Weiyuan shale gas play is characterized by thin high-quality reservoir thickness,big horizontal stress difference,and big productivity differences between wells.Based on integrated evaluation of shale gas reservoir ge...Weiyuan shale gas play is characterized by thin high-quality reservoir thickness,big horizontal stress difference,and big productivity differences between wells.Based on integrated evaluation of shale gas reservoir geology and well logging interpretation of more than 20 appraisal wells,a correlation was built between the single well test production rate and the high-quality reservoir length drilled in the horizontal wells,high-quality reservoir thickness and the stimulation treatment parameters in over 100 horizontal wells,the dominating factors on horizontal well productivity were found out,and optimized development strategies were proposed.The results show that the deployed reserves of high-quality reservoir are the dominating factors on horizontal well productivity.In other words,the shale gas well productivity is controlled by the thickness of the high-quality reservoir,the high-quality reservoir drilling length and the effectiveness of stimulation.Based on the above understanding,the development strategies in Weiyuan shale gas play are optimized as follows:(1)The target of horizontal wells is located in the middle and lower parts of Longyi 11(Wei202 area)and Longyi 11(Wei204 area).(2)Producing wells are drilled in priority in the surrounding areas of Weiyuan county with thick high-quality reservoir.(3)A medium to high intensity stimulation is adopted.After the implementation of these strategies,both the production rate and the estimated ultimate recovery(EUR)of individual shale gas wells have increased substantially.展开更多
Accurate prediction of drilling efficiency is critical for developing the earth-rock excavation schedule.The single machine learning(ML)prediction models usually suffer from problems including parameter sensitivity an...Accurate prediction of drilling efficiency is critical for developing the earth-rock excavation schedule.The single machine learning(ML)prediction models usually suffer from problems including parameter sensitivity and overfitting.In addition,the influence of environmental and operational factors is often ignored.In response,a novel stacking-based ensemble learning method taking into account the combined effects of those factors is proposed.Through multiple comparison tests,four models,e Xtreme gradient boosting(XGBoost),random forest(RF),back propagation neural network(BPNN)as the base learners,and support vector regression(SVR)as the meta-learner,are selected for stacking.Furthermore,an improved cuckoo search optimization(ICSO)algorithm is developed for hyper-parameter optimization of the ensemble model.The application to a real-world project demonstrates that the proposed method outperforms the popular single ML method XGBoost and the ensemble model optimized by particle swarm optimization(PSO),with 16.43%and 4.88%improvements of mean absolute percentage error(MAPE),respectively.展开更多
文摘Weiyuan shale gas play is characterized by thin high-quality reservoir thickness,big horizontal stress difference,and big productivity differences between wells.Based on integrated evaluation of shale gas reservoir geology and well logging interpretation of more than 20 appraisal wells,a correlation was built between the single well test production rate and the high-quality reservoir length drilled in the horizontal wells,high-quality reservoir thickness and the stimulation treatment parameters in over 100 horizontal wells,the dominating factors on horizontal well productivity were found out,and optimized development strategies were proposed.The results show that the deployed reserves of high-quality reservoir are the dominating factors on horizontal well productivity.In other words,the shale gas well productivity is controlled by the thickness of the high-quality reservoir,the high-quality reservoir drilling length and the effectiveness of stimulation.Based on the above understanding,the development strategies in Weiyuan shale gas play are optimized as follows:(1)The target of horizontal wells is located in the middle and lower parts of Longyi 11(Wei202 area)and Longyi 11(Wei204 area).(2)Producing wells are drilled in priority in the surrounding areas of Weiyuan county with thick high-quality reservoir.(3)A medium to high intensity stimulation is adopted.After the implementation of these strategies,both the production rate and the estimated ultimate recovery(EUR)of individual shale gas wells have increased substantially.
基金supported by the Yalong River Joint Funds of the National Natural Science Foundation of China(No.U1965207)the National Natural Science Foundation of China(Nos.51839007,51779169,and 52009090)。
文摘Accurate prediction of drilling efficiency is critical for developing the earth-rock excavation schedule.The single machine learning(ML)prediction models usually suffer from problems including parameter sensitivity and overfitting.In addition,the influence of environmental and operational factors is often ignored.In response,a novel stacking-based ensemble learning method taking into account the combined effects of those factors is proposed.Through multiple comparison tests,four models,e Xtreme gradient boosting(XGBoost),random forest(RF),back propagation neural network(BPNN)as the base learners,and support vector regression(SVR)as the meta-learner,are selected for stacking.Furthermore,an improved cuckoo search optimization(ICSO)algorithm is developed for hyper-parameter optimization of the ensemble model.The application to a real-world project demonstrates that the proposed method outperforms the popular single ML method XGBoost and the ensemble model optimized by particle swarm optimization(PSO),with 16.43%and 4.88%improvements of mean absolute percentage error(MAPE),respectively.
