The prediction of magnitude （M） of reservoir induced earthquake is an important task in earthquake engineering. In this article, we employ a Support Vector Machine （SVM） and Gaussian Process Regression （GPR） for...The prediction of magnitude （M） of reservoir induced earthquake is an important task in earthquake engineering. In this article, we employ a Support Vector Machine （SVM） and Gaussian Process Regression （GPR） for prediction of reservoir induced earthquake M based on reservoir parameters. Comprehensive parameter （E） and maximum reservoir depth] （H） are considered as inputs to the SVM and GPR. We give an equation for determination oil reservoir induced earthquake M. The developed SVM and GPR have been compared with] the Artificial Neural Network （ANN） method. The results show that the developed SVM and] GPR are efficient tools for prediction of reservoir induced earthquake M. /展开更多
It is a great challenge to match and predict the production performance of coalbed methane (CBM) wells in the initial production stage due to heterogeneity of coalbed, uniqueness of CBM production process, complexity ...It is a great challenge to match and predict the production performance of coalbed methane (CBM) wells in the initial production stage due to heterogeneity of coalbed, uniqueness of CBM production process, complexity of porosity-permeability variation and difficulty in obtaining some key parameters which are critical for the conventional prediction methods (type curve, material balance and numerical simulation). BP neural network, a new intelligent technique, is an effective method to deal with nonlinear, instable and complex system problems and predict the short-term change quantitatively. In this paper a BP neural model for the CBM productivity of high-rank CBM wells in Qinshui Basin was established and used to match the past gas production and predict the futural production performance. The results from two case studies showed that this model has high accuracy and good reliability in matching and predicting gas production with different types and different temporal resolutions, and the accuracy increases as the number of outliers in gas production data decreases. Therefore, the BP network can provide a reliable tool to predict the production performance of CBM wells without clear knowledge of coalbed reservoir and sufficient production data in the early development stage.展开更多
文摘The prediction of magnitude （M） of reservoir induced earthquake is an important task in earthquake engineering. In this article, we employ a Support Vector Machine （SVM） and Gaussian Process Regression （GPR） for prediction of reservoir induced earthquake M based on reservoir parameters. Comprehensive parameter （E） and maximum reservoir depth] （H） are considered as inputs to the SVM and GPR. We give an equation for determination oil reservoir induced earthquake M. The developed SVM and GPR have been compared with] the Artificial Neural Network （ANN） method. The results show that the developed SVM and] GPR are efficient tools for prediction of reservoir induced earthquake M. /
基金supported by the National Basic Research Program of Chi-na ("973" Project ) (Grant No. 2009CB219600)the Major National Sci-ence and Technology Special Projects (Grant Nos. 2008ZX05034-001, 2009ZX05038-002)
文摘It is a great challenge to match and predict the production performance of coalbed methane (CBM) wells in the initial production stage due to heterogeneity of coalbed, uniqueness of CBM production process, complexity of porosity-permeability variation and difficulty in obtaining some key parameters which are critical for the conventional prediction methods (type curve, material balance and numerical simulation). BP neural network, a new intelligent technique, is an effective method to deal with nonlinear, instable and complex system problems and predict the short-term change quantitatively. In this paper a BP neural model for the CBM productivity of high-rank CBM wells in Qinshui Basin was established and used to match the past gas production and predict the futural production performance. The results from two case studies showed that this model has high accuracy and good reliability in matching and predicting gas production with different types and different temporal resolutions, and the accuracy increases as the number of outliers in gas production data decreases. Therefore, the BP network can provide a reliable tool to predict the production performance of CBM wells without clear knowledge of coalbed reservoir and sufficient production data in the early development stage.
