Reservoir Porosity Construction Based on BiTCN-BiLSTM-AM Optimized by Improved Sparrow Search Algorithm

IF 2.8 4区工程技术 Q2 ENGINEERING, CHEMICAL

Processes Pub Date : 2024-09-05 DOI:10.3390/pr12091907

Lei Qiao, Haijun Gao, You Cui, Yang Yang, Shixin Liang, Kun Xiao

{"title":"Reservoir Porosity Construction Based on BiTCN-BiLSTM-AM Optimized by Improved Sparrow Search Algorithm","authors":"Lei Qiao, Haijun Gao, You Cui, Yang Yang, Shixin Liang, Kun Xiao","doi":"10.3390/pr12091907","DOIUrl":null,"url":null,"abstract":"To evaluate reservoir porosity accurately, a method based on the bidirectional temporal convolutional network (BiTCN), bidirectional long short-term memory network (BiLSTM), and attention mechanism (AM) optimized by the improved sparrow search algorithm (ISSA) is proposed. Firstly, the sparrow search algorithm improved by a phased control step size strategy and dynamic random Cauchy mutation is introduced. Secondly, the superiority of the ISSA is confirmed by the test functions of Congress on Evolutionary Computation in 2022 (CEC-2022). Furthermore, the experimental findings are assessed using the Wilcoxon test, which provides additional evidence of the ISSA’s superiority against the competing algorithms. Finally, the BiTCN-BiLSTM-AM is optimized by the ISSA, and the ISSA-BiTCN-BiLSTM-AM was applied to reservoir porosity construction in the Midlands basin. The results showed that the RMSE and MAE of the proposed model were 0.4293 and 0.5696, respectively, which verified the effectiveness and success rate of reservoir parameter construction by addressing the shortcomings in the capabilities shown by conventional interpretation procedures.","PeriodicalId":20597,"journal":{"name":"Processes","volume":"29 1","pages":""},"PeriodicalIF":2.8000,"publicationDate":"2024-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Processes","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.3390/pr12091907","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, CHEMICAL","Score":null,"Total":0}

引用次数: 0

Abstract

To evaluate reservoir porosity accurately, a method based on the bidirectional temporal convolutional network (BiTCN), bidirectional long short-term memory network (BiLSTM), and attention mechanism (AM) optimized by the improved sparrow search algorithm (ISSA) is proposed. Firstly, the sparrow search algorithm improved by a phased control step size strategy and dynamic random Cauchy mutation is introduced. Secondly, the superiority of the ISSA is confirmed by the test functions of Congress on Evolutionary Computation in 2022 (CEC-2022). Furthermore, the experimental findings are assessed using the Wilcoxon test, which provides additional evidence of the ISSA’s superiority against the competing algorithms. Finally, the BiTCN-BiLSTM-AM is optimized by the ISSA, and the ISSA-BiTCN-BiLSTM-AM was applied to reservoir porosity construction in the Midlands basin. The results showed that the RMSE and MAE of the proposed model were 0.4293 and 0.5696, respectively, which verified the effectiveness and success rate of reservoir parameter construction by addressing the shortcomings in the capabilities shown by conventional interpretation procedures.

查看原文本刊更多论文

通过改进的麻雀搜索算法优化基于 BiTCN-BiLSTM-AM 的储层孔隙度构造

为了准确评估储层孔隙度，提出了一种基于双向时空卷积网络（BiTCN）、双向长短期记忆网络（BiLSTM）和改进麻雀搜索算法（ISSA）优化的注意力机制（AM）的方法。首先，介绍了通过分阶段控制步长策略和动态随机考奇突变改进的麻雀搜索算法。其次，2022 年进化计算大会（CEC-2022）的测试功能证实了 ISSA 的优越性。此外，还使用 Wilcoxon 检验对实验结果进行了评估，从而进一步证明了 ISSA 相对于其他竞争算法的优越性。最后，ISSA 对 BiTCN-BiLSTM-AM 进行了优化，并将 ISSA-BiTCN-BiLSTM-AM 应用于 Midlands 盆地的储层孔隙度构建。结果表明，所提模型的 RMSE 和 MAE 分别为 0.4293 和 0.5696，解决了传统解释程序在能力上的不足，验证了储层参数构建的有效性和成功率。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Processes Chemical Engineering-Bioengineering

CiteScore

5.10

自引率

11.40%

发文量

2239

审稿时长

14.11 days

期刊介绍： Processes (ISSN 2227-9717) provides an advanced forum for process related research in chemistry, biology and allied engineering fields. The journal publishes regular research papers, communications, letters, short notes and reviews. Our aim is to encourage researchers to publish their experimental, theoretical and computational results in as much detail as necessary. There is no restriction on paper length or number of figures and tables.