Data-driven deep-learning forecasting for oil production and pressure

被引:35
|
作者
Werneck, Rafael de Oliveira [1 ]
Prates, Raphael [1 ]
Moura, Renato [1 ]
Goncalves, Maiara Moreira [2 ]
Castro, Manuel [1 ]
Soriano-Vargas, Aurea [1 ]
Mendes Junior, Pedro Ribeiro [1 ]
Hossain, M. Manzur [2 ]
Zampieri, Marcelo Ferreira [2 ]
Ferreira, Alexandre [1 ]
Davolio, Alessandra [2 ]
Schiozer, Denis [2 ,3 ]
Rocha, Anderson [1 ]
机构
[1] Univ Estadual Campinas, Inst Comp, RECOD Ai, UNICAMP, BR-13083852 Campinas, SP, Brazil
[2] Univ Estadual Campinas, CEPETRO, UNICAMP, BR-13083970 Campinas, SP, Brazil
[3] Univ Estadual Campinas, Sch Mech Engn, BR-13083970 Campinas, SP, Brazil
关键词
Forecasting; Data-driven; Deep learning; Oil production; Pre-salt; NEURAL-NETWORK; PREDICTION;
D O I
10.1016/j.petrol.2021.109937
中图分类号
TE [石油、天然气工业]; TK [能源与动力工程];
学科分类号
0807 ; 0820 ;
摘要
Production forecasting plays an important role in oil and gas production, aiding engineers to perform field management. However, this can be challenging for complex reservoirs such as the highly heterogeneous carbonate reservoirs from Brazilian Pre-salt fields. We propose a new setup for forecasting multiple outputs using machine-learning algorithms and evaluate a set of deep-learning architectures suitable for time-series forecasting. The setup proposed is called N-th Day and it provides a coherent solution for the problem of forecasting multiple data points in which a sliding window mechanism guarantees there is no data leakage during training. We also devise four deep-learning architectures for forecasting, stacking the layers to focus on different timescales, and compare them with different existing off-the-shelf methods. The obtained results confirm that specific architectures, as those we propose, are crucial for oil and gas production forecasting. Although LSTM and GRU layers are designed to capture temporal sequences, the experiments also indicate that the investigated scenario of production forecasting requires additional and specific structures.
引用
收藏
页数:16
相关论文
共 50 条
  • [21] An integrated framework for plant data-driven process modeling using deep-learning with Monte-Carlo simulations
    Hwangbo, Soonho
    Al, Resul
    Sin, Gurkan
    COMPUTERS & CHEMICAL ENGINEERING, 2020, 143
  • [22] Data-Driven Models for Forecasting Failure Modes in Oil and Gas Pipes
    Elshaboury, Nehal
    Al-Sakkaf, Abobakr
    Alfalah, Ghasan
    Abdelkader, Eslam Mohammed
    PROCESSES, 2022, 10 (02)
  • [23] Data-driven Deep Reinforcement Learning for Automated Driving
    Prabu, Avinash
    Li, Lingxi
    Chen, Yaobin
    King, Brian
    2023 IEEE 26TH INTERNATIONAL CONFERENCE ON INTELLIGENT TRANSPORTATION SYSTEMS, ITSC, 2023, : 3790 - 3795
  • [24] Online big data-driven oil consumption forecasting with Google trends
    Yu, Lean
    Zhao, Yaqing
    Tang, Ling
    Yang, Zebin
    INTERNATIONAL JOURNAL OF FORECASTING, 2019, 35 (01) : 213 - 223
  • [25] Data-Driven Deep Learning for OTFS Detection br
    Gong, Yi
    Li, Qingyu
    Meng, Fanke
    Li, Xinru
    Xu, Zhan
    CHINA COMMUNICATIONS, 2023, 20 (01) : 88 - 101
  • [26] A Survey on Deep Learning for Data-Driven Soft Sensors
    Sun, Qingqiang
    Ge, Zhiqiang
    IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2021, 17 (09) : 5853 - 5866
  • [27] DL-PDE: Deep-Learning Based Data-Driven Discovery of Partial Differential Equations from Discrete and Noisy Data
    Xu, Hao
    Chang, Haibin
    Zhang, Dongxiao
    COMMUNICATIONS IN COMPUTATIONAL PHYSICS, 2021, 29 (03) : 698 - 728
  • [28] Model-driven deep-learning
    Xu, Zongben
    Sun, Jian
    NATIONAL SCIENCE REVIEW, 2018, 5 (01) : 22 - 24
  • [29] Toward Data-Driven Weather and Climate Forecasting: Approximating a Simple General Circulation Model With Deep Learning
    Scher, S.
    GEOPHYSICAL RESEARCH LETTERS, 2018, 45 (22) : 12616 - 12622
  • [30] Data-Driven Hybrid Model for Forecasting Wastewater Influent Loads Based on Multimodal and Ensemble Deep Learning
    Heo, SungKu
    Nam, KiJeon
    Loy-Benitez, Jorge
    Yoo, ChangKyoo
    IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2021, 17 (10) : 6925 - 6934