Comparison of Machine Learning Algorithms for Sand Production Prediction: An Example for a Gas-Hydrate-Bearing Sand Case
This paper demonstrates the applicability of machine learning algorithms in sand production problems with natural gas hydrate (NGH)-bearing sands, which have been regarded as a grave concern for commercialization. The sanding problem hinders the commercial exploration of NGH reservoirs. The common s...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/15/18/6509 |
| _version_ | 1797489004364431360 |
|---|---|
| author | Jinze Song Yuhao Li Shuai Liu Youming Xiong Weixin Pang Yufa He Yaxi Mu |
| author_facet | Jinze Song Yuhao Li Shuai Liu Youming Xiong Weixin Pang Yufa He Yaxi Mu |
| author_sort | Jinze Song |
| collection | DOAJ |
| description | This paper demonstrates the applicability of machine learning algorithms in sand production problems with natural gas hydrate (NGH)-bearing sands, which have been regarded as a grave concern for commercialization. The sanding problem hinders the commercial exploration of NGH reservoirs. The common sand production prediction methods need assumptions for complicated mathematical derivations. The main contribution of this paper was to introduce machine learning into the prediction sand production by using data from laboratory experiments. Four main machine learning algorithms were selected, namely, K-Nearest Neighbor, Support Vector Regression, Boosting Tree, and Multi-Layer Perceptron. Training datasets for machine learning were collected from a sand production experiment. The experiment considered both the geological parameters and the sand control effect. The machine learning algorithms were mainly evaluated according to their mean absolute error and coefficient of determination. The evaluation results showed that the most accurate results under the given conditions were from the Boosting Tree algorithm, while the K-Nearest Neighbor had the worst prediction performance. Considering an ensemble prediction model, the Support Vector Regression and Multi-Layer Perceptron could also be applied for the prediction of sand production. The tuning process revealed that the Gaussian kernel was the proper kernel function for improving the prediction performance of SVR. In addition, the best parameters for both the Boosting Tree and Multi-Layer Perceptron were recommended for the accurate prediction of sand production. This paper also involved one case study to compare the prediction results of the machine learning models and classic numerical simulation, which showed the capability of machine learning of accurately predicting sand production, especially under stable pressure conditions. |
| first_indexed | 2024-03-10T00:10:20Z |
| format | Article |
| id | doaj.art-a56e2501318b4a3da756b237d3ce8785 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-10T00:10:20Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-a56e2501318b4a3da756b237d3ce87852023-11-23T16:00:55ZengMDPI AGEnergies1996-10732022-09-011518650910.3390/en15186509Comparison of Machine Learning Algorithms for Sand Production Prediction: An Example for a Gas-Hydrate-Bearing Sand CaseJinze Song0Yuhao Li1Shuai Liu2Youming Xiong3Weixin Pang4Yufa He5Yaxi Mu6Petroleum and Natural Gas Engineering School, Southwest Petroleum University, Chengdu 610500, ChinaPetroleum and Natural Gas Engineering School, Southwest Petroleum University, Chengdu 610500, ChinaPetroleum and Natural Gas Engineering School, Southwest Petroleum University, Chengdu 610500, ChinaPetroleum and Natural Gas Engineering School, Southwest Petroleum University, Chengdu 610500, ChinaState Key Laboratory of Natural Gas Hydrates, Technology Research Department CNOOC Research, Beijing 100102, ChinaState Key Laboratory of Natural Gas Hydrates, Technology Research Department CNOOC Research, Beijing 100102, ChinaPetroleum and Natural Gas Engineering School, Southwest Petroleum University, Chengdu 610500, ChinaThis paper demonstrates the applicability of machine learning algorithms in sand production problems with natural gas hydrate (NGH)-bearing sands, which have been regarded as a grave concern for commercialization. The sanding problem hinders the commercial exploration of NGH reservoirs. The common sand production prediction methods need assumptions for complicated mathematical derivations. The main contribution of this paper was to introduce machine learning into the prediction sand production by using data from laboratory experiments. Four main machine learning algorithms were selected, namely, K-Nearest Neighbor, Support Vector Regression, Boosting Tree, and Multi-Layer Perceptron. Training datasets for machine learning were collected from a sand production experiment. The experiment considered both the geological parameters and the sand control effect. The machine learning algorithms were mainly evaluated according to their mean absolute error and coefficient of determination. The evaluation results showed that the most accurate results under the given conditions were from the Boosting Tree algorithm, while the K-Nearest Neighbor had the worst prediction performance. Considering an ensemble prediction model, the Support Vector Regression and Multi-Layer Perceptron could also be applied for the prediction of sand production. The tuning process revealed that the Gaussian kernel was the proper kernel function for improving the prediction performance of SVR. In addition, the best parameters for both the Boosting Tree and Multi-Layer Perceptron were recommended for the accurate prediction of sand production. This paper also involved one case study to compare the prediction results of the machine learning models and classic numerical simulation, which showed the capability of machine learning of accurately predicting sand production, especially under stable pressure conditions.https://www.mdpi.com/1996-1073/15/18/6509sand production predictionnatural gas hydratesmachine learningk-nearest neighborsupport vector regressionboosting tree |
| spellingShingle | Jinze Song Yuhao Li Shuai Liu Youming Xiong Weixin Pang Yufa He Yaxi Mu Comparison of Machine Learning Algorithms for Sand Production Prediction: An Example for a Gas-Hydrate-Bearing Sand Case Energies sand production prediction natural gas hydrates machine learning k-nearest neighbor support vector regression boosting tree |
| title | Comparison of Machine Learning Algorithms for Sand Production Prediction: An Example for a Gas-Hydrate-Bearing Sand Case |
| title_full | Comparison of Machine Learning Algorithms for Sand Production Prediction: An Example for a Gas-Hydrate-Bearing Sand Case |
| title_fullStr | Comparison of Machine Learning Algorithms for Sand Production Prediction: An Example for a Gas-Hydrate-Bearing Sand Case |
| title_full_unstemmed | Comparison of Machine Learning Algorithms for Sand Production Prediction: An Example for a Gas-Hydrate-Bearing Sand Case |
| title_short | Comparison of Machine Learning Algorithms for Sand Production Prediction: An Example for a Gas-Hydrate-Bearing Sand Case |
| title_sort | comparison of machine learning algorithms for sand production prediction an example for a gas hydrate bearing sand case |
| topic | sand production prediction natural gas hydrates machine learning k-nearest neighbor support vector regression boosting tree |
| url | https://www.mdpi.com/1996-1073/15/18/6509 |
| work_keys_str_mv | AT jinzesong comparisonofmachinelearningalgorithmsforsandproductionpredictionanexampleforagashydratebearingsandcase AT yuhaoli comparisonofmachinelearningalgorithmsforsandproductionpredictionanexampleforagashydratebearingsandcase AT shuailiu comparisonofmachinelearningalgorithmsforsandproductionpredictionanexampleforagashydratebearingsandcase AT youmingxiong comparisonofmachinelearningalgorithmsforsandproductionpredictionanexampleforagashydratebearingsandcase AT weixinpang comparisonofmachinelearningalgorithmsforsandproductionpredictionanexampleforagashydratebearingsandcase AT yufahe comparisonofmachinelearningalgorithmsforsandproductionpredictionanexampleforagashydratebearingsandcase AT yaximu comparisonofmachinelearningalgorithmsforsandproductionpredictionanexampleforagashydratebearingsandcase |