Seismic fault identification is a critical step in structural interpretation,reservoir characterization,and well-drilling planning.However,fault identification in deep fault-karst carbonate formations is particularly ...Seismic fault identification is a critical step in structural interpretation,reservoir characterization,and well-drilling planning.However,fault identification in deep fault-karst carbonate formations is particularly challenging due to their deep burial depth and the complex effects of dissolution.Traditional manual interpretation methods are often labor intensive and prone to high uncertainty due to their subjective nature.To address these limitations,this study proposes a transfer learningebased strategy for fault identification in deep fault-karst carbonate formations.The proposed methodology began with the generation of a large volume of synthetic seismic samples based on statistical fault distribution patterns observed in the study area.These synthetic samples were used to pretrain an improved U-Net network architecture,enhanced with an attention mechanism,to create a robust pretrained model.Subsequently,real-world fault labels were manually annotated based on verified fault interpretations and integrated into the training dataset.This combination of synthetic and real-world data was used to fine-tune the pretrained model,significantly improving its fault interpretation accuracy.The experimental results demonstrate that the integration of synthetic and real-world samples effectively enhances the quality of the training dataset.Furthermore,the proposed transfer learning strategy significantly im-proves fault recognition accuracy.By replacing the traditional weighted cross-entropy loss function with the Dice loss function,the model successfully addresses the issue of extreme class imbalance between positive and negative samples.Practical applications confirm that the proposed transfer learning strategy can accurately identify fault structures in deep fault-karst carbonate formations,providing a novel and effective technical approach for fault interpretation in such complex geological settings.展开更多
Based on comprehensive analysis of tectonic and fault evolution, core, well logging, seismic, drilling, and production data, the reservoir space characteristic, distribution, origin of fault-karst carbonate reservoir ...Based on comprehensive analysis of tectonic and fault evolution, core, well logging, seismic, drilling, and production data, the reservoir space characteristic, distribution, origin of fault-karst carbonate reservoir in Yueman block of South Tahe area, Halahatang oilfield, Tarim Basin, were studied systematically. And the regular pattern of hydrocarbon accumulation and enrichment was analyzed systematically based on development practice of the reservoirs. The results show that fault-karst carbonate reservoirs are distributed in the form of "body by body" discontinuously, heterogeneously and irregularly, which are controlled by the development of faults. Three formation models of fault-karst carbonate reservoirs, namely, the models controlled by the main deep-large fault, the secondary fault and the secondary internal fault, are built. The hydrocarbon accumulation and enrichment of fault-karst carbonate reservoirs is controlled by the spatiotemporal matching relation between hydrocarbon generation period and fault activity, and the size and segmentation of fault. The study results can effectively guide the well deployment and help the efficient development of fault-karst carbonate reservoirs of South Tahe area, Halahatang oilfield.展开更多
The Ordovician reservoirs in the Tahe oilfield are dominated by fractured-vuggy carbonate reservoirs, of which fault-karst reservoirs are a hot topic in recent years. Fault-karst reservoirs feature high production, la...The Ordovician reservoirs in the Tahe oilfield are dominated by fractured-vuggy carbonate reservoirs, of which fault-karst reservoirs are a hot topic in recent years. Fault-karst reservoirs feature high production, large burial depth, and strong heterogeneity under the control of faulting and karstification. Based on geological, logging, and seismic data, this study classified the Ordovician fault-karst reservoirs in the Yuejin block of the Tahe oilfield into three types, namely karst-cave, dissolved-vug, and fractured types, and established the integrated identification criteria of the three types of reservoirs. This study characterized karst caves, dissolved vugs, and multi-scale faults through seismic wave impedance inversion and frequency-domain detection of multi-scale faults. 3D geological models of different types of reservoirs were built using the combined deterministic and stochastic methods and characterized the spatial distribution of multi-scale faults, karst caves, dissolved vugs, and physical property parameters of reservoir. This study established the method for the geological modeling of fault-karst reservoirs, achieved the quantitative characterization and revealed the heterogeneity of fault-karst reservoirs. The karst-cave and dissolved-vug types are high in porosity and act as reservoirs, while the fractured type is high in permeability and act as flow pathway. This study lays the foundation for the development index prediction, well emplacement, and efficient development of the fault-karst carbonate reservoirs.展开更多
基金support provided by the China Postdoctoral Science Foundation(Grant No.2024M763650)the Excellent Young Scientists Fund Program of SINOPEC Petroleum Exploration and Production Research Institute(Grant No.yk2024010).
文摘Seismic fault identification is a critical step in structural interpretation,reservoir characterization,and well-drilling planning.However,fault identification in deep fault-karst carbonate formations is particularly challenging due to their deep burial depth and the complex effects of dissolution.Traditional manual interpretation methods are often labor intensive and prone to high uncertainty due to their subjective nature.To address these limitations,this study proposes a transfer learningebased strategy for fault identification in deep fault-karst carbonate formations.The proposed methodology began with the generation of a large volume of synthetic seismic samples based on statistical fault distribution patterns observed in the study area.These synthetic samples were used to pretrain an improved U-Net network architecture,enhanced with an attention mechanism,to create a robust pretrained model.Subsequently,real-world fault labels were manually annotated based on verified fault interpretations and integrated into the training dataset.This combination of synthetic and real-world data was used to fine-tune the pretrained model,significantly improving its fault interpretation accuracy.The experimental results demonstrate that the integration of synthetic and real-world samples effectively enhances the quality of the training dataset.Furthermore,the proposed transfer learning strategy significantly im-proves fault recognition accuracy.By replacing the traditional weighted cross-entropy loss function with the Dice loss function,the model successfully addresses the issue of extreme class imbalance between positive and negative samples.Practical applications confirm that the proposed transfer learning strategy can accurately identify fault structures in deep fault-karst carbonate formations,providing a novel and effective technical approach for fault interpretation in such complex geological settings.
基金Supported by the China National Sicence and Technology Project(2016ZX05004)
文摘Based on comprehensive analysis of tectonic and fault evolution, core, well logging, seismic, drilling, and production data, the reservoir space characteristic, distribution, origin of fault-karst carbonate reservoir in Yueman block of South Tahe area, Halahatang oilfield, Tarim Basin, were studied systematically. And the regular pattern of hydrocarbon accumulation and enrichment was analyzed systematically based on development practice of the reservoirs. The results show that fault-karst carbonate reservoirs are distributed in the form of "body by body" discontinuously, heterogeneously and irregularly, which are controlled by the development of faults. Three formation models of fault-karst carbonate reservoirs, namely, the models controlled by the main deep-large fault, the secondary fault and the secondary internal fault, are built. The hydrocarbon accumulation and enrichment of fault-karst carbonate reservoirs is controlled by the spatiotemporal matching relation between hydrocarbon generation period and fault activity, and the size and segmentation of fault. The study results can effectively guide the well deployment and help the efficient development of fault-karst carbonate reservoirs of South Tahe area, Halahatang oilfield.
基金supported by the Strategic Priority Research Program of the Chinese Academy of Sciences (XDA14010204).
文摘The Ordovician reservoirs in the Tahe oilfield are dominated by fractured-vuggy carbonate reservoirs, of which fault-karst reservoirs are a hot topic in recent years. Fault-karst reservoirs feature high production, large burial depth, and strong heterogeneity under the control of faulting and karstification. Based on geological, logging, and seismic data, this study classified the Ordovician fault-karst reservoirs in the Yuejin block of the Tahe oilfield into three types, namely karst-cave, dissolved-vug, and fractured types, and established the integrated identification criteria of the three types of reservoirs. This study characterized karst caves, dissolved vugs, and multi-scale faults through seismic wave impedance inversion and frequency-domain detection of multi-scale faults. 3D geological models of different types of reservoirs were built using the combined deterministic and stochastic methods and characterized the spatial distribution of multi-scale faults, karst caves, dissolved vugs, and physical property parameters of reservoir. This study established the method for the geological modeling of fault-karst reservoirs, achieved the quantitative characterization and revealed the heterogeneity of fault-karst reservoirs. The karst-cave and dissolved-vug types are high in porosity and act as reservoirs, while the fractured type is high in permeability and act as flow pathway. This study lays the foundation for the development index prediction, well emplacement, and efficient development of the fault-karst carbonate reservoirs.
