An automatic well test interpretation method for radial composite reservoirs based on convolutional neural network(CNN) is proposed, and its effectiveness and accuracy are verified by actual field data. In this paper,...An automatic well test interpretation method for radial composite reservoirs based on convolutional neural network(CNN) is proposed, and its effectiveness and accuracy are verified by actual field data. In this paper, based on the data transformed by logarithm function and the loss function of mean square error(MSE), the optimal CNN is obtained by reducing the loss function to optimize the network with "dropout" method to avoid over fitting. The trained optimal network can be directly used to interpret the buildup or drawdown pressure data of the well in the radial composite reservoir, that is, the log-log plot of the given measured pressure variation and its derivative data are input into the network, the outputs are corresponding reservoir parameters(mobility ratio, storativity ratio, dimensionless composite radius, and dimensionless group characterizing well storage and skin effects), which realizes the automatic initial fitting of well test interpretation parameters. The method is verified with field measured data of Daqing Oilfield. The research shows that the method has high interpretation accuracy, and it is superior to the analytical method and the least square method.展开更多
Parameter inversions in oil/gas reservoirs based on well test interpretations are of great significance in oil/gas industry.Automatic well test interpretations based on artificial intelligence are the most promising t...Parameter inversions in oil/gas reservoirs based on well test interpretations are of great significance in oil/gas industry.Automatic well test interpretations based on artificial intelligence are the most promising to solve the problem of non-unique solution.In this work,a new deep reinforcement learning(DRL)based approach is proposed for automatic curve matching for well test interpretation,by using the double deep Q-network(DDQN).The DDQN algorithms are applied to train agents for automatic parameter tuning in three conventional well-testing models.In addition,to alleviate the dimensional disaster problem of parameter space,an asynchronous parameter adjustment strategy is used to train the agent.Finally,field applications are carried out by using the new DRL approaches.Results show that step number required for the DDQN to complete the curve matching is the least among,when comparing the naive deep Q-network(naive DQN)and deep Q-network(DQN).We also show that DDQN can improve the robustness of curve matching in comparison with supervised machine learning algorithms.Using DDQN algorithm to perform 100 curve matching tests on three traditional well test models,the results show that the mean relative error of the parameters is 7.58%for the homogeneous model,10.66%for the radial composite model,and 12.79%for the dual porosity model.In the actual field application,it is found that a good curve fitting can be obtained with only 30 steps of parameter adjustment.展开更多
The Lower Cambrian Longwangmiao Fm gas reservoir in the GaoshitieMoxi area,the Sichuan Basin,is a super giant monoblock marine carbonate gas reservoir with its single size being the largest in China.The key to the rea...The Lower Cambrian Longwangmiao Fm gas reservoir in the GaoshitieMoxi area,the Sichuan Basin,is a super giant monoblock marine carbonate gas reservoir with its single size being the largest in China.The key to the realization of high and stable production gas wells in this gas reservoir is to identify accurately high-permeability zones where there are dissolved pores or dissolved pores are superimposed with fractures.However,high quality dolomite reservoirs are characterized by large burial depth and strong heterogeneity,so reservoir prediction is of difficult.In this paper,related seismic researches were carried out and supporting technologies were developed as follows.First,a geologic model was built after an analysis of the existing data and forward modeling was carried out to establish a reservoir seismic response model.Second,by virtue of well-oriented amplitude processing technology,spherical diffusion compensation factor was obtained based on VSP well logging data and the true amplitude of seismic data was recovered.Third,the resolution of deep seismic data was improved by using the welloriented high-resolution frequency-expanding technology and prestack time migration data of high quality was acquired.And fourth,multiple shoal facies reservoirs were traced by using the global automatic seismic interpretation technology which is based on stratigraphic model,multiple reservoirs which are laterally continuous and vertically superimposed could be predicted,and the areal distribution of high quality reservoirs could be described accurately and efficiently.By virtue of the supporting technologies,drilling trajectory is positioned accurately,and the deployed development wells all have high yield.These technologies also promote the construction of a modern supergiant gas field of tens of billions of cubic meters.展开更多
This paper reviewed the developments of the last ten years in the field of international high-resolution earth observation, and introduced the developmental status and plans for China's high-resolution earth obser...This paper reviewed the developments of the last ten years in the field of international high-resolution earth observation, and introduced the developmental status and plans for China's high-resolution earth observation program. In addition, this paper expounded the transformation mechanism and procedure from earth observation data to geospatial information and geographical knowledge, and examined the key scientific and technological issues, including earth observation networks, high-precision image positioning, image understanding, automatic spatial information extraction, and focus services. These analyses provide a new impetus for pushing the application of China's high-resolution earth observation system from a "quantity" to "quality" change, from China to the world, from providing products to providing online service.展开更多
A robust deep learning model consisting of long short-term memory and fully connected neural net-works has been proposed to automatically interpret homogeneous petroleum reservoirs having infinite,no flow,and constant...A robust deep learning model consisting of long short-term memory and fully connected neural net-works has been proposed to automatically interpret homogeneous petroleum reservoirs having infinite,no flow,and constant pressure outer boundary conditions.The pressure change data recorded during the well test operation along with its derivative is input into the model to perform the classification for identifying the reservoir model and,further,regression to estimate output parameter.Gaussian noise was added to analytical models while generating the synthetic training data.The hyperparameters were regulated to perform model optimization,resulting in a batch size of 64,Adam optimization algorithm,learning rate of 0.01,and 80:10:10 data split ratio as the best choices of hyperparameters.The perfor-mance accuracy also increased with an increase in the number of samples during training.Suitable classification and regression metrics have been used to evaluate the performance of the models.The paper also demonstrates the prediction performance of the optimized model using simulated and actual oil well pressure drawdown test cases.The proposed model achieved minimum and maximum relative errors of 0.0019 and 0.0308,respectively,in estimating output for the simulated test cases and relative error of 0.0319 for the real test case.展开更多
基金Supported by the National Science and Technology Major Project(2017ZX05009005-002)
文摘An automatic well test interpretation method for radial composite reservoirs based on convolutional neural network(CNN) is proposed, and its effectiveness and accuracy are verified by actual field data. In this paper, based on the data transformed by logarithm function and the loss function of mean square error(MSE), the optimal CNN is obtained by reducing the loss function to optimize the network with "dropout" method to avoid over fitting. The trained optimal network can be directly used to interpret the buildup or drawdown pressure data of the well in the radial composite reservoir, that is, the log-log plot of the given measured pressure variation and its derivative data are input into the network, the outputs are corresponding reservoir parameters(mobility ratio, storativity ratio, dimensionless composite radius, and dimensionless group characterizing well storage and skin effects), which realizes the automatic initial fitting of well test interpretation parameters. The method is verified with field measured data of Daqing Oilfield. The research shows that the method has high interpretation accuracy, and it is superior to the analytical method and the least square method.
基金funding support from National Natural Science Foundation of China(52074322)Beijing Natural Science Foundation(3204052)+1 种基金Science Foundation of China University of Petroleum,Beijing(No.2462018YJRC032)National Major Project of China(2017ZX05030002-005)。
文摘Parameter inversions in oil/gas reservoirs based on well test interpretations are of great significance in oil/gas industry.Automatic well test interpretations based on artificial intelligence are the most promising to solve the problem of non-unique solution.In this work,a new deep reinforcement learning(DRL)based approach is proposed for automatic curve matching for well test interpretation,by using the double deep Q-network(DDQN).The DDQN algorithms are applied to train agents for automatic parameter tuning in three conventional well-testing models.In addition,to alleviate the dimensional disaster problem of parameter space,an asynchronous parameter adjustment strategy is used to train the agent.Finally,field applications are carried out by using the new DRL approaches.Results show that step number required for the DDQN to complete the curve matching is the least among,when comparing the naive deep Q-network(naive DQN)and deep Q-network(DQN).We also show that DDQN can improve the robustness of curve matching in comparison with supervised machine learning algorithms.Using DDQN algorithm to perform 100 curve matching tests on three traditional well test models,the results show that the mean relative error of the parameters is 7.58%for the homogeneous model,10.66%for the radial composite model,and 12.79%for the dual porosity model.In the actual field application,it is found that a good curve fitting can be obtained with only 30 steps of parameter adjustment.
文摘The Lower Cambrian Longwangmiao Fm gas reservoir in the GaoshitieMoxi area,the Sichuan Basin,is a super giant monoblock marine carbonate gas reservoir with its single size being the largest in China.The key to the realization of high and stable production gas wells in this gas reservoir is to identify accurately high-permeability zones where there are dissolved pores or dissolved pores are superimposed with fractures.However,high quality dolomite reservoirs are characterized by large burial depth and strong heterogeneity,so reservoir prediction is of difficult.In this paper,related seismic researches were carried out and supporting technologies were developed as follows.First,a geologic model was built after an analysis of the existing data and forward modeling was carried out to establish a reservoir seismic response model.Second,by virtue of well-oriented amplitude processing technology,spherical diffusion compensation factor was obtained based on VSP well logging data and the true amplitude of seismic data was recovered.Third,the resolution of deep seismic data was improved by using the welloriented high-resolution frequency-expanding technology and prestack time migration data of high quality was acquired.And fourth,multiple shoal facies reservoirs were traced by using the global automatic seismic interpretation technology which is based on stratigraphic model,multiple reservoirs which are laterally continuous and vertically superimposed could be predicted,and the areal distribution of high quality reservoirs could be described accurately and efficiently.By virtue of the supporting technologies,drilling trajectory is positioned accurately,and the deployed development wells all have high yield.These technologies also promote the construction of a modern supergiant gas field of tens of billions of cubic meters.
基金supported by National Basic Research Program of China(Grant No. 2012CB719906)
文摘This paper reviewed the developments of the last ten years in the field of international high-resolution earth observation, and introduced the developmental status and plans for China's high-resolution earth observation program. In addition, this paper expounded the transformation mechanism and procedure from earth observation data to geospatial information and geographical knowledge, and examined the key scientific and technological issues, including earth observation networks, high-precision image positioning, image understanding, automatic spatial information extraction, and focus services. These analyses provide a new impetus for pushing the application of China's high-resolution earth observation system from a "quantity" to "quality" change, from China to the world, from providing products to providing online service.
基金the Oil Industry Development Board,Ministry of Petroleum&Natural Gas,Government of India[Grant Number:4/3/2020-OIDB]and DIT University[Grant Num-ber:DITU/R&D/2021/4/Department of Petroleum and Energy Studies].
文摘A robust deep learning model consisting of long short-term memory and fully connected neural net-works has been proposed to automatically interpret homogeneous petroleum reservoirs having infinite,no flow,and constant pressure outer boundary conditions.The pressure change data recorded during the well test operation along with its derivative is input into the model to perform the classification for identifying the reservoir model and,further,regression to estimate output parameter.Gaussian noise was added to analytical models while generating the synthetic training data.The hyperparameters were regulated to perform model optimization,resulting in a batch size of 64,Adam optimization algorithm,learning rate of 0.01,and 80:10:10 data split ratio as the best choices of hyperparameters.The perfor-mance accuracy also increased with an increase in the number of samples during training.Suitable classification and regression metrics have been used to evaluate the performance of the models.The paper also demonstrates the prediction performance of the optimized model using simulated and actual oil well pressure drawdown test cases.The proposed model achieved minimum and maximum relative errors of 0.0019 and 0.0308,respectively,in estimating output for the simulated test cases and relative error of 0.0319 for the real test case.
