人工智能大模型在油气勘探开发领域的应用及挑战

doi:10.3969/j.issn.1002-302X.2024.06.013

石油科技论坛 ›› 2024, Vol. 43 ›› Issue (6): 107-113.DOI: 10.3969/j.issn.1002-302X.2024.06.013

人工智能大模型在油气勘探开发领域的应用及挑战

杨明澔^1,2,李小波^1,2,3,刘兴邦^1,2,曾倩^1,2

1. 中国石油勘探开发研究院人工智能研究中心； 2. 中国石油天然气集团有限公司勘探开发人工智能技术研发中心； 3. 多资源协同陆相页岩油绿色开采全国重点实验室

出版日期:2024-12-31 发布日期:2025-01-24
作者简介:杨明澔，1997年生，2022年毕业于悉尼大学，硕士，助理工程师，现从事人工智能技术在油气藏开发中的应用研究工作。
基金资助:
国家重点研发计划“二氧化碳驱油封存中的人工智能技术与应用研究”（编号：2023YFE0119600）；中国石油天然气集团有限公司“十四五”重点科技项目“油气勘探开发人工智能关键技术研究”（编号：2023DJ84-06）。

Application of Artificial Intelligence Pretrained Foundation Models in Exploration and Development and Challenges in This Area

Yang Minghao^1,2,Li Xiaobo^1,2,3,Liu Xingbang^1,2,Zeng Qian^1,2

1. AI Research Center, PetroChina Research Institute of Petroleum Exploration & Development, Beijing 100083, China;2.Artificial Intelligence Technology R&D Center for Exploration and Development, CNPC, Beijing 100083, China;3. National Key Laboratory for Green Mining of Multi-resource Collaborative Continental Shale Oil, Daqing 163712,China

Online:2024-12-31 Published:2025-01-24

摘要/Abstract

摘要： 自2022年底ChatGPT 发布以来，人工智能正在从弱人工智能走向以大模型为代表的强人工智能阶段，大模型能力快速提升，行业场景落地应用成为产投研各方关注热点。通过调研语言、图像和多模态大模型在油气勘探开发领域知识管理、地震解释、实验图像分析、生成数据分析、设备预测性维护等方面的应用情况，显示人工智能大模型在油气勘探开发领域应用需求巨大。受油气勘探开发领域业务和数据特征影响，人工智能大模型的落地应用还面临专业数据融合、领域认知深度和大模型应用安全等多方挑战。随着人工智能大模型技术在多模态能力、上下文学习、智能体及具身智能等方面取得的新进展，有望进一步提升其在解决油气勘探开发领域复杂任务的能力，加速油气上游业务的数字化转型和智能化发展。

关键词: 人工智能；大模型；勘探开发；应用场景；技术挑战；研发进展

Abstract: Artificial intelligence (AI) has developed towards the powerful stage characterized for pretrained foundation models from the weak one since ChatGPT was released at the end of 2022. With the capability of pretrained foundation models rising rapidly, actual application of industrial scenarios has become a focus of concerns from the production, investment and research communities.Base on investigation of languages, images and multi-model state, pretrained foundation models can be used in the oil and gas exploration and development area for knowledge management, seismic interpretation, experimental image analysis, generation of data analysis and predictive maintenance of equipment. Obviously, the demand for application of AI pretrained foundation models is huge in the oil and gas exploration and development area. Influenced by the characterizations of oil and gas business and data, actual application of AI pretrained foundation models still faced some challenges, such as integration of specialized data, depth of domain understanding and safety for application of pretrained foundation models. With the new progress made in the areas of multi-model state capability, context learning, Agent and embodied artificial intelligence, AI pretrained foundation model technology will hopefully improve the ability for settlement of complicated tasks in the oil and gas exploration and development area and accelerate digital transformation and intelligent development of the oil and gas upstream business.

Key words: artificial intelligence pretrained foundation models; exploration and development; application scenarios; challenges for technology; R&D progress

中图分类号:

TE319
TP18

杨明澔,李小波,刘兴邦,曾倩. 人工智能大模型在油气勘探开发领域的应用及挑战[J]. 石油科技论坛, 2024, 43(6): 107-113.

Yang Minghao,Li Xiaobo,Liu Xingbang,Zeng Qian. Application of Artificial Intelligence Pretrained Foundation Models in Exploration and Development and Challenges in This Area[J]. Petroleum Science and Technology Forum, 2024, 43(6): 107-113.

参考文献

[1] 刘合, 任义丽, 李欣, 等. 油气行业人工智能大模型应用研究现状及展望[J]. 石油勘探与开发, 2024, 51(4): 910-923.
Liu He, Ren Yili, Li Xin, et al. Research status and application of artificial intelligence large models in the oil and gas industry[J].Petroleum Exploration and Development, 2024, 51(4): 910-923.
[2] 刘合. 油气勘探开发数字化转型　人工智能应用大势所趋[J]. 石油科技论坛, 2023, 42(3): 1-9.
Liu He. Digital transformation of oil and gas exploration and development; unstoppable artificial intelligence application[J].Petroleum Science and Technology Forum, 2023, 42(3): 1-9.
[3] 葛文臣. 非常规油气资源勘探技术的发展与应用[J]. 石油石化物资采购, 2023(22): 91-93.
Ge Wenchen. Development and application of exploration technology for unconventional oil and gas resources [J]. Petroleum & Petrochemical Material Procurement, 2023(22): 91-93.
[4] Eckroth J, Gipson M, Boden J, et al. Answering natural language questions with OpenAI’s GPT in the petroleum industry[EB/OL].[2024-12-01]. https://dx. doi. org/10.2118/214888-MS. DOI: 10.2118/214888-MS.
[5] 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 International Publishing, 2022: 101-109.
[6] Abijith P Y, Patidar P, Nair G, et al. Large language models trained on equipment maintenance text[EB/OL]. [2024-12-01]. https://dx.doi.org/10.2118/216336-MS.
[7] Lokhande A, Pillai P, Mangsuli P. Enabling contextual natural language search on oil and gas databases[EB/OL]. [2024-12-01]. https://dx. doi.org/10.2118/216349-MS.
[8] Yi M, Ceglinski K, Ashok P, et al. Applications of large language models in well construction planning and real-time operation[EB/OL].[2024-12-01]. https://dx.doi.org/10.2118/217700-MS.
[9] Saboo S, Shekhawat D. Enhancing predictive maintenance in an oil & gas refinery using IoT, AI & ML: An generative AI solution[EB/OL].[2024-12-01]. https://dx.doi.org/10.2523/IPTC-23466-MS.
[10] Anonymous. ENERGYai at ADNOC[EB/OL]. [2024-12-01]. https://www.adnoc.ae/en/energy-ai.
[11] 杨明澔, 李小波, 曾倩, 等. 大语言模型在油气上游业务落地的技术实践[J]. 信息系统工程, 2024(6): 61-65.
Yang Minghao, Li Xiaobo, Zeng Qian, et al. Practice of large language model technology in oil and gas upstream sector [J]. China CIO News,2024(6): 61-65.
[12] Ogundare O, Madasu S, Wiggins N. Industrial engineering with large language models: A case study of ChatGPT’s performance on oil & gas problems[EB/OL]. [2024-12-01]. https://ieeexplore. ieee. org/document/10374622.
[13] Marlot M, Srivastava D N, Wong F K, et al. Unsupervised multitask learning for oil and gas language models with limited resources[EB/OL]. [2024-12-01]. https://dx.doi.org/10.2118/216402-MS.
[14] Kumar P, Kathuria S. Large language models (LLMs) for natural language processing (NLP) of oil and gas drilling data[C/OL]. [2024-12-01]. https://onepetro. org/SPEATCE/proceedings/23ATCE/2-23ATCE/D021S012R004/535656.
[15] Singh A, Jia T, Nalagatla V. Generative AI enabled conversational chatbot for drilling and production analytics[EB/OL]. [2024-10-29]. https://dx.doi.org/10.2118/216267-MS.
[16] Duff M. SLB launches AI-powered Lumi platform[EB/OL]. (2024-09-17) [2024-12-01]. https://www. slb. com/zh-cn/news-and-insights/newsroom/press-release/2024/slb-launches-ai-powered-lumi-platform.
[17] Tveritnev A, Khanji M, Abdullah S, et al. Applying machine learning NLP algorithm for reconciliation geology and petrophysics in rock typing[EB/OL]. [2024-10-29]. https://dx.doi.org/10.2118/216223-MS.
[18] Sheng H, Wu X, Si X, et al. Seismic foundation model (SFM): A new generation deep learning model in geophysics[EB/OL]. (2023-12-15)[2024-12-01]. http://arxiv.org/abs/2309.02791.
[19] Liu Q, Chen Z, Ma J. Foundation models for exploration geophysics [EB/OL]. (2024-12-10)[2024-12-01]. http://arxiv.org/abs/2406.03163.
[20] Liua 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.
[21] Zheng Q, Zhang D. RockGPT: Reconstructing three-dimensional digital rocks from single two-dimensional slice with deep learning[J].Computational Geosciences, 2022, 26(3): 677-696.
[22] 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, 239: 212909.
[23] 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)[2024-12-01]. http://arxiv.org/abs/2311.10865.
[24] Wu W, Wong M S, Yu X, et al. Compositional oil spill detection based on object detector and adapted segment anything model from sar images[J]. IEEE Geoscience and Remote Sensing Letters, 2024, 21:1-5.
[25] Liu S, Chen J, He B G, et al. Adapting segment anything model for shield tunnel water leakage segmentation[EB/OL] [2024-12-11]. https://dl.acm.org/doi/10.1145/3606042.3616453.
[26] Ura A, Minervini P, Fourrier C. The open medical-LLM leaderboard: Benchmarking large language models in healthcare[EB/OL]. [2024-09-30]. https://huggingface.co/blog/leaderboard-medicalllm.
[27] Sheng He, Rina Bao, Jingpeng Li, et al. Accuracy of segment-anything model (SAM) in medical image segmentation tasks[Z](2023). DOI:10.48550/arxiv.2304.09324.
[28] Liu H, Zheng Z, Qiao Y, et al. MathBench: Evaluating the theory and application proficiency of LLMS with a hierarchical mathematics benchmark[EB/OL]. (2024-05-20) [2024-12-01]. http://arxiv. org/abs/2405.12209.
[29] Fei Z, Shen X, Zhu D, et al. LawBench: Benchmarking legal knowledge of pretrained foundation models[J/OL]. (2023-09-28)[2024-12-01]. http://arxiv.org/abs/2309.16289.
[30] Chen J, Guo H, Yi K, et al. VisualGPT: Data-efficient adaptation of pretrained language models for image captioning[EB/OL]. (2022-03-30)[2024-10-17]. http://arxiv.org/abs/2102.10407.
[31] Zhang P, Dong X, Zang Y, et al. InternLM-xcomposer-2.5: A versatile large vision language model supporting long-contextual input and output[EB/OL]. (2024-07-03) [2024-10-16]. http://arxiv. org/abs/2407.03320.
[32] Hong W, Wang W, Ding M, et al. CogVLM2: Visual language models for image and video understanding[EB/OL]. (2024-08-29) [2024-10-17]. http://arxiv.org/abs/2408.16500.
[33] Chen Y, Qian S, Tang H, et al. LongLoRA: Efficient fine-tuning of long-context pretrained foundation models[EB/OL]. (2024-03-08)[2024-10-17]. http://arxiv.org/abs/2309.12307.
[34] Qian C, Liu W, Liu H, et al. ChatDev: Communicative agents for software development[EB/OL]. (2024-06-05) [2024-10-17]. http://arxiv.org/abs/2307.07924.
[35] Duan J, Yu S, Tan H L, et al. A survey of embodied AI: From simulators to research tasks[EB/OL]. (2022-01-05) [2024-10-16]. http://arxiv.org/abs/2103.04918.

人工智能大模型在油气勘探开发领域的应用及挑战

Application of Artificial Intelligence Pretrained Foundation Models in Exploration and Development and Challenges in This Area

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics