Oil reservoir sweet spot identification method based on Shapelet-Transformer

doi:10.11772/j.issn.1001-9081.2025081033

Journal of Computer Applications ›› 2026, Vol. 46 ›› Issue (9): 3054-3064.DOI: 10.11772/j.issn.1001-9081.2025081033

• Frontier and comprehensive applications • Previous Articles

Oil reservoir sweet spot identification method based on Shapelet-Transformer

Mingzhe LIU¹, Xiaoqin XIONG¹(), Shixun BAI², Renbao ZHAO³, Ziwei WANG⁴, Faqiang GOU⁴, Liang XU⁴

^1.School of Engineering，China University of Petroleum - Beijing at Karamay，Karamay Xinjiang 834000，China
^2.School of Petroleum，China University of Petroleum - Beijing at Karamay，Karamay Xinjiang 834000，China
^3.College of Petroleum Engineering，China University of Petroleum - Beijing，Beijing 102249，China
^4.Operation District of Shixi Oilfield，PetroChina Xinjiang Oilfield Company，Karamay Xinjiang 834000，China

Received:2025-09-09 Revised:2025-11-03 Accepted:2025-11-10 Online:2026-09-16 Published:2026-09-10
Contact: Xiaoqin XIONG
About author:LIU Mingzhe， born in 1999， M. S. candidate. Her research interests include intelligent identification of sweet spots in oil reservoirs.
XIONG Xiaoqin， born in 1983， M. S.， associate professor. Her research interests include oil and gas storage and transportation， sweet spot capacity matching.
BAI Shixun， born in 1990， Ph. D.， associate professor. His research interests include unconventional oil and gas sweet spot identification and development.
ZHAO Renbao， born in 1971， Ph. D.， professor. His research interests include oil reservoir sweet spot prediction.
WANG Ziwei， born in 1999， assistant engineer. Her research interests include sweet spot positioning in oil and gas fields.
GOU Faqiang， born in 1995， engineer. His research interests include well placement in oil and gas fields.
XU Liang， born in 1993， engineer. His research interests include oil and gas sweet spot productivity prediction.
Supported by:
Xinjiang Tianshan Innovative Research Team Project(2022TSYCTD0002)

基于Shapelet-Transformer的油层甜点识别方法

刘明喆¹, 熊小琴¹(), 白世勋², 赵仁保³, 王子薇⁴, 苟发强⁴, 徐亮⁴

^1.中国石油大学（北京）克拉玛依校区工学院，新疆克拉玛依 834000
^2.中国石油大学（北京）克拉玛依校区石油学院，新疆克拉玛依 834000
^3.中国石油大学（北京）石油工程学院，北京 102249
^4.中国石油新疆油田公司石西油田作业区，新疆克拉玛依 834000

通讯作者: 熊小琴
作者简介:刘明喆（1999—），女，山西太原人，硕士研究生，主要研究方向：油层甜点智能识别
熊小琴（1983—），女，重庆人，副教授，硕士，主要研究方向：油气储运、甜点产能匹配
白世勋（1990—），男，山东东营人，副教授，博士，主要研究方向：非常规油气甜点识别与开发
赵仁保（1971—），男，安徽和县人，教授，博士，主要研究方向：储层甜点预测
王子薇（1999—），女，甘肃天水人，助理工程师，主要研究方向：油气田甜点定位
苟发强（1995—），男，甘肃白银人，工程师，主要研究方向：油气田井位部署
徐亮（1993—），男，四川彭州人，工程师，主要研究方向：油气甜点产能预测。
基金资助:
新疆天山创新团队项目(2022TSYCTD0002)

Abstract

Abstract:

To address the issues that oil reservoir geological data are complex to represent and the existing methods struggle to fully extract the features of oil reservoir sweet spots， an oil reservoir sweet spot identification method based on Shapelet-Transformer was proposed. In this method， well log data were re-represented as a multi-variable depth sequence and a network model integrating local and global features was constructed to achieve accurate identification of oil reservoir sweet spots. First， a local feature learning unit was proposed， and the unique local well log response features of sweet spots were captured through the Shapelet extraction and selection mechanism. Second， a global feature learning mechanism was constructed to mine the global trend and parameter correlation of well log sequences， thereby providing global geological features. Finally， a fusion and classification module was designed to output the identification results of oil reservoir sweet spots by fusing local and global features. Experimental results show that the average identification accuracy of this method on the well log data of Ma 2 well block is 84.62 %， which is at least 1.26 percentage points higher than that of Fully Convolutional Neural Network （FCNN）， BiLSTM-FCNN （Bidirectional Long Short-Term Memory and FCNN hybrid model）， Temporal Graph Convolutional Network （T-GCN）， Disaggregated Multi-Scale Time Series decomposition model （DisMS-TS） and other benchmark models， which verifies the effectiveness of this method.

Key words: well log response sequence, Shapelet, local feature learning, global feature learning, oil reservoir sweet spot identification

摘要：

针对油藏地质数据表示复杂，现有方法难以充分提取油层甜点特征的问题，提出基于Shapelet-Transformer的油层甜点识别方法。该方法将测井数据重新表示为多变量深度序列，并构建融合局部与全局特征的网络模型，实现油层甜点的精准识别。首先，提出局部特征学习单元，通过Shapelet提取与筛选机制捕捉甜点特有的局部测井响应特征；其次，构建全局特征学习机制，挖掘测井序列的全局趋势与参数关联，提供全局地质特征；最后，设计融合分类模块，通过融合局部和全局特征输出油层甜点识别结果。实验结果表明，该方法在玛2井区的测井数据上的平均识别准确率达84.62%，较全卷积神经网络（FCNN）、BiLSTM-FCNN （Bidirectional Long Short-Term Memory and FCNN hybrid model）、图卷积时序网络（T-GCN）和多尺度时序分解模型（DisMS-TS）等基准模型至少提升了1.26个百分点，验证了该方法的有效性。

关键词: 测井响应序列, Shapelet, 局部特征学习, 全局特征学习, 油层甜点识别

CLC Number:

TP391.41

Mingzhe LIU, Xiaoqin XIONG, Shixun BAI, Renbao ZHAO, Ziwei WANG, Faqiang GOU, Liang XU. Oil reservoir sweet spot identification method based on Shapelet-Transformer[J]. Journal of Computer Applications, 2026, 46(9): 3054-3064.

刘明喆, 熊小琴, 白世勋, 赵仁保, 王子薇, 苟发强, 徐亮. 基于Shapelet-Transformer的油层甜点识别方法[J]. 《计算机应用》唯一官方网站, 2026, 46(9): 3054-3064.

Figures/Tables 16

Tab. 1 Eight key well log parameters and their physical meanings

名称	物理意义
SP	由地层水与泥浆的离子浓度差形成的电位，可有效区分砂岩与泥岩
RT	反映地层导电性，油层因含烃类流体通常呈现高阻特征
RI	辅助判断钻井液侵入程度，间接反映储层渗透性
RXO	反映钻井液冲洗后地层的残余电阻率，与储层含油性相关
AC	表征地层孔隙度大小，数值小指示地层致密，数值增大则反映孔隙发育
GR	反映地层放射性强度，黏土岩放射性最强，泥岩数值较高，砂岩数值较低
DEN	关联储层孔隙度与流体类型，低密度值通常对应高孔隙度地层
CNL	测量氢核含量占比，间接反映储层孔隙中流体体积百分比

Fig. 1 Overall architecture of proposed method

Fig. 2 Shapelet extraction

Fig. 3 Shapelet filtering

Fig. 4 Global feature learning module

Fig. 5 Histograms and crossplot of resistivity and sonic travel time for test interval in Well Ma20008

Fig. 6 Shapelet-Transformer model training results

Tab. 2 Identification results of different network models in oil-bearing reservoir intervals of Well Ma20008

序号	含油储层深度段		Shapelet-Transformer		DisMS-TS		T-GCN
序号	起始深度	终止深度	起始深度	终止深度	起始深度	终止深度	起始深度	终止深度
1	3 551.400	3 556.800	3 542.125	3 542.875	3 551.750	3 557.875	3 552.000	3 558.125
2	3 561.100	3 567.000	3 551.500	3 556.875	3 561.500	3 566.500	3 562.250	3 565.500
3	3 584.800	3 586.200	3 561.000	3 567.125	3 585.000	3 586.500	3 585.250	3 586.125
4	3 588.000	3 591.500	3 584.500	3 592.250	3 588.250	3 591.250	3 588.500	3 591.000
5	3 606.000	3 607.000	3 605.250	3 607.625	3 606.250	3 607.500	3 606.500	3 607.125
6	3 616.900	3 620.700	3 616.875	3 620.375	3 617.250	3 620.000	3 617.500	3 619.875
7	3 634.100	3 635.500	3 633.750	3 637.125	3 634.500	3 635.750	3 634.750	3 635.250
8	3 643.100	3 644.600	3 642.875	3 646.750	3 643.500	3 644.500	3 643.750	3 644.250
9	3 648.600	3 656.000	3 647.750	3 657.000	3 649.250	3 655.750	3 649.500	3 655.500
10	3 664.500	3 666.500	3 665.375	3 666.500	3 665.500	3 665.250	3 665.750	3 666.000
序号	BiLSTM-FCNN		FCNN		RNN		LSTM
序号	起始深度	终止深度	起始深度	终止深度	起始深度	终止深度	起始深度	终止深度
1	3 551.500	3 557.625	—	—	3 551.750	3 558.125	3 550.750	3 558.000
2	3 561.750	3 565.750	—	—	—	—	—	—
3	3 584.875	3 586.375	3 584.750	3 586.375	3 585.125	3 586.125	3 585.125	3 586.375
4	3 587.750	3 592.000	3 587.750	3 591.375	3 587.750	3 589.500	3 588.000	3 591.125
5	3 606.000	3 607.375	3 605.625	3 607.000	3 606.125	3 607.375	3 606.250	3 607.375
6	—	—	—	—	—	—	—	—
7	3 634.250	3 636.375	3 634.000	3 636.375	3 634.500	3 636.625	3 634.375	3 635.375
8	3 643.375	3 644.875	3 643.000	3 647.000	3 643.375	3 645.000	3 643.375	3 644.875
9	3 649.000	3 655.875	3 648.625	3 656.250	—	—	3 649.125	3 653.750
10	3 665.375	3 666.500	3 665.125	3 666.250	—	—	3 665.625	3 665.875

Fig. 7 Identification results of reservoir sweet spots of different network models in Well Ma20008

Tab. 3 Identification accuracy of different network models in different wells in Ma 2 well block

井号	FCNN	RNN	LSTM	BiLSTM-FCNN	T-GCN	DisMS-TS	Shapelet-Transformer
平均	79.78	78.88	81.98	80.40	83.04	83.36	84.62
Ma2217	81.64	82.81	80.08	83.20	82.50	81.80	83.20
Ma2220	72.09	77.25	79.24	79.07	78.90	79.50	80.62
Ma2295	70.61	79.69	78.52	80.08	79.80	80.20	80.92
Ma20006	87.89	69.63	84.39	71.67	86.50	87.20	89.01
Ma20008	86.65	85.04	87.69	87.96	87.50	88.10	89.34

Fig. 8 Comparison of identification accuracy among different network models in different wells in Ma 2 well block

Fig. 9 Shapelets and their best matching subsequence

Fig. 10 t-SNE visualization

Tab. 4 Impact of key hyperparameters on identification accuracy of Well Ma20008

超参数	取值	准确率/%	超参数	取值	准确率/%
batch size	8	79.2	Shapelet池容量 $g$	16	82.1
	16	85.5		32	85.6
	32	89.3		64	89.3
	64	86.5		128	87.8
学习率	1×10^-4	82.1	注意力头数	2	84.5
	5×10^-4	86.8		4	87.2
	1×10^-3	89.3		8	89.3
	5×10^-3	84.7		16	88.1

Tab. 4 Impact of key hyperparameters on identification accuracy of Well Ma20008

超参数	取值	准确率/%	超参数	取值	准确率/%
batch size	8	79.2	Shapelet池容量 $g$	16	82.1
	16	85.5		32	85.6
	32	89.3		64	89.3
	64	86.5		128	87.8
学习率	1×10^-4	82.1	注意力头数	2	84.5
	5×10^-4	86.8		4	87.2
	1×10^-3	89.3		8	89.3
	5×10^-3	84.7		16	88.1

Tab. 5 Classification accuracy comparison of different feature module combinations

井号	局部特征学习模块	全局特征学习模块	准确率
Ma2217	√	—	52.73
	—	√	82.81
	√	√	83.20
Ma2220	√	—	70.28
	—	√	79.84
	√	√	80.62
Ma2295	√	—	52.67
	—	√	79.39
	√	√	80.92
Ma20006	√	—	64.42
	—	√	80.53
	√	√	89.01
Ma20008	√	—	55.58
	—	√	86.35
	√	√	89.34
平均	√	—	59.14
	—	√	81.78
	√	√	84.62

Tab. 6 Comparison of inference time and accuracy among different models

模型	单井推理时间/ms	准确率/%	复杂度量级
FCNN	35.2	86.65	$O (105)$
RNN	89.6	85.04	$O (106)$
LSTM	112.4	87.69	$O (106)$
BiLSTM-FCNN	156.8	87.69	$O (106)$
T-GCN	160.0	87.50	$O (106)$
DisMS-TS	181.6	88.10	$O (106)$
本文方法	189.5	89.34	$O (107)$

Tab. 6 Comparison of inference time and accuracy among different models

模型	单井推理时间/ms	准确率/%	复杂度量级
FCNN	35.2	86.65	$O (105)$
RNN	89.6	85.04	$O (106)$
LSTM	112.4	87.69	$O (106)$
BiLSTM-FCNN	156.8	87.69	$O (106)$
T-GCN	160.0	87.50	$O (106)$
DisMS-TS	181.6	88.10	$O (106)$
本文方法	189.5	89.34	$O (107)$

References 42

[1]	吴宝成，吴承美，谭强，等. 准噶尔盆地吉木萨尔凹陷昌吉页岩油成藏条件及勘探开发关键技术［J］. 石油学报， 2024， 45（2）： 437-460.
	Wu Baocheng， Wu Chengmei， Tan Qiang， et al. Accumulation conditions and key technologies for exploration and development of Changji shale oil in Jimusar sag of Junggar Basin［J］. Acta Petrolei Sinica， 2024， 45（2）： 437-460.
[2]	翁定为，雷群，管保山，等. 中美页岩油气储层改造技术进展及发展方向［J］. 石油学报， 2023， 44（12）： 2297-2307.
	Weng Dingwei， Lei Qun， Guan Baoshan， et al. Progress and development directions of reservoir stimulation techniques for shale oil and gas in China and the United States ［J］. Acta Petrolei Sinica， 2023， 44（12）： 2297-2307.
[3]	万乔升，李雪英，赵玉秋，等. 齐家北地区高台子油层油水层识别方法［J］. 地球物理学进展， 2017， 32（2）： 714-720.
	Wan Qiaosheng， Li Xueying， Zhao Yuqiu， et al. Oil and water layer identification method of Gaotaizi reservoirs in Qijiabei area ［J］. Progress in Geophysics， 2017， 32（2）： 714-720.
[4]	Salim A M A， Pan H P， Luo M， et al. Integrated log interpretation in the Chinese continental scientific drilling main hole （Eastern China）： lithology and mineralization ［J］. Journal of Applied Sciences， 2008， 8（20）： 3593-3602.
[5]	Saggaf M M， Nebrija E L. Estimation of lithologies and depositional facies from wire-line logs ［J］. AAPG Bulletin， 2000， 84（10）： 1633-1646.
[6]	Otcere D A， Ganat T O A， Gholami R， et al. Application of supervised machine learning paradigms in the prediction of petroleum reservoir properties： comparative analysis of ANN and SVM models ［J］. Journal of Petroleum Science and Engineering， 2021， 200： No.108182.
[7]	李浩，刘双莲，魏修平. 浅析我国测井解释技术面临的问题与对策［J］. 地球物理学进展， 2010， 25（6）： 2084-2090.
	Li Hao， Liu Shuanglian， Wei Xiuping. Analysis of the problem and strategy in logging interpretation techniques in our country ［J］. Progress in Geophysics， 2010， 25（6）： 2084-2090.
[8]	张会雪. 莫里青油田伊59区块流体识别技术研究与应用［J］. 中国石油和化工标准与质量， 2023， 43（18）： 160-162.
	Zhang Huixue. Research and application of fluid identification technology in Yi 59 block of Moliqing oilfield ［J］. China Petroleum and Chemical Standard and Quality， 2023， 43（18）： 160-162.
[9]	宋鹏，杨卫国，孙栋，等. 华庆油田长6油藏油水层识别方法［J］. 大庆石油地质与开发， 2016， 35（6）： 144-147.
	Song Peng， Yang Weiguo， Sun Dong， et al. Oil-water-layer identifying method for reservoir Chang6 in Huaqing Oilfield ［J］. Petroleum Geology and Oilfield Development in Daqing， 2016， 35（6）： 144-147.
[10]	邹文波. 人工智能研究现状及其在测井领域的应用［J］. 测井技术， 2020， 44（4）： 323-328.
	Zou Wenbo. Artificial intelligence research status and applications in well logging ［J］. Well Logging Technology， 2020， 44（4）： 323-328.
[11]	安小平，李相方，郭海敏，等. RMT测井解释方法及软件开发研究［J］. 石油学报， 2005， 26（3）： 82-85.
	An Xiaoping， Li Xiangfang， Guo Haimin， et al. Logging interpretation and software development of reservoir monitor tool ［J］. Acta Petrolei Sinica， 2005， 26（3）： 82-85.
[12]	Singh U K. Fuzzy inference system for identification of geological stratigraphy off Prydz Bay， East Antarctica ［J］. Journal of Applied Geophysics， 2011， 75（4）： 687-698.
[13]	Amirgaliev E， Isabaev Z， Iskakov S， et al. Recognition of rocks at uranium deposits by using a few methods of machine learning ［M］// Rhee S Y， Park J， Inoue A. Soft computing in machine learning， AISC 273. Cham： Springer， 2014： 33-40.
[14]	Yang H， Pan H， Ma H， et al. Performance of the synergetic wavelet transform and modified K-means clustering in lithology classification using nuclear log ［J］. Journal of Petroleum Science and Engineering， 2016， 144： 1-9.
[15]	陈清华，程祥，王晶，等. 人工神经网络在闵北断块低阻油层识别上的应用［J］. 海洋地质前沿， 2015， 31（11）： 52-57.
	Chen Qinghua， Cheng Xiang， Wang Jing， et al. Application of artificial neural network to identification of low resistivity reservoir in the north block of Minqiao oilfield ［J］. Marine Geology Frontiers， 2015， 31（11）： 52-57.
[16]	Rogers S J， Fang J H， Karr C L， et al. Determination of lithology from well logs using a neural network ［J］. AAPG Bulletin， 1992， 76（5）： 731-739.
[17]	Silversides K， Melkumyan A， Wyman D， et al. Automated recognition of stratigraphic marker shales from geophysical logs in iron ore deposits ［J］. Computers and Geosciences， 2015， 77： 118-125.
[18]	安鹏，曹丹平，赵宝银，等. 基于LSTM循环神经网络的储层物性参数预测方法研究［J］. 地球物理学进展， 2019， 34（5）： 1849-1858.
	An Peng， Cao Danping， Zhao Baoyin， et al. Reservoir physical parameters prediction based on LSTM recurrent neural network ［J］. Progress in Geophysics， 2019， 34（5）： 1849-1858.
[19]	寻知锋，余继峰. 聚类和判别分析在测井岩性识别中的应用［J］. 山东科技大学学报（自然科学版）， 2008， 27（5）： 10-13.
	Xun Zhifeng， Yu Jifeng. The application of cluster and discriminant analyses in logging lithology recognition ［J］. Journal of Shandong University of Science and Technology （Natural Science）， 2008， 27（5）： 10-13.
[20]	Mu Z， Li C， Liu Z， et al. A deep learning identification method of tight sandstone lithofacies integrating multilayer perceptron and multivariate time series ［J］. Scientific Reports， 2024， 14： No.31252.
[21]	Grabocka J， Schilling N， Wistuba M， et al. Learning time-series Shapelets ［C］// KDD 2014. New York： ACM， 2014： 392-401.
[22]	Lines J， Davis L M， Hills J， et al. A shapelet transform for time series classification ［C］// KDD 2012. New York： ACM， 2012： 289-297.
[23]	王志海，张伟，原继东，等. 一种基于Shapelets的懒惰式时间序列分类算法［J］. 计算机学报， 2019， 42（1）： 29-43.
	Wang Zhihai， Zhang Wei， Yuan Jidong， et al. A novel lazy time series classification algorithm based on Shapelets ［J］. Chinese Journal of Computers， 2019， 42（1）： 29-43.
[24]	Grabocka J， Wistuba M， Schmidt-Thieme L. Fast classification of univariate and multivariate time series through shapelet discovery［J］. Knowledge and Information Systems， 2016， 49（2）： 429-454.
[25]	Li G， Choi B， Xu J， et al. ShapeNet： a shapelet-neural network approach for multivariate time series classification ［J］. Proceedings of the AAAI Conference on Artificial Intelligence， 2021， 35（9）： 8375-8383.
[26]	Le X M， Tran M T， Huynh V N. Learning perceptual position-aware shapelets for time series classification ［C］// ECML PKDD 2022， LNCS 13718. Cham： Springer， 2022： 53-69.
[27]	Vaswani A， Shazeer N， Parmar N， et al. Attention is all you need［C］// NeurIPS 2017. Red Hook： Curran Associates Inc.， 2017： 6000-6010.
[28]	范艺扬，张洋，曾尚，等. 基于分解和频域特征提取的多变量长时间序列预测模型［J］. 计算机应用， 2024， 44（11）： 3442-3448.
	Fan Yiyang， Zhang Yang， Zeng Shang， et al. Multivariate long-term series forecasting model based on decomposition and frequency-domain feature extraction ［J］. Journal of Computer Applications， 2024， 44（11）： 3442-3448.
[29]	Liu M， Ren S， Ma S， et al. Gated transformer networks for multivariate time series classification［PP/OL］. arXiv （2021-03-26）［2025-06-25］..
[30]	Foumani N M， Tan C W， Webb G I， et al. Improving position encoding of Transformers for multivariate time series classification［J］. Data Mining and Knowledge Discovery， 2024， 38（1）： 22-48.
[31]	Zuo R， Li G， Choi B， et al. SVP-T： a shape-level variable-position transformer for multivariate time series classification ［J］. Proceedings of the AAAI Conference on Artificial Intelligence， 2023， 37（9）： 11497-11505.
[32]	Devlin J， Chang M W， Lee K， et al. BERT： pre-training of deep bidirectional transformers for language understanding ［C］// NAACL-HLT 2019， Volume 1 （Long and Short Papers）. Stroudsburg： ACL， 2019： 4171-4186.
[33]	Tran M T， Le T， Le X M， et al. Text-enhanced data-free approach for federated class-incremental learning ［C］// CVPR 2024. Piscataway： IEEE， 2024： 23870-23880.
[34]	Tran M T， Le T， Le X M， et al. NAYER： noisy layer data generation for efficient and effective data-free knowledge distillation ［C］// CVPR 2024. Piscataway： IEEE， 2024： 23860-23869.
[35]	Yang C， Han J. Revisiting citation prediction with cluster-aware text-enhanced heterogeneous graph neural networks ［C］// ICDE 2023. Piscataway： IEEE， 2023： 682-695.
[36]	Yu W， Lin X， Ge J， et al. Semi-supervised collaborative filtering by text-enhanced domain adaptation ［C］// KDD 2020. New York： ACM， 2020： 2136-2144.
[37]	Le X-M， Luo L， Aickelin U， et al. ShapeFormer： shapelet Transformer for multivariate time series classification ［C］// KDD 2024. New York： ACM， 2024： 1484-1494.
[38]	Ma K， Sun X， Zhang Z， et al. Intelligent location of microseismic events based on a Fully Convolutional Neural Network （FCNN）［J］. Rock Mechanics and Rock Engineering， 2022， 55（8）： 4801-4817.
[39]	Sherstinsky A. Fundamentals of Recurrent Neural Network （RNN） and Long Short-Term Memory （LSTM） network ［J］. Physica D： Nonlinear Phenomena， 2020， 404： No.132306.
[40]	Abdullahi S B， Chamnongthai K， Gabralla L A， et al. ℱsign-Net： depth sensor aggregated frame-based Fourier network for sign word recognition ［J］. IEEE Sensors Journal， 2024， 24（22）： 37630-37645.
[41]	Huan C， Song S L， Liu Y， et al. T-GCN： a sampling based streaming graph neural network system with hybrid architecture［C］// PACT 2022. New York： ACM， 2022： 69-82.
[42]	Liu Z， Duan P， Wang B， et al. DisMS-TS： eliminating redundant multi-scale features for time series classification ［C］// MM 2025. New York： ACM， 2025： 10817-10826.

Oil reservoir sweet spot identification method based on Shapelet-Transformer

基于Shapelet-Transformer的油层甜点识别方法

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 16

References 42

Related Articles 6

Recommended Articles

Metrics

[1]	Miaomiao YUAN, Yihong CHU, Guanjun YIN, Chunhua DENG. High-precision recognition method for imperfect grain images based on TransNeXt [J]. Journal of Computer Applications, 2026, 46(5): 1684-1691.
[2]	Qianting ZHANG, Liying HU, Lifei CHEN. Robust shapelet representation method for time series [J]. Journal of Computer Applications, 2025, 45(2): 436-443.
[3]	Zhixiong ZHENG, Jianhua LIU, Shuihua SUN, Ge XU, Honghui LIN. Aspect-based sentiment analysis model fused with multi-window local information [J]. Journal of Computer Applications, 2023, 43(6): 1796-1802.
[4]	YAN Xinming, MENG Fanrong, YAN Qiuyan. Shapelet classification method based on trend feature representation [J]. Journal of Computer Applications, 2017, 37(8): 2343-2348.
[5]	YU Siqin, YAN Qiuyan, YAN Xinming. Clustering algorithm of time series with optimal u-shapelets [J]. Journal of Computer Applications, 2017, 37(8): 2349-2356.
[6]	SUN Qifa, YAN Qiuyan, YAN Xinming. Diversified top-k shapelets transform for time series classification [J]. Journal of Computer Applications, 2017, 37(2): 335-340.