A Three-dimensional IP-based Telecom Metropolitan Area Network Model

The Metropolitan Area Network (MAN) has faced serious problems after years of rapid development. The model of three-dimensional IP-based MAN, proposed by ZTE, is a next-generation MAN solution, which not only solves the existing problems but also brings new ideas for the development of next-generation MAN.

Prediction of Salinity Variations in a Tidal Estuary Using Artificial Neural Network and Three-Dimensional Hydrodynamic Models

The simulation of salinity at different locations of a tidal river using physically-based hydrodynamic models is quite cumbersome because it requires many types of data, such as hydrological and hydraulic time series at boundaries, river geometry, and adjusted coefficients. Therefore, an artificial neural network (ANN) technique using a back-propagation neural network (BPNN) and a radial basis function neural network (RBFNN) is adopted as an effective alternative in salinity simulation studies. The present study focuses on comparing the performance of BPNN, RBFNN, and three-dimensional hydrodynamic models as applied to a tidal estuarine system. The observed salinity data sets collected from 18 to 22 May, 16 to 22 October, and 26 to 30 October 2002 (totaling 4320 data points) were used for BPNN and RBFNN model training and for hydrodynamic model calibration. The data sets collected from 30 May to 2 June and 11 to 15 November 2002 (totaling 2592 data points) were adopted for BPNN and RBFNN model verification and for hydrodynamic model verification. The results revealed that the ANN (BPNN and RBFNN) models were capable of predicting the nonlinear time series behavior of salinity to the multiple forcing signals of water stages at different stations and freshwater input at upstream boundaries. The salinity predicted by the ANN models was better than that predicted by the physically based hydrodynamic model. This study suggests that BPNN and RBFNN models are easy-to-use modeling tools for simulating the salinity variation in a tidal estuarine system.

Discontinuity development patterns and the challenges for 3D discrete fracture network modeling on complicated exposed rock surfaces

Natural slopes usually display complicated exposed rock surfaces that are characterized by complex and substantial terrain undulation and ubiquitous undesirable phenomena such as vegetation cover and rockfalls.This study presents a systematic outcrop research of fracture pattern variations in a complicated rock slope,and the qualitative and quantitative study of the complex phenomena impact on threedimensional(3D)discrete fracture network(DFN)modeling.As the studies of the outcrop fracture pattern have been so far focused on local variations,thus,we put forward a statistical analysis of global variations.The entire outcrop is partitioned into several subzones,and the subzone-scale variability of fracture geometric properties is analyzed(including the orientation,the density,and the trace length).The results reveal significant variations in fracture characteristics(such as the concentrative degree,the average orientation,the density,and the trace length)among different subzones.Moreover,the density of fracture sets,which is approximately parallel to the slope surface,exhibits a notably higher value compared to other fracture sets across all subzones.To improve the accuracy of the DFN modeling,the effects of three common phenomena resulting from vegetation and rockfalls are qualitatively analyzed and the corresponding quantitative data processing solutions are proposed.Subsequently,the 3D fracture geometric parameters are determined for different areas of the high-steep rock slope in terms of the subzone dimensions.The results show significant variations in the same set of 3D fracture parameters across different regions with density differing by up to tenfold and mean trace length exhibiting differences of 3e4 times.The study results present precise geological structural information,improve modeling accuracy,and provide practical solutions for addressing complex outcrop issues.

3D geological modeling for mineral resource assessment of the Tongshan Cu deposit,Heilongjiang Province,China

Three-dimensional geological modeling （3DGM） assists geologists to quantitatively study in three-dimensional （3D） space structures that define temporal and spatial relationships between geological objects. The 3D property model can also be used to infer or deduce causes of geological objects. 3DGM technology provides technical support for extraction of diverse geoscience information, 3D modeling, and quantitative calculation of mineral resources. Based on metallogenic concepts and an ore deposit model, 3DGM technology is applied to analyze geological characteristics of the Tongshan Cu deposit in order to define a metallogenic model and develop a virtual borehole technology; a BP neural network and a 3D interpolation technique were combined to integrate multiple geoscience information in a 3D environment. The results indicate： （1） on basis of the concept of magmatic-hydrothermal Cu polymetallic mineraliza- tion and a porphyry Cu deposit model, a spatial relational database of multiple geoscience information for mineralization in the study area （geology, geophysics, geochemistry, borehole, and cross-section data） was established, and 3D metallogenic geological objects including mineralization stratum, granodiorite, alteration rock, and magnetic anomaly were constructed; （2） on basis of the 3D ore deposit model, 23,800 effective surveys from 94 boreholes and 21 sections were applied to establish 3D orebody models with a kriging interpolation method; （3） combined 23,800 surveys involving 21 sections, using VC＋＋ and OpenGL platform, virtual borehole and virtual section with BP network, and an improved inverse distance interpolation （IDW） method were used to predict and delineate mineralization potential targets （Cu-grade of cell not less than 0.1%）; （4） comparison of 3D ore bodies, metallogenic geological objects of mineralization, and potential targets of mineralization models in the study area, delineated the 3D spatial and temporal relationship and causal processes among the ore bodies, alteration rock, metallo- genic stratum, intrusive rock, and the Tongshan Fault. This study provides important technical support and a scientific basis for assessment of the Tongshan Cu deposit and surrounding exploration and mineral resources.

Improving Wind Forecasts Using a Gale-Aware Deep Attention Network

Numerical weather prediction of wind speed requires statistical postprocessing of systematic errors to obtain reliable and accurate forecasts.However,use of postprocessing models is often undesirable for extreme weather events such as gales.Here,we propose a postprocessing algorithm based on a gale-aware deep attention network to simultaneously improve wind speed forecasts and gale area warnings.Specifically,the algorithm includes both a galeaware loss function that focuses the model on potential gale areas,and an observation station supervision strategy that alleviates the problem of missing extreme values caused by data gridding.The effectiveness of the proposed model was verified by using data from 235 wind speed observation stations.Experimental results show that our model can produce wind speed forecasts with a root-mean-square error of 1.1547 m s^(-1),and a Hanssen–Kuipers discriminant score of 0.517,performance that is superior to that of the other postprocessing algorithms considered.

Deep 3D reconstruction:methods,data,and challenges

Three-dimensional(3D)reconstruction of shapes is an important research topic in the fields of computer vision,computer graphics,pattern recognition,and virtual reality.Existing 3D reconstruction methods usually suffer from two bottlenecks:(1)they involve multiple manually designed states which can lead to cumulative errors,but can hardly learn semantic features of 3D shapes automatically;(2)they depend heavily on the content and quality of images,as well as precisely calibrated cameras.As a result,it is difficult to improve the reconstruction accuracy of those methods.3D reconstruction methods based on deep learning overcome both of these bottlenecks by automatically learning semantic features of 3D shapes from low-quality images using deep networks.However,while these methods have various architectures,in-depth analysis and comparisons of them are unavailable so far.We present a comprehensive survey of 3D reconstruction methods based on deep learning.First,based on different deep learning model architectures,we divide 3D reconstruction methods based on deep learning into four types,recurrent neural network,deep autoencoder,generative adversarial network,and convolutional neural network based methods,and analyze the corresponding methodologies carefully.Second,we investigate four representative databases that are commonly used by the above methods in detail.Third,we give a comprehensive comparison of 3D reconstruction methods based on deep learning,which consists of the results of different methods with respect to the same database,the results of each method with respect to different databases,and the robustness of each method with respect to the number of views.Finally,we discuss future development of 3D reconstruction methods based on deep learning.