6,22]],"date-time":"2023-06-22T01:49:32Z","timestamp":1687398572000},"page":"126","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Fast Reservoir Characterization with AI-Based Lithology Prediction Using Drill Cuttings Images and Noisy Labels"],"prefix":"10.3390","volume":"9","author":[{"given":"Ekaterina","family":"Tolstaya","sequence":"first","affiliation":[{"name":"Aramco Innovations LLC, 117127 Moscow, Russia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anuar","family":"Shakirov","sequence":"additional","affiliation":[{"name":"Aramco Innovations LLC, 117127 Moscow, Russia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mokhles","family":"Mezghani","sequence":"additional","affiliation":[{"name":"EXPEC Advanced Research Center Saudi Aramco, Dhahran 34466, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sergey","family":"Safonov","sequence":"additional","affiliation":[{"name":"Aramco Innovations LLC, 117127 Moscow, Russia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2023,6,21]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1016\/j.petrol.2018.03.034","article-title":"Lithology identification using an optimized KNN clustering method based on entropy-weighed cosine distance in Mesozoic strata of Gaoqing field, Jiyang depression","volume":"166","author":"Wang","year":"2018","journal-title":"J. Pet. Sci. Eng."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"107955","DOI":"10.1016\/j.petrol.2020.107955","article-title":"A new method for predicting formation lithology while drilling at horizontal well bit","volume":"196","author":"Sun","year":"2021","journal-title":"J. Pet. Sci. Eng."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"104306","DOI":"10.1016\/j.jngse.2021.104306","article-title":"Feature-Depth Smoothness Based Semi-Supervised Weighted Extreme Learning Machine for lithology identification","volume":"96","author":"Li","year":"2021","journal-title":"J. Nat. Gas Sci. Eng."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Chen, G., Chen, M., Hong, G., Lu, Y., Zhou, B., and Gao, Y. (2020). A new method of lithology classification based on convolu-tional neural network algorithm by utilizing drilling string vibration data. Energies, 13.","DOI":"10.3390\/en13040888"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Kathrada, M., and Adillah, B.J. (2019, January 17\u201319). Visual Recognition of Drill Cuttings Lithologies Using Convolutional Neural Networks to Aid Reservoir Characterisation. Proceedings of the SPE Reservoir Characterisation and Simulation Conference and Exhibition, Abu Dhabi, United Arab Emirates.","DOI":"10.2118\/196675-MS"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"108898","DOI":"10.1016\/j.petrol.2021.108898","article-title":"Novel lithology identification method for drilling cuttings under PDC bit condition","volume":"205","author":"Huo","year":"2021","journal-title":"J. Pet. Sci. Eng."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"108853","DOI":"10.1016\/j.petrol.2021.108853","article-title":"Integrated lithology identification based on images and elemental data from rocks","volume":"205","author":"Xu","year":"2021","journal-title":"J. Pet. Sci. Eng."},{"key":"ref_8","unstructured":"Equinor (2023, May 10). Cuillin. Available online: https:\/\/www.npd.no\/globalassets\/2-force\/2019\/documents\/archive-2010-2018\/force-hackathon\/nr.15-wade-cuillin.pdf\/."},{"key":"ref_9","unstructured":"Tamaazousti, Y., Fran\u00e7ois, M., and Kherroubi, J. (2020). SEG Technical Program Expanded Abstracts, Society of Exploration Geophysicists."},{"key":"ref_10","unstructured":"Girard, J., Tamaazousti, Y., Borgne, H.L., and Hudelot, C. (2018). Learning finer-class networks for universal representations. arXiv."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Yan, X., Misra, I., Gupta, A., Ghadiyaram, D., and Mahajan, D. (2020, January 13\u201319). Clusterfit: Improving generalization of visual represen-tations. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00654"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"917","DOI":"10.1093\/bioinformatics\/bth007","article-title":"Gaussian mixture clustering and imputation of microarray data","volume":"20","author":"Ouyang","year":"2004","journal-title":"Bioinformatics"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Shahapure, K.R., and Nicholas, C. (2020, January 6\u20139). Cluster quality analysis using silhouette score. Proceedings of the 2020 IEEE 7th International Conference on Data Science and Advanced Analytics (DSAA), Sydney, Australia.","DOI":"10.1109\/DSAA49011.2020.00096"},{"key":"ref_14","first-page":"1","article-title":"Toward Autonomous Wellsite Geology: Artificial Intelligence for Cutting Li-thology Prediction","volume":"Volume 2022","author":"Mezghani","year":"2022","journal-title":"Proceedings of the Second EAGE Subsurface Intelligence Workshop"},{"key":"ref_15","unstructured":"Northcutt, C.G., Athalye, A., and Mueller, J. (2021). Pervasive label errors in test sets destabilize machine learning benchmarks. arXiv."},{"key":"ref_16","first-page":"2825","article-title":"Scikit-learn: Machine Learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."}],"container-title":["Journal of Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-433X\/9\/7\/126\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T19:58:17Z","timestamp":1760126297000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-433X\/9\/7\/126"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,21]]},"references-count":16,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2023,7]]}},"alternative-id":["jimaging9070126"],"URL":"https:\/\/doi.org\/10.3390\/jimaging9070126","relation":{},"ISSN":["2313-433X"],"issn-type":[{"value":"2313-433X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,21]]}}}