To assess whether a development strategy will be profitable enough,production forecasting is a crucial and difficult step in the process.The development history of other reservoirs in the same class tends to be studie...To assess whether a development strategy will be profitable enough,production forecasting is a crucial and difficult step in the process.The development history of other reservoirs in the same class tends to be studied to make predictions accurate.However,the permeability field,well patterns,and development regime must all be similar for two reservoirs to be considered in the same class.This results in very few available experiences from other reservoirs even though there is a lot of historical information on numerous reservoirs because it is difficult to find such similar reservoirs.This paper proposes a learn-to-learn method,which can better utilize a vast amount of historical data from various reservoirs.Intuitively,the proposed method first learns how to learn samples before directly learning rules in samples.Technically,by utilizing gradients from networks with independent parameters and copied structure in each class of reservoirs,the proposed network obtains the optimal shared initial parameters which are regarded as transferable information across different classes.Based on that,the network is able to predict future production indices for the target reservoir by only training with very limited samples collected from reservoirs in the same class.Two cases further demonstrate its superiority in accuracy to other widely-used network methods.展开更多
Two different evaporitic sequences occurred in the latest Cretaceous-Early Paleocene in Yarkand Basin,southwestern Tarim Basin,Xinjiang Province,China:one is characterized by poor gypsum and some small,lenticularshape...Two different evaporitic sequences occurred in the latest Cretaceous-Early Paleocene in Yarkand Basin,southwestern Tarim Basin,Xinjiang Province,China:one is characterized by poor gypsum and some small,lenticularshaped halite layers in the Tuyiluoke Formation of the latest Cretaceous,the other is characterized by very thick gypsum and halite layers in the Aertashen Formation of the early Paleocene.In the early developmental stage of the Tuyiluoke Formation,the Yarkand ancient saline lake was a long,strip-shaped depression,NW-SE oriented,along the West Kunlun piedmont,with its eastern boundary to the line along bores Ys1-T1-Ks101,the concentrated center located in the area of borehole S1.In the later developmental stage,the depositional scope was shifted inch by inch to the NW of this saline lake,forming a triangular depositional area,with apices at boreholes Wx1,Ak2 and S1,the concentrated center of the saline lake gradually migrating from borehole S1 region to the northwestern area of the lake,developing four small,evaporatedconcentrated sub-depressions,depositing lenticular-shaped halite.In the early Paleocene,the ancient saline lake was stretched from the West Kunlun piedmont in the west,to the Markit slope in the east,from the South Tianshan piedmont in the north,to the Hotan area in the south,accompanied by giant thicknesses of halite and large-scale gypsum layers,mainly interbedded with limestone in the Aertashen Formation.The evaporites in the latest Cretaceous-early Paleocene were controlled by the marine transgression-regression geological background in the Yarkand Basin.Generally,integrated evaporitic depositional sequences,such as clasolite-gypsum-halite-potash,usually occur in the presence of persistent seawater through evaporation,but this is not the case in the Tuyiluoke Formation.In contrast,very thick gypsum layers are common in the early Paleocene.Typically,adequate mineral sources for evaporites are found within seawater,such as in large basins undergoing long-term marine transgression-regression cycles,where adequate seawater remains,even though the basin was going through a marine regression stage.In the latest Cretaceous,thin gypsum layers indicate a lack of mineral sources.In contrast,the early Paleocene has far larger evaporites,both in width and thickness.This suggests a short-term marine regression stage must have occurred during the spatiotemporal evolution of the evaporites in the latest Cretaceous-Early Paleocene in the basin,meaning that a rapid marine regressive episode has been identified at the end of the Cretaceous.展开更多
The study on Lower Cambrian dolostones in Tarim Basin can improve our understanding of ancient and deeply buried carbonate reservoirs.In this research,diagenetic fluid characteristics and their control on porosity evo...The study on Lower Cambrian dolostones in Tarim Basin can improve our understanding of ancient and deeply buried carbonate reservoirs.In this research,diagenetic fluid characteristics and their control on porosity evolution have been revealed by studying the petrography and in situ geochemistry of different dolomites.Three types of diagenetic fluids were identified:(1) Replacive dolomites were deviated from shallow burial dolomitizing fluids,which might probably be concentrated ancient seawater at early stage.(2) Fine-to-medium crystalline,planar-e diamond pore-filling dolomites(Fd1) were likely slowly and sufficiently crystallized from deep-circulating crustal hydrothermal fluids during Devonian.(3) Coarse crystalline,non-planar-a saddle pore-filling dolomites(Fd2) might rapidly and insufficiently crystallize from magmatic hydrothermal fluids during Permian.Early dolomitizing fluids did not increase the porosity,but transformed the primary pores to dissolution pores through dolomitization.Deep-circulating crustal hydrothermal fluids significantly increased porosity in the early stages by dissolving and then slightly decreased the porosity in the late stage due to Fd1 precipitation.Magmatic hydrothermal fluids only precipitated the Fd2 dolomites and slightly decreased the porosity.In summary,Devonian deep-circulating crustal hydrothermal fluids dominated the porosity evolution of the Lower Cambrian dolostone reservoir in the Tarim Basin.展开更多
基金This work is supported by the National Natural Science Foundation of China under Grant 52274057,52074340 and 51874335the Major Scientific and Technological Projects of CNPC under Grant ZD2019-183-008+2 种基金the Major Scientific and Technological Projects of CNOOC under Grant CCL2022RCPS0397RSNthe Science and Technology Support Plan for Youth Innovation of University in Shandong Province under Grant 2019KJH002111 Project under Grant B08028.
文摘To assess whether a development strategy will be profitable enough,production forecasting is a crucial and difficult step in the process.The development history of other reservoirs in the same class tends to be studied to make predictions accurate.However,the permeability field,well patterns,and development regime must all be similar for two reservoirs to be considered in the same class.This results in very few available experiences from other reservoirs even though there is a lot of historical information on numerous reservoirs because it is difficult to find such similar reservoirs.This paper proposes a learn-to-learn method,which can better utilize a vast amount of historical data from various reservoirs.Intuitively,the proposed method first learns how to learn samples before directly learning rules in samples.Technically,by utilizing gradients from networks with independent parameters and copied structure in each class of reservoirs,the proposed network obtains the optimal shared initial parameters which are regarded as transferable information across different classes.Based on that,the network is able to predict future production indices for the target reservoir by only training with very limited samples collected from reservoirs in the same class.Two cases further demonstrate its superiority in accuracy to other widely-used network methods.
基金supported by the National Natural Science Foundation of China(No.41972082)the Scientific and Technical Supporting Project during the National Twelfth Five-Year Plan Period(No.2011BAB06B06)。
文摘Two different evaporitic sequences occurred in the latest Cretaceous-Early Paleocene in Yarkand Basin,southwestern Tarim Basin,Xinjiang Province,China:one is characterized by poor gypsum and some small,lenticularshaped halite layers in the Tuyiluoke Formation of the latest Cretaceous,the other is characterized by very thick gypsum and halite layers in the Aertashen Formation of the early Paleocene.In the early developmental stage of the Tuyiluoke Formation,the Yarkand ancient saline lake was a long,strip-shaped depression,NW-SE oriented,along the West Kunlun piedmont,with its eastern boundary to the line along bores Ys1-T1-Ks101,the concentrated center located in the area of borehole S1.In the later developmental stage,the depositional scope was shifted inch by inch to the NW of this saline lake,forming a triangular depositional area,with apices at boreholes Wx1,Ak2 and S1,the concentrated center of the saline lake gradually migrating from borehole S1 region to the northwestern area of the lake,developing four small,evaporatedconcentrated sub-depressions,depositing lenticular-shaped halite.In the early Paleocene,the ancient saline lake was stretched from the West Kunlun piedmont in the west,to the Markit slope in the east,from the South Tianshan piedmont in the north,to the Hotan area in the south,accompanied by giant thicknesses of halite and large-scale gypsum layers,mainly interbedded with limestone in the Aertashen Formation.The evaporites in the latest Cretaceous-early Paleocene were controlled by the marine transgression-regression geological background in the Yarkand Basin.Generally,integrated evaporitic depositional sequences,such as clasolite-gypsum-halite-potash,usually occur in the presence of persistent seawater through evaporation,but this is not the case in the Tuyiluoke Formation.In contrast,very thick gypsum layers are common in the early Paleocene.Typically,adequate mineral sources for evaporites are found within seawater,such as in large basins undergoing long-term marine transgression-regression cycles,where adequate seawater remains,even though the basin was going through a marine regression stage.In the latest Cretaceous,thin gypsum layers indicate a lack of mineral sources.In contrast,the early Paleocene has far larger evaporites,both in width and thickness.This suggests a short-term marine regression stage must have occurred during the spatiotemporal evolution of the evaporites in the latest Cretaceous-Early Paleocene in the basin,meaning that a rapid marine regressive episode has been identified at the end of the Cretaceous.
基金funded by the National Basic Research Program of China (Grant 2012CB214801)Tarim Oilfield Branch of Petro China (Grant 041013100042)。
文摘The study on Lower Cambrian dolostones in Tarim Basin can improve our understanding of ancient and deeply buried carbonate reservoirs.In this research,diagenetic fluid characteristics and their control on porosity evolution have been revealed by studying the petrography and in situ geochemistry of different dolomites.Three types of diagenetic fluids were identified:(1) Replacive dolomites were deviated from shallow burial dolomitizing fluids,which might probably be concentrated ancient seawater at early stage.(2) Fine-to-medium crystalline,planar-e diamond pore-filling dolomites(Fd1) were likely slowly and sufficiently crystallized from deep-circulating crustal hydrothermal fluids during Devonian.(3) Coarse crystalline,non-planar-a saddle pore-filling dolomites(Fd2) might rapidly and insufficiently crystallize from magmatic hydrothermal fluids during Permian.Early dolomitizing fluids did not increase the porosity,but transformed the primary pores to dissolution pores through dolomitization.Deep-circulating crustal hydrothermal fluids significantly increased porosity in the early stages by dissolving and then slightly decreased the porosity in the late stage due to Fd1 precipitation.Magmatic hydrothermal fluids only precipitated the Fd2 dolomites and slightly decreased the porosity.In summary,Devonian deep-circulating crustal hydrothermal fluids dominated the porosity evolution of the Lower Cambrian dolostone reservoir in the Tarim Basin.