Classification of shale gas “sweet spot” based on Random Forest machine learning
The classification and identification of shale gas “sweet spot” involves a variety of different factors, which requires personal experience, and is usually time and resources consuming. In order to solve this problem, an efficient and effective classification and identification method for shale gas...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Department of Petroleum Reservoir Evaluation and Development
2023-06-01
|
| Series: | Youqicang pingjia yu kaifa |
| Subjects: | |
| Online Access: | https://red.magtech.org.cn/fileup/2095-1426/PDF/1687763795779-1455433064.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850132175479898112 |
|---|---|
| author | NIE Yunli, GAO Guozhong |
| author_facet | NIE Yunli, GAO Guozhong |
| author_sort | NIE Yunli, GAO Guozhong |
| collection | DOAJ |
| description | The classification and identification of shale gas “sweet spot” involves a variety of different factors, which requires personal experience, and is usually time and resources consuming. In order to solve this problem, an efficient and effective classification and identification method for shale gas “sweet spot” based on the Random Forest method is proposed. Firstly, data from ten wells in Changning area are selected and eleven features are selected for “sweet spot” classification by the Kendall correlation. Then, the single decision tree and the Random Forest method are used for the “sweet spot” classification and identification. Finally, the results are verified and the Random Forest parameters are optimized. The experimental results show that although the prediction accuracy of a single decision tree can reach 97.7 %, it shows a trend of overfitting, and the fitting accuracy is greatly reduced by only 70.7 % after pruning. The Random Forest method avoids the disadvantage of the single decision tree method, and the prediction accuracy reaches 98 %. Moreover, the computational cost is low, which can effectively reduce the time loss and save the labor cost. As a result, the proposed Random Forest machine learning method with multi-source information is an effective shale gas “sweet spot” classification and identification method. |
| format | Article |
| id | doaj-art-7fa970e8046e4f49822b93082404a749 |
| institution | OA Journals |
| issn | 2095-1426 |
| language | zho |
| publishDate | 2023-06-01 |
| publisher | Editorial Department of Petroleum Reservoir Evaluation and Development |
| record_format | Article |
| series | Youqicang pingjia yu kaifa |
| spelling | doaj-art-7fa970e8046e4f49822b93082404a7492025-08-20T02:32:15ZzhoEditorial Department of Petroleum Reservoir Evaluation and DevelopmentYouqicang pingjia yu kaifa2095-14262023-06-0113335836710.13809/j.cnki.cn32-1825/te.2023.03.011Classification of shale gas “sweet spot” based on Random Forest machine learningNIE Yunli, GAO Guozhong01. Cooperative Innovation Center of Unconventional Oil and Gas, Yangtze University（Ministry of Education & Hubei Province）, Wuhan, Hubei 430100, China;2. College of Geophysics and Petroleum Resources, Yangtze University, Wuhan, Hubei 430100, ChinaThe classification and identification of shale gas “sweet spot” involves a variety of different factors, which requires personal experience, and is usually time and resources consuming. In order to solve this problem, an efficient and effective classification and identification method for shale gas “sweet spot” based on the Random Forest method is proposed. Firstly, data from ten wells in Changning area are selected and eleven features are selected for “sweet spot” classification by the Kendall correlation. Then, the single decision tree and the Random Forest method are used for the “sweet spot” classification and identification. Finally, the results are verified and the Random Forest parameters are optimized. The experimental results show that although the prediction accuracy of a single decision tree can reach 97.7 %, it shows a trend of overfitting, and the fitting accuracy is greatly reduced by only 70.7 % after pruning. The Random Forest method avoids the disadvantage of the single decision tree method, and the prediction accuracy reaches 98 %. Moreover, the computational cost is low, which can effectively reduce the time loss and save the labor cost. As a result, the proposed Random Forest machine learning method with multi-source information is an effective shale gas “sweet spot” classification and identification method.https://red.magtech.org.cn/fileup/2095-1426/PDF/1687763795779-1455433064.pdf|shale gas|“sweet spot”|machine learning|decision tree|random forest |
| spellingShingle | NIE Yunli, GAO Guozhong Classification of shale gas “sweet spot” based on Random Forest machine learning Youqicang pingjia yu kaifa |shale gas|“sweet spot”|machine learning|decision tree|random forest |
| title | Classification of shale gas “sweet spot” based on Random Forest machine learning |
| title_full | Classification of shale gas “sweet spot” based on Random Forest machine learning |
| title_fullStr | Classification of shale gas “sweet spot” based on Random Forest machine learning |
| title_full_unstemmed | Classification of shale gas “sweet spot” based on Random Forest machine learning |
| title_short | Classification of shale gas “sweet spot” based on Random Forest machine learning |
| title_sort | classification of shale gas sweet spot based on random forest machine learning |
| topic | |shale gas|“sweet spot”|machine learning|decision tree|random forest |
| url | https://red.magtech.org.cn/fileup/2095-1426/PDF/1687763795779-1455433064.pdf |
| work_keys_str_mv | AT nieyunligaoguozhong classificationofshalegassweetspotbasedonrandomforestmachinelearning |