Prediction model of TOC contents in source rocks with different salinity degrees based on Support Vector Machine (SVM)
The total organic carbon (TOC) content is an important parameter for the evaluation of abundance of organic matter in source rocks, and its predicting accuracy is of great significance to oil and gas exploration and development. At present, TOC prediction is mainly based on statistical analysis meth...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Office of Petroleum Geology and Experiment
2022-07-01
|
| Series: | Shiyou shiyan dizhi |
| Subjects: | |
| Online Access: | https://www.sysydz.net/cn/article/doi/10.11781/sysydz202204739 |
| _version_ | 1797277320214478848 |
|---|---|
| author | Yongzhi CHU Chenglin LIU Wanxue TAI Hong YANG |
| author_facet | Yongzhi CHU Chenglin LIU Wanxue TAI Hong YANG |
| author_sort | Yongzhi CHU |
| collection | DOAJ |
| description | The total organic carbon (TOC) content is an important parameter for the evaluation of abundance of organic matter in source rocks, and its predicting accuracy is of great significance to oil and gas exploration and development. At present, TOC prediction is mainly based on statistical analysis methods such as ΔlogR method and multiple regression analysis, problems such as weak generalization ability and strong subjectivity exist. The introduction of machine learning methods can effectively solve these problems of instability, nonlinearity, and high complexity. However, current research remains at the level of method comparison and selection with no indepth analysis of good models and their applicability. In this paper, a Support Vector Machine (SVM) model with better application effects was used to predict TOC contents of source rocks with different salinity degrees. As source rocks of freshwater lacustrine facies, the Paleogene Dongying Formation in the Bozhong Sag of Bohai Bay Basin and Paleogene source rocks in the Shizigou area of the western Qaidam Basin as saline lacustrine facies source rocks were selected to test and compare the effectiveness of the model. Through correlation analysis and XGBoost feature importance analysis, the logging sonic differential time (DT), volume density (DEN), spontaneous potential (SP), Gamma ray (GR) and depth were selected as the input layer, while the TOC was used as the output layer to establish a TOC prediction model based on SVM. Results show a strong generalization ability when applied to different sedimentary environments. It can adapt to the geological characteristics of different regions. The sensitivity of logging curves to the abundance of organic matter in source rocks varies in different sedimentary environments, which makes the model more relevant when applying to the fresh water lacustrine facies area in the Bohai Bay Basin. |
| first_indexed | 2024-03-07T15:46:57Z |
| format | Article |
| id | doaj.art-e458e0f03406456bb76d4eb10d44933b |
| institution | Directory Open Access Journal |
| issn | 1001-6112 |
| language | zho |
| last_indexed | 2024-03-07T15:46:57Z |
| publishDate | 2022-07-01 |
| publisher | Editorial Office of Petroleum Geology and Experiment |
| record_format | Article |
| series | Shiyou shiyan dizhi |
| spelling | doaj.art-e458e0f03406456bb76d4eb10d44933b2024-03-05T04:29:57ZzhoEditorial Office of Petroleum Geology and ExperimentShiyou shiyan dizhi1001-61122022-07-0144473974610.11781/sysydz202204739sysydz-44-4-739Prediction model of TOC contents in source rocks with different salinity degrees based on Support Vector Machine (SVM)Yongzhi CHU0Chenglin LIU1Wanxue TAI2Hong YANG3State Key Laboratory of Petroleum Resources and Prospecting, China University of Petroleum (Beijing), Beijing 102249, ChinaState Key Laboratory of Petroleum Resources and Prospecting, China University of Petroleum (Beijing), Beijing 102249, ChinaState Key Laboratory of Petroleum Resources and Prospecting, China University of Petroleum (Beijing), Beijing 102249, ChinaState Key Laboratory of Petroleum Resources and Prospecting, China University of Petroleum (Beijing), Beijing 102249, ChinaThe total organic carbon (TOC) content is an important parameter for the evaluation of abundance of organic matter in source rocks, and its predicting accuracy is of great significance to oil and gas exploration and development. At present, TOC prediction is mainly based on statistical analysis methods such as ΔlogR method and multiple regression analysis, problems such as weak generalization ability and strong subjectivity exist. The introduction of machine learning methods can effectively solve these problems of instability, nonlinearity, and high complexity. However, current research remains at the level of method comparison and selection with no indepth analysis of good models and their applicability. In this paper, a Support Vector Machine (SVM) model with better application effects was used to predict TOC contents of source rocks with different salinity degrees. As source rocks of freshwater lacustrine facies, the Paleogene Dongying Formation in the Bozhong Sag of Bohai Bay Basin and Paleogene source rocks in the Shizigou area of the western Qaidam Basin as saline lacustrine facies source rocks were selected to test and compare the effectiveness of the model. Through correlation analysis and XGBoost feature importance analysis, the logging sonic differential time (DT), volume density (DEN), spontaneous potential (SP), Gamma ray (GR) and depth were selected as the input layer, while the TOC was used as the output layer to establish a TOC prediction model based on SVM. Results show a strong generalization ability when applied to different sedimentary environments. It can adapt to the geological characteristics of different regions. The sensitivity of logging curves to the abundance of organic matter in source rocks varies in different sedimentary environments, which makes the model more relevant when applying to the fresh water lacustrine facies area in the Bohai Bay Basin.https://www.sysydz.net/cn/article/doi/10.11781/sysydz202204739toc predictionlogging datasupport vector machinebohai bay basinqaidam basin |
| spellingShingle | Yongzhi CHU Chenglin LIU Wanxue TAI Hong YANG Prediction model of TOC contents in source rocks with different salinity degrees based on Support Vector Machine (SVM) Shiyou shiyan dizhi toc prediction logging data support vector machine bohai bay basin qaidam basin |
| title | Prediction model of TOC contents in source rocks with different salinity degrees based on Support Vector Machine (SVM) |
| title_full | Prediction model of TOC contents in source rocks with different salinity degrees based on Support Vector Machine (SVM) |
| title_fullStr | Prediction model of TOC contents in source rocks with different salinity degrees based on Support Vector Machine (SVM) |
| title_full_unstemmed | Prediction model of TOC contents in source rocks with different salinity degrees based on Support Vector Machine (SVM) |
| title_short | Prediction model of TOC contents in source rocks with different salinity degrees based on Support Vector Machine (SVM) |
| title_sort | prediction model of toc contents in source rocks with different salinity degrees based on support vector machine svm |
| topic | toc prediction logging data support vector machine bohai bay basin qaidam basin |
| url | https://www.sysydz.net/cn/article/doi/10.11781/sysydz202204739 |
| work_keys_str_mv | AT yongzhichu predictionmodeloftoccontentsinsourcerockswithdifferentsalinitydegreesbasedonsupportvectormachinesvm AT chenglinliu predictionmodeloftoccontentsinsourcerockswithdifferentsalinitydegreesbasedonsupportvectormachinesvm AT wanxuetai predictionmodeloftoccontentsinsourcerockswithdifferentsalinitydegreesbasedonsupportvectormachinesvm AT hongyang predictionmodeloftoccontentsinsourcerockswithdifferentsalinitydegreesbasedonsupportvectormachinesvm |