Predicting long-term production dynamics in tight/shale gas reservoirs with dual-stage attention-based TEN-Seq2Seq model: A case study in Duvernay formation

期限(时间) 页岩气 石油工程 油页岩 对偶(语法数字) 阶段(地层学) 生产(经济) 地质学 致密气 环境科学 岩石学 水力压裂 古生物学 物理 经济 艺术 文学类 量子力学 宏观经济学
作者
Hai Yan Wu,Shuhua Wang,Shengnan Chen,Gang Hui
标识
DOI:10.1016/j.geoen.2023.211495
摘要

Production dynamics forecasting plays an important role in the decision-making and development scenario evaluation process throughout the entire life cycle of the unconventional tight/shale gas reservoirs. The traditional method such as decline curve analysis can't be applied prior to the wells are put into production as it heavily depends on the historical production for the estimation of parameters. In this work, a new artificial intelligence framework is proposed to predict the well behaviors by simultaneously processing the sequential and tabular data including well depth, proppant tonnage, and fracturing stages. Specifically, a time evolution network is employed first to encode the tabular features matrix into a pseudo-sequence tensor, and then an encoder-decoder architecture based on the dual-stage attention mechanism is used to extract effective information from the encoded information and capture long-term dependencies relationship. A comparison of the proposed model with the fully connected neural network (FCNN) and the long and short-term memory (LSTM) network indicates that the new framework has better generalization performance and robustness to predict well productivities, that is, the prediction errors are reduced by 65% and 50% respectively compared with LSTM and FCNN. Moreover, a bidirectional parametric rectified linear unit (BPReLU) is employed to adaptively learn the sign and magnitude of slopes. It is found that the error is further reduced by approximately 10% compared to that using PReLU. Also, four different target variables are defined, and the experimental results reveal that the average rate within the production time Vi is much easier to predict, with an average error of 19%.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
借一颗糖完成签到,获得积分10
2秒前
西兰花的科研小助手完成签到,获得积分10
4秒前
雨落发布了新的文献求助10
5秒前
月亮打盹儿完成签到 ,获得积分10
6秒前
田田完成签到,获得积分10
6秒前
橘子关注了科研通微信公众号
6秒前
小苹果完成签到,获得积分10
8秒前
WD完成签到 ,获得积分10
9秒前
10秒前
酷波er应助三和小神采纳,获得10
11秒前
cailiaokexue完成签到,获得积分10
12秒前
大个应助雨落采纳,获得10
12秒前
zz完成签到,获得积分10
14秒前
whq531608发布了新的文献求助30
14秒前
像心跳完成签到 ,获得积分10
15秒前
17秒前
17秒前
19秒前
20秒前
雨落完成签到,获得积分10
20秒前
enli完成签到,获得积分10
21秒前
寒冷晓凡发布了新的文献求助10
22秒前
Akim应助迷路以筠采纳,获得10
24秒前
31秒前
珊珊完成签到 ,获得积分10
34秒前
Shuai发布了新的文献求助10
35秒前
迷路以筠发布了新的文献求助10
36秒前
寒冷晓凡完成签到,获得积分10
38秒前
chenhunhun完成签到,获得积分10
39秒前
tingting完成签到,获得积分10
42秒前
隐形曼青应助冷言采纳,获得10
43秒前
43秒前
任性的梦菲完成签到,获得积分10
44秒前
香蕉觅云应助Kamelia采纳,获得10
44秒前
最好的完成签到,获得积分10
44秒前
44秒前
YAAAO发布了新的文献求助10
45秒前
落竹完成签到,获得积分10
46秒前
css1997完成签到 ,获得积分10
47秒前
zzl发布了新的文献求助10
47秒前
高分求助中
Continuum Thermodynamics and Material Modelling 3000
Production Logging: Theoretical and Interpretive Elements 2700
Les Mantodea de Guyane Insecta, Polyneoptera 1000
Structural Load Modelling and Combination for Performance and Safety Evaluation 1000
Conference Record, IAS Annual Meeting 1977 820
England and the Discovery of America, 1481-1620 600
電気学会論文誌D(産業応用部門誌), 141 巻, 11 号 510
热门求助领域 (近24小时)
化学 材料科学 生物 医学 工程类 有机化学 生物化学 物理 纳米技术 计算机科学 内科学 化学工程 复合材料 基因 遗传学 物理化学 催化作用 量子力学 光电子学 冶金
热门帖子
关注 科研通微信公众号,转发送积分 3572296
求助须知:如何正确求助?哪些是违规求助? 3142501
关于积分的说明 9448015
捐赠科研通 2843973
什么是DOI,文献DOI怎么找? 1563103
邀请新用户注册赠送积分活动 731630
科研通“疑难数据库(出版商)”最低求助积分说明 718640