Parallel Vision ■ Image Synthesis/Augmentation

Dear Editor,Scene understanding is an essential task in computer vision.The ultimate objective of scene understanding is to instruct computers to understand and reason about the scenes as humans do.Parallel vision is a research framework that unifies the explanation and perception of dynamic and complex scenes.

Heterogeneous Image Knowledge Driven Visual Perception

Dear Editor,This letter is concerned with visual perception closely related to heterogeneous images.Facing the huge challenge brought by different image modalities,we propose a visual perception framework based on heterogeneous image knowledge,i.e.,the domain knowledge associated with specific vision tasks,to better address the corresponding visual perception problems.

Sedimentary systems of the Oligocene Huagang Formation in the central anticline zone of the Xihu Depression,East China Sea Shelf Basin

The Xihu Depression is the largest hydrocarbon-bearing depression of the East China Sea Shelf Basin(also referred to as the ECSSB).However,the depositional systems and reservoir distribution of the Oligocene Huagang Formation in the Xihu Depression are still controversial.Under the guidance of sedimentology and stratigraphy,this study documented a marine-terrestrial transitional environment in the restricted bay setting of the Oligocene Huagang Formation through core description,well logging,and seismic data analysis.This study also revealed that the Oligocene Huagang Formation is dominated by tidal delta,estuary,and gravity flow deposits in the central anticline zone of the Xihu Depression.The new understanding of the sedimentary systems and the discovery of the transgressive gap in the eastern Diaoyu Islands uplift explain the origin of fine-grained sediments and the EW-trending sand bodies in the central depression and the sand bodies parallel to shoreline in the west slope belt,which cannot be explained by previous study results,such as southern transgression or fluvial deltas and even lacustrine deposition.Moreover,the tidal channels,tidal sand flats,and gravity flow sand bodies formed by the transgressive tides are high-quality reservoirs.The study will provide a basis for well placement and serve as guidance for the selection of favorable hydrocarbon exploration areas in the Xihu Depression.

Intelligent architecture modeling for multilevel fluvial reservoirs based on architecture interface and elements

At present,the architecture modeling method of fluvial reservoirs are still developing.Traditional methods usually use grids to characterize architecture interbeds within the reservoir.Due to the thin thickness of this type of the interlayers,the number of the model grids must be greatly expanded.The number of grids in the tens of millions often makes an expensive computation;however,upscaling the model will generate a misleading model.The above confusion is the major reason that restricts the largescale industrialization of fluvial reservoir architecture models in oilfield development and production.Therefore,this paper explores an intelligent architecture modeling method for multilevel fluvial reservoirs based on architecture interface and element.Based on the superpositional relationship of different architectural elements within the fluvial reservoir,this method uses a combination of multilevel interface constraints and non-uniform grid techniques to build a high-resolution 3D geological model for reservoir architecture.Through the grid upscaling technology of heterogeneous architecture elements,different upscaling densities are given to the lateral-accretion bedding and lateral-accretion bodies to simplify the model gridding.This new method greatly reduces the number of model grids while ensuring the accuracy of lateral-accretion bedding models,laying a foundation for large-scale numerical simulation of the subsequent industrialization of the architecture model.This method has been validated in A layer of X oilfield with meandering fluvial channel sands as reservoirs and B layer of Y oilfield with braided river sands as reservoirs.The simulation results show that it has a higher accuracy of production history matching and remaining oil distribution forecast of the targeted sand body.The numerical simulation results show that in the actual development process of oilfield,the injected water will not displace oil in a uniform diffusive manner as traditionally assumed,but in a more complex pattern with oil in upper part of sand body being left behind as residual oil due to the influences of different levels of architecture interfaces.This investigation is important to guiding reservoir evaluation,remaining oil analysis,profile control and potential tapping and well pattern adjustment.

Spatial distribution characteristics and influence factor analysis of landslides——case study of the Hanwang area in Qinba Mountains

The geological hazards of landslides in Hanwang Town, Ziyang County, Ankang City, Shaanxi Province, have emerged. Yet, the current understanding of the spatial distribution characteristics and influencing factors of landslides in this area remains unclear. Combining the results of remote sensing interpretation and field investigation, seven influencing factors, namely, elevation, slope direction, slope gradient, distance from rivers, distance from faults, engineering geologic lithology, and distance from roads, are selected for the study. The distribution characteristics of landslides in each influencing factor and the influence of the resolution of the Digital Elevation Model(DEM) on the results are statistically and analytically analyzed. Furthermore, two highrisk landslides within the study area were subjected to comprehensive analysis, integrating the findings from drilling and other field investigations in order to examine their deformation mechanisms. Based on this analysis,the following conclusions were derived:(1) 34 landslides in the study area, mainly small earth landslides, with a distribution density of 0.42/km~2, threatening 414 people and property of about 55.87 million Yuan.(2)The landslides in the study area easily occur in the <400 m elevation range;the landslides are developed in all slope directions, the gradient is mainly concentrated in the range of 10°–40°, the distribution density of the landslides is higher in the closer distance from the river and the faults(0–200 m), the landslide-prone strata are mainly the softer and weaker metamorphic rocks, and the landslides are mainly around roads.(3) The resolution of the DEM should be selected based on the specific conditions of the study area, the requirements of the investigation, and the scale of the landslide. Opting for an appropriate DEM resolution is advantageous for understanding the patterns of landslides and conducting risk assessments in the region.(4) The Zhengjiabian landslide is a traction Landslide. The landslide body is a binary structure of gravel soil and slate weathering layer, and the damage process can be divided into three stages:(1)damage to the leading edge and stress release,(2)continuous creep and cracking,(3)rainfall infiltration and damage. The predominant slope material in the Brickyard landslide comprises clay, and the landslide is triggered by a combination of the traction effect resulting from the excavation at the slope's base and the nudging effect caused by the stacking load of the brick factory. Additionally, the Brickyard landslide exhibits persistent creep deformation. The study results provide a scientific basis for disaster prevention and mitigation in the Hanwang Township area.

DAO to HANOI via DeSci: AI Paradigm Shifts from AlphaGo to ChatGPT

From AlphaGo to ChatGPT,the field of AI has launched a series of remarkable achievements in recent years.Analyzing,comparing,and summarizing these achievements at the paradigm level is important for future AI innovation,but has not received sufficient attention.In this paper,we give an overview and perspective on machine learning paradigms.First,we propose a paradigm taxonomy with three levels and seven dimensions from a knowledge perspective.Accordingly,we give an overview on three basic and twelve extended learning paradigms,such as Ensemble Learning,Transfer Learning,etc.,with figures in unified style.We further analyze three advanced paradigms,i.e.,AlphaGo,AlphaFold and ChatGPT.Second,to enable more efficient and effective scientific discovery,we propose to build a new ecosystem that drives AI paradigm shifts through the decentralized science(DeSci)movement based on decentralized autonomous organization(DAO).To this end,we design the Hanoi framework,which integrates human factors,parallel intelligence based on a combination of artificial systems and the natural world,and the DAO to inspire AI innovations.

Experimental study on instability mechanism and critical intensity of rainfall of high-steep rock slopes under unsaturated conditions

Two critical factors,namely intense precipitation and intricate excavation,can trigger rock mass disasters in mining operations.In this study,an indoor rainfall system was developed to precisely regulate the flow and intensity of precipitation.A large-scale model experiment was conducted on a self-designed physical simulation experiment platform to investigate the failure and instability of high-steep rock slopes under unsaturated conditions.The real-time reproduction of the progressive failure process in high-steep rock slopes enabled the determination of the critical rainfall intensity and revealed the mechanism underlying slope instability.Experiment results indicated that rainfall may be the primary factor contributing to rock mass instability,while continuous pillar mining exacerbates the extent of rock mass failure.The critical failure stage of high-steep rock slopes occurs at a rainfall intensity of 40 mm/h,whereas a rainfall exceeding 50 mm can induce critical instability and precipitation reaching up to 60 mm will result in slope failure.The improved region growing segmentation method(IRGSM)was subsequently employed for image recognition of rock mass deformation in underground mines.Herein an error comparison with the simple linear iterative cluster(SLIC)superpixel method and the original region growing segmentation method(ORGSM)showed that the average identification error in the X and Y directions by the method was reduced significantly(1.82%and 1.80%in IRGSM;4.70%and 6.26%in SLIC;9.45%and 12.40%in ORGSM).Ultimately,the relationship between rainfall intensity and failure probability was analyzed using the Monte Carlo method.Moreover,the stability assessment criteria of rock slope under unsaturated condition were quantitatively and accurately evaluated.

Quantitative characterization of deep fault-karst carbonate reservoirs: A case study of the Yuejin block in the Tahe oilfield

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.

Effect of graph generation on slope stability analysis based on graph theory

Limit equilibrium method （LEM） and strength reduction method （SRM） are the most widely used methods for slope stability analysis. However, it can be noted that they both have some limitations in practical application. In the LEM, the constitutive model cannot be considered and many assumptions are needed between slices of soil/rock. The SRM requires iterative calculations and does not give the slip surface directly. A method for slope stability analysis based on the graph theory is recently developed to directly calculate the minimum safety factor and potential critical slip surface according to the stress results of numerical simulation. The method is based on current stress state and can overcome the disadvantages mentioned above in the two traditional methods. The influences of edge generation and mesh geometry on the position of slip surface and the safety factor of slope are studied, in which a new method for edge generation is proposed, and reasonable mesh size is suggested. The results of benchmark examples and a rock slope show good accuracy and efficiency of the presented method.

High-Gain and Low-RCS Patch Antenna Array Based on Slot-EBG Structure

A novel low radar cross-section(RCS)and high gain patch antenna array is proposed.A pair of slots introduced on the mushroom electromagnetic bandgap(EBG)patch realize polarization-dependency and act as parasitic radiation to enhance the antenna gain.A chessboard-like configuration composed of slot-EBG blocks is further equipped on the antenna array for scattering cancellation.Optimizing the layout pattern enables the designing of a high-gain and low-RCS antenna array using the slot-EBGs.Full-wave simulations validate that a front gain enhancement of more than 2.5.dB in the operating frequency band and low-RCS in a broad frequency band for normal incidence are obtained by the proposed antenna array.

Design of Tapered Novel AMC Chessboard Reflector for Broadband RCS Reduction

An artificial magnetic conductor(AMC)chessboard reflector is designed which shows low backscattered radar cross sections(RCS)in a broad frequency band in this paper.Designed by the phase cancellation principle,a conventional chessboard low RCS metasurface can be formed by polarization-dependent mushroom-shaped AMCs.Two new features are added to this design based on the conventional chessboard metasurface.Firstly,the long edge of the metallic patch on the AMC element is concave to obtain a broader bandwidth.Then,the width of the patch in each AMC block is tapered in one direction to further extend the operating bandwidth for RCS reduction.The backscattered RCS of the tapered AMC reflector is numerically investigated and compared with a non-tapered one.It is found that by introducing the above features,an RCS reduction greater than 10.dB can be obtained by the reflectors with relative bandwidth of 46%in the X-band.

Displacement field reconstruction in landslide physical modeling by using a terrain laser scanner e Part 1:Methodology,error analysis and validation

Laser scanning technology has been widely used in landslide aspects.However,the existing deformation analysis based on terrain laser scanners can only provide limited information,which is insufficient for understanding landslide kinematics and failure mechanisms.To overcome this limitation,this paper proposes an automated method for processing point clouds collected in landslide physical modeling.This method allows the acquisition of quantitative three-dimensional(3D)deformation field information.The results show the organized and spatially related point cloud segmentation in terms of spherical targets.The segmented point clouds can be fitted to determine the locations of all preset targets and their corresponding location changes.The proposed method has been validated based on theoretical analysis and numerical and physical tests,which indicates that it can batch-process massive data sets with high computational efficiency and good noise resistance.Compared to existing methods,this method shows a significant potential for understanding landslide kinematics and failure mechanisms and advancing the application of 3D laser scanning in geotechnical modeling.

Displacement field reconstruction in landslide physical modeling by using a terrain laser scanner e Part 2:Application and large strain/displacement and water effect analysis

Deformation analysis is fundamental in geotechnical modeling.Nevertheless,there is still a lack of an effective method to obtain the deformation field under various experimental conditions.In this study,we introduce a processebased physical modeling of a pileereinforced reservoir landslide and present an improved deformation analysis involving large strains and water effects.We collect multieperiod point clouds using a terrain laser scanner and reconstruct its deformation field through a point cloud processing workflow.The results show that this method can accurately describe the landslide surface deformation at any time and area by both scalar and vector fields.The deformation fields in different profiles of the physical model and different stages of the evolutionary process provide adequate and detailed landslide information.We analyze the large strain upstream of the pile caused by the pile installation and the consequent violent deformation during the evolutionary process.Furthermore,our method effectively overcomes the challenges of identifying targets commonly encountered in geotechnical modeling where water effects are considered and targets are polluted,which facilitates the deformation analysis at the wading area in a reservoir landslide.Eventually,combining subsurface deformation as well as numerical modeling,we comprehensively analyze the kinematics and failure mechanisms of this complicated object involving landslides and pile foundations as well as water effects.This method is of great significance for any geotechnical modeling concerning large-strain analysis and water effects.

A 10-miRNA risk score-based prediction model for pathological complete response to neoadjuvant chemotherapy in hormone receptor-positive breast cancer

Patients with hormone receptor(HR)-positive tumors breast cancer usually experience a relatively low pathological complete response(p CR)to neoadjuvant chemotherapy(NAC).Here,we derived a 10-micro RNA risk score(10-mi RNA RS)-based model with better performance in the prediction of p CR and validated its relation with the disease-free survival(DFS)in 755 HRpositive breast cancer patients(273,265,and 217 in the training,internal,and external validation sets,respectively).This model,presented as a nomogram,included four parameters:the 10-mi RNA RS found in our previous study,progesterone receptor(PR),human epidermal growth factor receptor 2(HER2)status,and volume transfer constant(K).Favorable calibration and discrimination of 10-mi RNA RS-based model with areas under the curve(AUC)of 0.865,0.811,and 0.804 were shown in the training,internal,and external validation sets,respectively.Patients who have higher nomogram score(>92.2)with NAC treatment would have longer DFS(hazard ratio=0.57;95%CI:0.39–0.83;P=0.004).In summary,our data showed the 10-mi RNA RS-based model could precisely identify more patients who can attain p CR to NAC,which may help clinicians formulate the personalized initial treatment strategy and consequently achieves better clinical prognosis for patients with HRpositive breast cancer.

On the seismic stability analysis of reinforced rock slope and optimization of prestressed cables

The evaluation of the seismic stability of high rock slopes is of vital importance to ensure the safe operation of the hydropower stations.In this paper,an equivalent pseudo-static force analysis based on the finite element method is developed to evaluate the seismic stability of reinforced rock slopes where the prestressed cables are modeled by the bar elements applied with nodal forces and bounded only at the anchored parts.The method is applied to analyze a high rock slope in south-west China and the optimization of cables.The stabilization effects of prestressed cables on the seismic stability of the slope are studied,the simulations of the concrete heading are discussed and the potential failure modes of the shear concrete plug are compared.Based on this,the optimization of cables is studied including the anchor spacing and inclined angles.

Parallel cognition:hybrid intelligence for human-machine interaction and management

As an interdisciplinary research approach,traditional cognitive science adopts mainly the experiment,induction,modeling,and validation paradigm.Such models are sometimes not applicable in cyber-physical-socialsystems (CPSSs),where the large number of human users involves severe heterogeneity and dynamics.To reduce the decision-making conflicts between people and machines in human-centered systems,we propose a new research paradigm called parallel cognition that uses the system of intelligent techniques to investigate cognitive activities and functionals in three stages:descriptive cognition based on artificial cognitive systems (ACSs),predictive cognition with computational deliberation experiments,and prescriptive cognition via parallel behavioral prescription.To make iteration of these stages constantly on-line,a hybrid learning method based on both a psychological model and user behavioral data is further proposed to adaptively learn an individual’s cognitive knowledge.Preliminary experiments on two representative scenarios,urban travel behavioral prescription and cognitive visual reasoning,indicate that our parallel cognition learning is effective and feasible for human behavioral prescription,and can thus facilitate human-machine cooperation in both complex engineering and social systems.