Petroleum Exploration and Development >

0 20240804 - 20240804

DOI: https://doi.org/10.11698/PED.20240254

Research status and prospects of artificial intelligence large model applications in the oil and gas industry

Expand
  • 1. National key Laboratory for Multi-resources Collaborative Green Production of Continental Shale Oil, Daqing 163000, China;
    2. Research Institute of Petroleum Exploration and Development, Beijing 100083, China;
    3. Beijing University of Aeronautics and Astronautics, Beijing 100191, China;
    4. Peking University, Beijing 100091, China;
    5. China University of Petroleum (Beijing), Beijing 102249, China

Received date: 2024-04-17

  Revised date: 2024-06-18

  Online published: 2024-06-18

Fold

Abstract

This article elucidates the concept of large model technology, summarizes the research status of large model technology both domestically and internationally, provides an overview of the application status of large models in vertical domains, outlines the challenges and issues confronted in applying large models in the oil and gas sector, and offers prospects for the application of large models in the oil and gas industry. The existing large models can be divided into three categories: large language models, visual large models, and multimodal large models. The application of large models in the oil and gas industry is still in its infancy. Based on open-source large language models, some oil and gas enterprises have released large language model products using methods like fine-tuning and retrieval augmented generation. Several scholars have attempted to develop scenario-specific models for oil and gas operations by using visual/multimodal foundation models. Additionally, a few researchers have constructed pre-trained foundation models for seismic data processing and interpretation, as well as core analysis. The application of large models in the oil and gas industry faces challenges such as current data quantity and quality being difficult to support the training of large models, high research and development costs, and poor algorithm autonomy and control. The application of large models must be guided by the needs of oil and gas business, to take the application of large models as an opportunity to improve data lifecycle management, enhance data governance capabilities, promote the construction of computing power, strengthen the construction of “artificial intelligence + energy” composite teams, and boost the autonomy and control of big model technology.

Key words： foundation model; large language mode; visual large model; multimodal large model; large model of oil and gas industry; pre-training; fine-tuning

Cite this article

LIU He, REN Yili, LI Xin, DENG Yue, WANG Yongtao, CAO Qianwen, DU Jinyang, LIN Zhiwei, WANG Wenjie . Research status and prospects of artificial intelligence large model applications in the oil and gas industry[J]. Petroleum Exploration and Development, 0 : 20240804 -20240804 . DOI: 10.11698/PED.20240254

References

[1] DEVLIN J, CHANG M W, LEE K, et al.BERT: Pre-training of deep bidirectional transformers for language understanding[C]//BURSTEIN J, DORAN C, SOLORIO T. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Stroudsburg, PA: Association for Computational Linguistics, 2019: 4171-4186.
[2] RADFORD A, NARASIMHAN K, SALIMANS T, et al.Improving language understanding by generative pre-training[DB/OL]. [2024-04-12].https://cdn.openai.com/research-covers/language-unsupervised/ language_understanding_paper.pdf.
[3] RAFFEL C, SHAZEER N, ROBERTS A, et al.Exploring the limits of transfer learning with a unified text-to-text transformer[J]. Journal of Machine Learning Research, 2020, 21(1): 140.
[4] CHUNG H W, HOU L, LONGPRE S, et al.Scaling instruction: Finetuned language models[J]. Journal of Machine Learning Research, 2024, 25(70): 1-53.
[5] TOUVRON H, LAVRIL T, IZACARD G, et al. LLaMA: Open and efficient foundation language models[DB/OL]. (2023-02-27) [2024-04-12]. https://arxiv.org/abs/2302.13971.
[6] YANG A Y, XIAO B, WANG B N, et al. Baichuan 2: Open large-scale language models[DB/OL]. (2023-09-20)[2024-04-12]. https://arxiv.org/abs/2309.10305.
[7] InternLM Team. InternLM: A multilingual language model with progressively enhanced capabilities[DB/OL].[2024-04-12]. https:// static.aminer.cn/upload/pdf/127/1564/656/6481884993eaf7045294a0c4_0. pdf.
[8] HU E J, SHEN Y L, WALLIS P, et al. LoRA: Low-rank adaptation of large language models[DB/OL]. (2021-10-16)[2024-04-12]. https:// arxiv.org/abs/2106.096851.
[9] FANG Y X, WANG W, XIE B H, et al. EVA: Exploring the limits of masked visual representation learning at scale[R]. Vancouver:2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023.
[10] OQUAB M, DARCET T, MOUTAKANNI T, et al. DINOv2: Learning robust visual features without supervision[DB/OL]. (2024-02-02)[2024-04-12]. https://arxiv.org/abs/2304.07193.
[11] KIRILLOV A, MINTUN E, RAVI N, et al. Segment anything[R]. Paris:2023 IEEE/CVF International Conference on Computer Vision (ICCV), 2023.
[12] CHEN T, SAXENA S, LI L L, et al. Pix2seq: A language modeling framework for object detection[DB/OL]. (2022-03-27)[2024-04-12]. https://arxiv.org/abs/2109.10852.
[13] WANG X L, ZHANG X S, CAO Y, et al. SegGPT: Towards segmenting everything in context[R]. Paris:2023 IEEE/CVF International Conference on Computer Vision (ICCV), 2023.
[14] RADFORD A, KIM J W, HALLACY C, et al.Learning transferable visual models from natural language supervision[J]. Proceedings of Machine Learning Research, 2021, 139: 8748-8763.
[15] JIA C, YANG Y F, XIA Y, et al.Scaling up visual and vision-language representation learning with noisy text supervision[J]. Proceedings of Machine Learning Research, 2021, 139: 4904-4916.
[16] ZHAI X H, WANG X, MUSTAFA B, et al. LiT: Zero-shot transfer with locked-image text tuning[R]. New Orleans:2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
[17] SUN Q, FANG Y X, WU L, et al. EVA-CLIP: Improved training techniques for CLIP at scale[DB/OL]. (2023-03-27)[2024-04-12]. https://arxiv.org/abs/2303.15389.
[18] GIRDHAR R, EL-NOUBY A, LIU Z, et al. ImageBind one embedding space to bind them all[R]. Vancouver:2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023.
[19] HONG Y N, ZHEN H Y, CHEN P H, et al.3D-LLM: Injecting the 3D world into large language models[C]//OH A, NAUMANN T, GLOBERSON A, et al. Advances in Neural Information Processing Systems 36 (NeurIPS 2023). Red Hook: Curran Associates, Inc., 2023: 20482-20494.
[20] ROMBACH R, BLATTMANN A, LORENZ D, et al. High-resolution image synthesis with latent diffusion models[R]. New Orleans:2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
[21] HU A, RUSSELL L, YEO H, et al. GAIA-1: A generative world model for autonomous driving[DB/OL]. (2023-09-29)[2024-04-12]. https://arxiv.org/abs/2309.17080.
[22] WANG W H, CHEN Z, CHEN X K, et al.VisionLLM: Large language model is also an open-ended decoder for vision-centric tasks[C]//OH A, NAUMANN T, GLOBERSON A, et al. Advances in Neural Information Processing Systems 36 (NeurIPS 2023). Red Hook: Curran Associates, Inc., 2023: 61501-61513.
[23] YUAN H B, LI X T, ZHOU C, et al. Open-vocabulary SAM: Segment and recognize twenty-thousand classes interactively[DB/OL]. (2024-01-05)[2024-04-12]. https://arxiv.org/abs/2401.02955.
[24] WU J F, JIANG Y, LIU Q H, et al. General object foundation model for images and videos at scale[DB/OL]. (2023-12-14)[2024-04-12]. https://arxiv.org/abs/2312.09158.
[25] LIU H T, LI C Y, WU Q Y, et al.Visual instruction tuning[C]//OH A, NAUMANN T, GLOBERSON A, et al. Advances in Neural Information Processing Systems 36 (NeurIPS 2023). Red Hook: Curran Associates, Inc., 2023: 34892-34916.
[26] ZHU D Y, CHEN J, SHEN X Q, et al. MiniGPT-4: Enhancing vision-language understanding with advanced large language models[DB/OL]. (2023-10-02)[2024-04-12]. https://arxiv.org/abs/2304. 10592.
[27] WANG W H, LV Q S, YU W M, et al. CogVLM: Visual expert for pretrained language models[DB/OL]. (2024-02-04)[2024-04-12]. https://arxiv.org/abs/2311.03079.
[28] LIN Z, LIU C, ZHANG R R, et al. SPHINX: The joint mixing of weights, tasks,visual embeddings for multi-modal large language models[DB/OL]. (2023-11-13)[2024-04-12]. https://arxiv. org/abs/2311.07575.
[29] ICHTER B, BROHAN A, CHEBOTAR Y, et al.Do as I can, not as I say: Grounding language in robotic affordances[J]. Proceedings of Machine Learning Research, 2023, 205: 287-318.
[30] O’NEILL A, REHMAN A, MADDUKURI A, et al. Open X-embodiment: Robotic learning datasets and RT-X models[DB/OL]. (2024-04-02)[2024-04-12]. https://arxiv.org/abs/2310.08864.
[31] LIAO H C, SHEN H M, LI Z N, et al.GPT-4 enhanced multimodal grounding for autonomous driving: Leveraging cross-modal attention with large language models[J]. Communications in Transportation Research, 2024, 4: 100116.
[32] ZHOU Y S, HUANG L Y, BU Q W, et al. Embodied understanding of driving scenarios[DB/OL]. (2024-03-07)[2024-04-12]. https://arxiv.org/ abs/2403.04593.
[33] MAO J G, QIAN Y X, YE J J, et al. GPT-driver: Learning to drive with GPT[J]. (2023-12-05)[2024-04-12]. https://arxiv.org/abs/2310. 01415.
[34] SHA H, MU Y, JIANG Y X, et al. LanguageMPC: Large language models as decision makers for autonomous driving[DB/OL]. (2023-10-13)[2024-04-12]. https://arxiv.org/abs/2310.03026.
[35] TIAN X Y, GU J R, LI B L, et al. DriveVLM: The convergence of autonomous driving and large vision-language models[DB/OL]. (2024-03-31)[2024-04-12]. https://arxiv.org/abs/2402.12289.
[36] WEN L C, FU D C, LI X, et al. DiLu: A knowledge-driven approach to autonomous driving with large language models[DB/OL]. (2024-02-22)[2024-04-12]. https://arxiv.org/abs/2309.16292.
[37] ] SHAO H, HU Y X, WANG L T, et al. LMDrive: Closed-loop end-to-end driving with large language models[DB/OL]. (2023-12-21)[2024-04-12]. https://arxiv.org/abs/2312.07488.
[38] XU Z H, ZHANG Y J, XIE E Z, et al. DriveGPT4: Interpretable end-to-end autonomous driving via large language model[DB/OL]. (2024-03-14)[2024-04-12]. https://arxiv.org/abs/2310.01412.
[39] SIMA C, RENZ K, CHITTA K, et al. DriveLM: Driving with graph visual question answering[DB/OL]. (2023-12-21)[2024-04-12]. https://arxiv.org/abs/2312.14150.
[40] JIA F, MAO W X, LIU Y F, et al. ADriver-I: A general world model for autonomous driving[DB/OL]. (2023-11-22)[2024-04-12]. https://arxiv.org/abs/2311.13549.
[41] WANG X F, ZHU Z, HUANG G, et al. DriveDreamer: Towards real-world-driven world models for autonomous driving[DB/OL]. (2023-11-27)[2024-04-12]. https://arxiv.org/abs/2309.09777.
[42] ZHAO G S, WANG X F, ZHU Z, et al. DriveDreamer-2: LLM-enhanced world models for diverse driving video generation[DB/OL]. (2024-04-11)[2024-04-12]. https://arxiv.org/abs/2403.06845.
[43] WANG Y Q, HE J W, FAN L, et al. Driving into the future: Multiview visual forecasting and planning with world model for autonomous driving[DB/OL]. (2023-11-29)[2024-04-12]. https://arxiv. org/abs/2311.17918.
[44] YANG J Z, GAO S Y, QIU Y H, et al. Generalized predictive model for autonomous driving[DB/OL]. (2024-03-14)[2024-04-12]. https:// arxiv.org/abs/2403.09630.
[45] ZHANG L J, XIONG Y W, YANG Z, et al.Copilot4D: Learning unsupervised world models for autonomous driving via discrete diffusion[R]. Vienna: ICLR 2024, 2024.
[46] ZHENG W Z, CHEN W L, HUANG Y H, et al. OccWorld: Learning a 3D occupancy world model for autonomous driving[DB/OL]. (2023-11-27)[2024-04-12]. https://arxiv.org/abs/2311.16038.
[47] WU Y Q, LIU Y H, LIU Y F, et al. zhihaiLLM/ wisdomInterrogatory[DB/OL]. (2024-03-18)[2024-04-12]. https://github. com/zhihaiLLM/wisdomInterrogatory.
[48] 阿里云计算有限公司. 通义法睿[EB/OL].[2024-04-12]. https:// tongyi.aliyun.com/farui.
Alibaba Cloud Computing Co. Ltd.Tongyi Farui[EB/OL]. [2024-04-12]. https://tongyi.aliyun.com/farui.
[49] NGUYEN H T. A brief report on LawGPT 1.0: A virtual legal assistant based on GPT-3[DB/OL]. (2023-02-14)[2024-04-12]. https://arxiv.org/abs/2302.05729.
[50] DU Z X, QIAN Y J, LIU X, et al.GLM: General language model pretraining with autoregressive blank infilling[C]//MURESAN S, NAKOV P, VILLAVICENCIO A. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, PA: Association for Computational Linguistics, 2022: 320-335.
[51] HUANG Q Z, TAO M X, ZHANG C, et al. Lawyer LLaMA technical report[DB/OL]. (2023-10-14)[2024-04-12]. https://arxiv.org/abs/2305. 15062.
[52] YUE S B, CHEN W, WANG S Y, et al. DISC-LawLLM: Fine-tuning large language models for intelligent legal services[DB/OL]. (2023-09-23)[2024-04-12]. https://arxiv.org/abs/2309.11325.
[53] CUI J X, LI Z J, YAN Y, et al. ChatLaw: Open-source legal large language model with integrated external knowledge bases[DB/OL]. (2023-06-28)[2024-04-12]. https://arxiv.org/abs/2306.16092.
[54] WANG R S, DUAN Y F, LAM C, et al.IvyGPT: InteractiVe Chinese pathway language model in medical domain[C]//FANG L, PEI J, ZHAI G T, et al. Artificial intelligence. Singapore: Springer, 2024: 378-382.
[55] WANG R S, ZHOU R Z, CHEN H M, et al.WangRongsheng/ CareGPT[DB/OL]. [2024-04-12].https://github.com/WangRongsheng/ CareGPT.
[56] SINGHAL K, AZIZI S, TU T, et al.Large language models encode clinical knowledge[J]. Nature, 2023, 620(7972): 172-180.
[57] LI Y X, LI Z H, ZHANG K, et al.ChatDoctor: A medical chat model fine-tuned on a large language model meta-AI (LLaMA) using medical domain knowledge[J]. Cureus, 2023, 15(6): e40895.
[58] XIONG H L, WANG S, ZHU Y T, et al. DoctorGLM: Fine-tuning your Chinese doctor is not a herculean task[DB/OL]. (2023-04-17)[2024-04-12]. https://arxiv.org/abs/2304.01097.
[59] CHEN W, WANG Q S, LONG Z F, et al. DISC-FinLLM: A Chinese financial large language model based on multiple experts fine- tuning[DB/OL]. (2023-10-25)[2024-04-12]. https://arxiv.org/abs/2310.15205.
[60] LAI S Q, XU Z, ZHANG W J, et al. LLMLight: Large language models as traffic signal control agents[DB/OL]. (2024-03-05) [2024-04-12]. https://arxiv.org/abs/2312.16044.
[61] GitHub. SecGPT[DB/OL].[2024-04-12]. https://github.com/Clouditera/ secgpt.
[62] ECKROTH J, GIPSON M, BODEN J, et al.Answering natural language questions with OpenAI’s GPT in the petroleum industry[R]. SPE 214888-MS, 2023.
[63] Deep-time Digital Earth. GeoGPT[EB/OL].[2024-06-11]. https:// geogpt.deep-time.org.
[64] MARLOT M, SRIVASTAVA D N, WONG F K, et al.Unsupervised multitask learning for oil and gas language models with limited resources[R]. SPE 216402-MS, 2023.
[65] RODRIGUES R B M, PRIVATTO P I M, DE SOUSA G J, et al. PetroBERT: A domain adaptation language model for oil and gas applications in Portuguese[C]//PINHEIRO V, GAMALLO P, AMARO R, et al. Computational processing of the Portuguese language. Cham: Springer, 2022: 101-109.
[66] ABIJITH P Y, PATIDAR P, NAIR G, et al.Large language models trained on equipment maintenance text[R]. SPE 216336-MS, 2023.
[67] KUMAR P, KATHURIA S.Large language models (LLMs) for natural language processing (NLP) of oil and gas drilling data[R]. San Antonio: 2023 SPE Annual Technical Conference and Exhibition, 2023.
[68] AVINASH L, PRASHANTH P, PURNAPRAJNA M, et al.Enabling contextual natural language search on oil and gas databases[R]. SPE 216349-MS, 2023.
[69] SINGH A, JIA T X, NALAGATLA V.Generative AI enabled conversational Chabot for drilling and production analytics[R]. SPE 216267-MS, 2023.
[70] YI M, CEGLINSKI K, ASHOK P, et al.Applications of large language models in well construction planning and real-time operation[R]. SPE 217700-MS, 2024.
[71] MALIN C. World’s largest industrial LLM revealed![EB/OL]. (2024-03-04) [2024-05-29]. https://www.middleeastainews.com/p/ aramco-launches-largest-industrial-llm.
[72] TVERITNEV A, KHANJI M, ABDULLAH S, et al.Applying machine learning NLP algorithm for reconciliation geology and petrophysics in rock typing[R]. Abu Dhabi: Abu Dhabi International Petroleum Exhibition and Conference, 2023.
[73] OGUNDARE O, MADASU S, WIGGINS N.Industrial engineering with large language models: A case study of ChatGPT’s performance on oil & gas problems[R]. Athens, Greece: 2023 11th International Conference on Mechatronics and Control Engineering, 2023.
[74] WEI J, WANG X, SCHUURMANS D, et al.Chain-of-thought prompting elicits reasoning in large language models[J]. Advances in Neural Information Processing Systems, 2022, 35: 24824-24837.
[75] KUMAR A.Vision transformer based foundation model for oil reservoir forecasting view affiliations[R]. Oslo, Norway: 85th EAGE Annual Conference & Exhibition, 2024.
[76] SABOO S, SHEKHAWAT D. Enhancing predictive maintenance in an oil & gas refinery using IoT, AI & ML: An generative AI solution[R]. Dharhan, Saudi Arabia: 16th International Petroleum Technology Conference (IPTC2024), 2024:.
[77] LIU H, REN Y L, LI X, et al.Rock thin-section analysis and identification based on artificial intelligent technique[J]. Petroleum Science, 2022, 19(4): 1605-1621.
[78] REN Y, LI X, BI J, et al. Multi-channel attention transformer for rock thin-section image segmentation[J]. Journal of Engineering Research, 2024: in press.
[79] 刘茜, 任义丽, 汪文洁, 等.基于语义分割的页岩孔隙结构智能表征方法[J/OL].北京航空航天大学学报. [2024-06-11]. https://doi.org/10. 13700/j.bh.1001-5965.2024.0018.
LIU Xi, REN Yili, WANG Wenjie, et al.Intelligent representation method of shale pore structure based on semantic segmentation[J/OL]. Journal of Beijing University of Aeronautics and Astronautics. [2024-06-11]. https://doi.org/10.13700/j.bh.1001-5965.2024.0018.
[80] 苏乾潇, 乔德新, 任义丽, 等.基于傅里叶卷积的电成像测井图像修复[J/OL]. 北京航空航天大学学报. [2024-04-12]. https://doi. org/10.13700/j.bh.1001-5965.2023.0754.
SU Qianxiao, QIAO Dexin, REN Yili, et al.Restoration of electrical imaging logging images based on Fourier convolution[J/OL]. Journal of Beijing University of Aeronautics and Astronautics. [2024-04-12]. https://doi.org/10.13700/j.bh.1001-5965.2023.0754.
[81] ZHENG Q, ZHANG D X.RockGPT: Reconstructing three- dimensional digital rocks from single two-dimensional slice with deep learning[J]. Computational Geosciences, 2022, 26(3): 677-696.
[82] SHENG H L, WU X M, SI X, et al. Seismic Foundation Model (SFM): A new generation deep learning model in geophysics[EB/OL]. (2023-12-15)[2024-04-12]. https://arxiv.org/abs/2309.02791.
[83] ZHANG Z, TANG J, FAN B, et al.An intelligent lithology recognition system for continental shale by using digital coring images and convolutional neural networks[J]. Geoenergy Science and Engineering, 2024: 212909.
[84] LI X J, ZHANG T, ZHU Y, et al. Artificial general intelligence (AGI) for the oil and gas industry: A review[EB/OL]. (2024-06-02) [2024-06-10]. https://arxiv.org/abs/2406.00594.
[85] MA Z, HE X, SUN S, et al. Zero-shot digital rock image segmentation with a fine-tuned segment anything model[EB/OL]. (2023-11-17)[2024-06-10]. https://arxiv.org/abs/ 2311.1086.
[86] WU W H, WONG M S, YU X Y, et al. Compositional oil spill detection based on object detector and adapted segment anything model from SAR images[EB/OL]. (2024-01-15)[2024-04-12]. https://arxiv.org/abs/2401.07502.
[87] LIU S C, CHEN J X, HE B G, et al.Adapting segment anything model for shield tunnel water leakage segmentation[C]//CHEN J X, WANG W, JEON G. Proceedings of the 2023 Workshop on Advanced Multimedia Computing for Smart Manufacturing and Engineering. New York: Association for Computing Machinery, 2023: 13-18.
[88] ZHAO W X, ZHOU K, LI J, et al. A survey of large language models[EB/OL]. (2023-11-24)[2024-06-11]. https://arxiv.org/abs/2303. 18223.
Options
Outlines

/

〈 〉

Copyright © Petroleum Exploration and Development
Address:P. O. Box 910, No.20 Xueyuan Road, Haidian District, Beijing 100083, China
Powered by Beijing Magtech Co. Ltd.