In common practice in the oil fields,the injection of water and gas into reservoirs is a crucial technique to increase production.The control of the waterflooding front in oil/gas exploitation is a matter of great con...In common practice in the oil fields,the injection of water and gas into reservoirs is a crucial technique to increase production.The control of the waterflooding front in oil/gas exploitation is a matter of great concern to reservoir engineers.Monitoring the waterflooding front in oil/gas wells plays a very important role in adjusting the well network and later in production,taking advantage of the remaining oil po-tential and ultimately achieving great success in improving the recovery rate.For a long time,micro-seismic monitoring,numerical simulation,four-dimensional seismic and other methods have been widely used in waterflooding front monitoring.However,reconciling their reliability and cost poses a significant challenge.In order to achieve real-time,reliable and cost-effective monitoring,we propose an innovative method for waterflooding front monitoring through the similarity analysis of passive source time-lapse seismic images.Typically,passive source seismic data collected from oil fields have extremely low signal-to-noise ratio(SNR),which poses a serious problem for obtaining structural images.The proposed method aims to visualize and analyze underground changes by highlighting time-lapse images and provide a strategy for underground monitoring using long-term passive source data under low SNR conditions.First,we verify the feasibility of the proposed method by designing a theoretical model.Then,we conduct an analysis of the correlation coefficient(similarity)on the passive source time-lapse seismic imaging results to enhance the image differences and identify the simulated waterflooding fronts.Finally,the proposed method is applied to the actual waterflooding front monitoring tasks in Shengli Oilfield,China.The research findings indicate that the monitoring results are consistent with the actual devel-opment conditions,which in turn demonstrates that the proposed method has great potential for practical application and is very suitable for monitoring common development tasks in oil fields.展开更多
Passive source imaging can reconstruct body wave reflections similar to those of active sources through seismic interferometry(SI).It has become a low-cost,environmentally friendly alternative to active source seismic...Passive source imaging can reconstruct body wave reflections similar to those of active sources through seismic interferometry(SI).It has become a low-cost,environmentally friendly alternative to active source seismic,showing great potential.However,this method faces many challenges in practical applications,including uneven distribution of underground sources and complex survey environments.These situations seriously affect the reconstruction quality of virtual shot records,resulting in unguaranteed imaging results and greatly limiting passive source seismic exploration applications.In addition,the quality of the reconstructed records is directly related to the time length of the noise records,but in practice it is often difficult to obtain long-term,high-quality noise segments containing body wave events.To solve the above problems,we propose a deep learning method for reconstructing passive source virtual shot records and apply it to passive source time-lapse monitoring.This method combines the UNet network and the BiLSTM(Bidirectional Long Short-Term Memory)network for extracting spatial features and temporal features respectively.It introduces the spatial attention mechanism to establish a hybrid SUNet-BiLSTM-Attention(SBA)network for supervised training.Through pre-training and fine-tuning training,the network can accurately reconstruct passive source virtual shot records directly from short-time noisy segments containing body wave events.The experimental results of theoretical data show that the virtual shot records reconstructed by the network have high resolution and signal to noise ratio(SNR),providing high-quality data for subsequent monitoring and imaging.Finally,to further validate the effectiveness of proposed method,we applied it to field data collected from gas storage in northwest China.The reconstruction results of field data effectively improve the quality of virtual records and obtain more reliable time-lapse imaging monitoring results,which have significant practical value.展开更多
基金supported by the CNPC-SWPU Innovation Alliance Technology Cooperation Project(2020CX020000)the National Natural Science Foundation of China(42022028)+1 种基金the Natural Science Foundation of Sichuan Province(24NSFSC0808)the China Scholarship Council(202306440144)。
文摘In common practice in the oil fields,the injection of water and gas into reservoirs is a crucial technique to increase production.The control of the waterflooding front in oil/gas exploitation is a matter of great concern to reservoir engineers.Monitoring the waterflooding front in oil/gas wells plays a very important role in adjusting the well network and later in production,taking advantage of the remaining oil po-tential and ultimately achieving great success in improving the recovery rate.For a long time,micro-seismic monitoring,numerical simulation,four-dimensional seismic and other methods have been widely used in waterflooding front monitoring.However,reconciling their reliability and cost poses a significant challenge.In order to achieve real-time,reliable and cost-effective monitoring,we propose an innovative method for waterflooding front monitoring through the similarity analysis of passive source time-lapse seismic images.Typically,passive source seismic data collected from oil fields have extremely low signal-to-noise ratio(SNR),which poses a serious problem for obtaining structural images.The proposed method aims to visualize and analyze underground changes by highlighting time-lapse images and provide a strategy for underground monitoring using long-term passive source data under low SNR conditions.First,we verify the feasibility of the proposed method by designing a theoretical model.Then,we conduct an analysis of the correlation coefficient(similarity)on the passive source time-lapse seismic imaging results to enhance the image differences and identify the simulated waterflooding fronts.Finally,the proposed method is applied to the actual waterflooding front monitoring tasks in Shengli Oilfield,China.The research findings indicate that the monitoring results are consistent with the actual devel-opment conditions,which in turn demonstrates that the proposed method has great potential for practical application and is very suitable for monitoring common development tasks in oil fields.
基金supported by the CNPC-SWPU Innovation Alliance Technology Cooperation Project(2020CX020000)the Natural Science Foundation of Sichuan Province(24NSFSC0808)the China Scholarship Council(202306440144).
文摘Passive source imaging can reconstruct body wave reflections similar to those of active sources through seismic interferometry(SI).It has become a low-cost,environmentally friendly alternative to active source seismic,showing great potential.However,this method faces many challenges in practical applications,including uneven distribution of underground sources and complex survey environments.These situations seriously affect the reconstruction quality of virtual shot records,resulting in unguaranteed imaging results and greatly limiting passive source seismic exploration applications.In addition,the quality of the reconstructed records is directly related to the time length of the noise records,but in practice it is often difficult to obtain long-term,high-quality noise segments containing body wave events.To solve the above problems,we propose a deep learning method for reconstructing passive source virtual shot records and apply it to passive source time-lapse monitoring.This method combines the UNet network and the BiLSTM(Bidirectional Long Short-Term Memory)network for extracting spatial features and temporal features respectively.It introduces the spatial attention mechanism to establish a hybrid SUNet-BiLSTM-Attention(SBA)network for supervised training.Through pre-training and fine-tuning training,the network can accurately reconstruct passive source virtual shot records directly from short-time noisy segments containing body wave events.The experimental results of theoretical data show that the virtual shot records reconstructed by the network have high resolution and signal to noise ratio(SNR),providing high-quality data for subsequent monitoring and imaging.Finally,to further validate the effectiveness of proposed method,we applied it to field data collected from gas storage in northwest China.The reconstruction results of field data effectively improve the quality of virtual records and obtain more reliable time-lapse imaging monitoring results,which have significant practical value.
