Inter-well connectivity detection in CO2 WAG projects using statistical recurrent unit models

被引:9
|
作者
Sen, Deepthi [1 ]
Chen, Hongquan [1 ]
Datta-Gupta, Akhil [1 ]
机构
[1] Texas A&M Univ, College Stn, TX USA
关键词
CO2 WAG process; CO2; EOR; Inter-well connectivity; Statistical recurrent unit; Variable importance; Loss function regularization; RELATIVE IMPORTANCE; PATH LINES; NETWORKS; SYSTEMS;
D O I
10.1016/j.fuel.2021.122600
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
Routine well-wise injection and production measurements contain significant information on subsurface structure and properties. Data-driven technology that interprets surface data into subsurface structure or properties can assist operators in making informed decisions by providing a better understanding of field assets. Our machine-learning framework is built on the statistical recurrent unit (SRU) model and interprets well-based injection/production data into inter-well connectivity without relying on a geologic model. We test it on synthetic and field-scale CO2 EOR projects utilizing the water-alternating-gas (WAG) process. SRU is a special type of recurrent neural network (RNN) that allows for better characterization of temporal trends, by learning various statistics of the input at different time scales. In our application, the complete states (injection rate, pressure and cumulative injection) at injectors and pressure states at producers are fed to SRU as the input and the phase rates at producers are treated as the output. Once the SRU is trained and validated, it is then used to assess the connectivity of each injector to any producer using permutation variable importance method, wherein inputs corresponding to an injector are shuffled and the increase in prediction error at a given producer is recorded as the importance (connectivity metric) of the injector to the producer. This method is tested in both synthetic and field-scale cases. The validation of the proposed data-driven inter-well connectivity assessment is performed using synthetic data from simulation models where inter-well connectivity can be easily measured using the streamline-based flux allocation. The SRU model is shown to offer excellent prediction performance on the synthetic case. Despite significant measurement noise and frequent well shut-ins imposed in the field-scale case, the SRU model offers good prediction accuracy, the overall relative error of the phase production rates at most producers ranges from 10% to 30%. It is shown that the dominant connections identified by the data-driven method and streamline method are in close agreement. This significantly improves confidence in our data-driven procedure. The novelty of this work is that it is purely data-driven method and can directly interpret routine surface measurements to intuitive subsurface knowledge. Furthermore, the streamline-based validation procedure provides physics-based backing to the results obtained from data analytics. The study results in a reliable and efficient data analytics framework that is well-suited for large field applications.
引用
收藏
页数:17
相关论文
共 12 条
  • [1] Numerical modeling of the CO2 injection in the Kizildere geothermal field using multiple inter-well tracer tests
    Sevindik, Doguhan Barlas
    Erol, Selcuk
    Akin, Serhat
    [J]. GEOTHERMICS, 2024, 119
  • [2] Statistical performance of CO2 leakage detection using seismic travel time measurements
    Wang, Zan
    Small, Mitchell J.
    [J]. GREENHOUSE GASES-SCIENCE AND TECHNOLOGY, 2016, 6 (01): : 55 - 69
  • [3] Accurate occupancy detection of an office room from light, temperature, humidity and CO2 measurements using statistical learning models
    Candanedo, Luis M.
    Feldheim, Veronique
    [J]. ENERGY AND BUILDINGS, 2016, 112 : 28 - 39
  • [4] Life cycle cost and CO2 emission simulation models of apartment building projects using system dynamics
    Lim, Dong-Bum
    Son, Seunghyun
    Kim, Sunkuk
    Park, Junyoung
    [J]. INDOOR AND BUILT ENVIRONMENT, 2019, 28 (03) : 310 - 321
  • [5] Evaluation of Growth and CO2 Biofixation by Spirulina platensis in Different Culture Media Using Statistical Models
    Claudia Andrea, Carvajal Tatis
    Marianella Maria, Suarez Marenco
    Morgado Gamero, W. B.
    Rubiano Adriana, Sarmiento
    Alexander Elias, Parody Munoz
    Silva, Jesus
    [J]. COMPUTATIONAL VISION AND BIO-INSPIRED COMPUTING, 2020, 1108 : 697 - 707
  • [6] Using Statistical Models to Detect Occupancy in Buildings through Monitoring VOC, CO2, and Other Environmental Factors
    Varnosfaderani, Mahsa Pahlavikhah
    Heydarian, Arsalan
    Jazizadeh, Farrokh
    [J]. COMPUTING IN CIVIL ENGINEERING 2021, 2022, : 705 - 712
  • [7] Fast selection of geologic models honoring CO2 plume monitoring data using Hausdorff distance and scaled connectivity analysis
    Jeong, Hoonyoung
    Srinivasan, Sanjay
    [J]. INTERNATIONAL JOURNAL OF GREENHOUSE GAS CONTROL, 2017, 59 : 40 - 57
  • [8] Computer-based optimization of acid gas removal unit using modified CO2 absorption kinetic models
    Dara, Satyadileep
    Berrouk, Abdallah S.
    [J]. INTERNATIONAL JOURNAL OF GREENHOUSE GAS CONTROL, 2017, 59 : 172 - 183
  • [9] Mass flowrate measurement of two-phase CO2 in a transient process using a gated recurrent unit neural network model
    Ding, Ning
    Shao, Ding
    Yan, Yong
    Zhang, Wenbiao
    [J]. Yi Qi Yi Biao Xue Bao/Chinese Journal of Scientific Instrument, 2021, 42 (10): : 112 - 120
  • [10] CO2 storage well rate optimisation in the Forties sandstone of the Forties and Nelson reservoirs using evolutionary algorithms and upscaled geological models
    Babaei, Masoud
    Pan, Indranil
    Korre, Anna
    Shi, Ji-Quan
    Govindan, Rajesh
    Durucan, Sevket
    Quinn, Martyn
    [J]. INTERNATIONAL JOURNAL OF GREENHOUSE GAS CONTROL, 2016, 50 : 1 - 13