A 3D attention U-Net network and its application in geological model parameterization

To solve the problems of convolutional neural network–principal component analysis(CNN-PCA)in fine description and generalization of complex reservoir geological features,a 3D attention U-Net network was proposed not using a trained C3D video motion analysis model to extract the style of a 3D model,and applied to complement the details of geologic model lost in the dimension reduction of PCA method in this study.The 3D attention U-Net network was applied to a complex river channel sandstone reservoir to test its effects.The results show that compared with CNN-PCA method,the 3D attention U-Net network could better complement the details of geological model lost in the PCA dimension reduction,better reflect the fluid flow features in the original geologic model,and improve history matching results.

Wisdom and Geology, the North German Basin, and the Significance of Thrown Dices

For thousands of years, mankind is observing the surrounding nature. Often, they found no obvious clues for inexplicable and complex facts, leading to the belief that their wisdom was limited. This is in the majority of cases still true today, but based on hundreds of years of (geo-) scientific work some older thoughts can now be readjusted by combining newer geological, environmental, historical and philosophical clues. Facts about the development of the North German Basin are used to demonstrate the variability of geological systems and how these can be described by taking dice as a metaphor for ruling geological parameters. This includes all kinds of plate tectonically controlled basin forming processes, especially metamorphism of the lower crust due to a fixed mantle plume, basin filling processes with their galactic and lunar overprints, basin modifying tectonics due to internal (halokinesis, inversion) or external forces (one-sided loads at the surface due to mighty Delta sediments or glacial ice sheets) and geochemical reactions as a result of pressure and temperature changes in course of subsidence. Especially, the Rotliegend (Lower Permian) Gas Play is one of the possible illustrations of the entity of the North German Basin with its more than 70 - 90 independent parameters belonging to a global set of very complex hydrocarbon systems. Processes on Earth like the formation of systems of hydrocarbon fields as well as environmental systems (e.g. river systems, lakes, islands, sedimentary basins) are subordinated to the dices of nature and are steered invisibly by a selection of rules of the game that one understands as natural laws. The facts and remaining uncertainties as well as problems with subsurface-related processes (e.g. manmade tectonics, subsidence and uplift) guide the thoughts of engaged individuals on how to proceed wisely with limited predictability of challenges and dangers of a subsurface system. This work will be a trial to associate once more the natural sciences (geology) and the humanities (philosophy) for the benefit of both.

Theoretical analysis of ground displacements induced by deep fluid injection based on fully-coupled poroelastic simulation

Observations of surface displacements are expected to aid in geomechanical analyses of injectioninduced seismicity.However,the controlling factors of the displacement magnitude remain poorly understood except the elastic modulus of the fluid-bearing reservoir.Here,an experiment scheme of numerical simulation based on fully-coupled poroelasticity is designed to investigate the displacements induced by deep underground fluid injection.According to the sealing ability of deep reservoirs,the numerical experiments are classified into two scenarios:injection into open and sealed reservoirs.Potential effects from both geological and operational parameters are considered during the experiments,which include the hydromechanical properties,the reservoir geometry,injection rates and volumes.Experimental results reveal that in addition to the reservoir depth and Young’s modulus,the porosity also has significant influences on the surface displacements.Geodetic modeling of injection-induced displacements should include the parameter of reservoir porosity.When the reservoir is characterized by a good sealing ability,fluid injection is prone to induce larger horizontal displacements than vertical uplifts.Most of injection activities including hydraulic fracturing can probably induce detectable surface displacements.Geodetic surveying,especially using Global Navigation Satellite System(GNSS)with both horizontal and vertical observations,should become an essential monitoring task for anthropogenic fluid injection/production activities,which is conducive to assess and mitigate some geohazards including earthquakes.

A Novel ISSA–DELM Model for Predicting Rock Mass Permeability

In pumped storage projects,the permeability of rock masses is a crucial parameter in engineering design and construction.The rock mass permeability coefficient(K)is influenced by various geological parameters,and previous studies aimed to establish an accurate relationship between K and geological parameters.This study uses the improved sparrow search algorithm(ISSA)to optimize the parameter settings of the deep extreme learning machine(DELM),constructing a prediction model with flexible parameter selection and high accuracy.First,the Spearman method is applied to analyze the correlation between geological parameters.A sample database is built by comprehensively selecting four geological indexes:burial depth,rock quality designation(RQD),fracture density characteristic index(FD),and rock mass integrity designation(RID).Hence,the defects of the sparrow search algorithm(SSA)are enhanced using the improved strategy,and the initial input weights of the DELM are optimized.Finally,the proposed ISSA–DELM model is employed to predict the permeability coefficient of rock mass in the entire study area.The results showed that the predictive performance of the model is superior to that of the DELM and SSA–DELM.Therefore,this model successfully provides insights into the distribution characteristics of rock mass permeability at engineering sites.