Probabilistic seismic inversion based on physics-guided deep mixture density network

Deterministic inversion based on deep learning has been widely utilized in model parameters estimation.Constrained by logging data,seismic data,wavelet and modeling operator,deterministic inversion based on deep learning can establish nonlinear relationships between seismic data and model parameters.However,seismic data lacks low-frequency and contains noise,which increases the non-uniqueness of the solutions.The conventional inversion method based on deep learning can only establish the deterministic relationship between seismic data and parameters,and cannot quantify the uncertainty of inversion.In order to quickly quantify the uncertainty,a physics-guided deep mixture density network(PG-DMDN)is established by combining the mixture density network(MDN)with the deep neural network(DNN).Compared with Bayesian neural network(BNN)and network dropout,PG-DMDN has lower computing cost and shorter training time.A low-frequency model is introduced in the training process of the network to help the network learn the nonlinear relationship between narrowband seismic data and low-frequency impedance.In addition,the block constraints are added to the PG-DMDN framework to improve the horizontal continuity of the inversion results.To illustrate the benefits of proposed method,the PG-DMDN is compared with existing semi-supervised inversion method.Four synthetic data examples of Marmousi II model are utilized to quantify the influence of forward modeling part,low-frequency model,noise and the pseudo-wells number on inversion results,and prove the feasibility and stability of the proposed method.In addition,the robustness and generality of the proposed method are verified by the field seismic data.

Neural-Network-Based Charge Density Quantum Correction of Nanoscale MOSFETs

For the treatment of the quantum effect of charge distribution in nanoscale MOSFETs,a quantum correction model using Levenberg-Marquardt back-propagation neural networks is presented that can predict the quantum density from the classical density. The training speed and accuracy of neural networks with different hidden layers and numbers of neurons are studied. We conclude that high training speed and accuracy can be obtained using neural networks with two hidden layers,but the number of neurons in the hidden layers does not have a noticeable effect, For single and double-gate nanoscale MOSFETs, our model can easily predict the quantum charge density in the silicon layer,and it agrees closely with the Schrodinger-Poisson approach.

Fast recognition using convolutional neural network for the coal particle density range based on images captured under multiple light sources

A method based on multiple images captured under different light sources at different incident angles was developed to recognize the coal density range in this study.The innovation is that two new images were constructed based on images captured under four single light sources.Reconstruction image 1 was constructed by fusing greyscale versions of the original images into one image,and Reconstruction image2 was constructed based on the differences between the images captured under the different light sources.Subsequently,the four original images and two reconstructed images were input into the convolutional neural network AlexNet to recognize the density range in three cases:-1.5(clean coal) and+1.5 g/cm^(3)(non-clean coal);-1.8(non-gangue) and+1.8 g/cm^(3)(gangue);-1.5(clean coal),1.5-1.8(middlings),and+1.8 g/cm^(3)(gangue).The results show the following:(1) The reconstructed images,especially Reconstruction image 2,can effectively improve the recognition accuracy for the coal density range compared with images captured under single light source.(2) The recognition accuracies for gangue and non-gangue,clean coal and non-clean coal,and clean coal,middlings,and gangue reached88.44%,86.72% and 77.08%,respectively.(3) The recognition accuracy increases as the density moves further away from the boundary density.

Prediction of nuclear charge density distribution with feedback neural network

Nuclear charge density distribution plays an important role in both nuclear and atomic physics,for which the two-parameter Fermi(2pF)model has been widely applied as one of the most frequently used models.Currently,the feedforward neural network has been employed to study the available 2pF model parameters for 86 nuclei,and the accuracy and precision of the parameter-learning effect are improved by introducing A^(1∕3)into the input parameter of the neural network.Furthermore,the average result of multiple predictions is more reliable than the best result of a single prediction and there is no significant difference between the average result of the density and parameter values for the average charge density distribution.In addition,the 2pF parameters of 284(near)stable nuclei are predicted in this study,which provides a reference for the experiment.

Modeling of Energy Consumption and Effluent Quality Using Density Peaks-based Adaptive Fuzzy Neural Network

Modeling of energy consumption(EC) and effluent quality(EQ) are very essential problems that need to be solved for the multiobjective optimal control in the wastewater treatment process(WWTP). To address this issue, a density peaks-based adaptive fuzzy neural network(DP-AFNN) is proposed in this study. To obtain suitable fuzzy rules, a DP-based clustering method is applied to fit the cluster centers to process nonlinearity.The parameters of the extracted fuzzy rules are fine-tuned based on the improved Levenberg-Marquardt algorithm during the training process. Furthermore, the analysis of convergence is performed to guarantee the successful application of the DPAFNN. Finally, the proposed DP-AFNN is utilized to develop the models of EC and EQ in the WWTP. The experimental results show that the proposed DP-AFNN can achieve fast convergence speed and high prediction accuracy in comparison with some existing methods.

Correcting the systematic error of the density functional theory calculation:the alternate combination approach of genetic algorithm and neural network

The alternate combinational approach of genetic algorithm and neural network （AGANN） has been presented to correct the systematic error of the density functional theory （DFT） calculation. It treats the DFT as a black box and models the error through external statistical information. As a demonstration, the ACANN method has been applied in the correction of the lattice energies from the DFT calculation for 72 metal halides and hydrides. Through the AGANN correction, the mean absolute value of the relative errors of the calculated lattice energies to the experimental values decreases from 4.93% to 1.20% in the testing set. For comparison, the neural network approach reduces the mean value to 2.56%. And for the common combinational approach of genetic algorithm and neural network, the value drops to 2.15%. The multiple linear regression method almost has no correction effect here.

Data Gathering in Wireless Sensor Networks Via Regular Low Density Parity Check Matrix

A great challenge faced by wireless sensor networks(WSNs) is to reduce energy consumption of sensor nodes. Fortunately, the data gathering via random sensing can save energy of sensor nodes. Nevertheless, its randomness and density usually result in difficult implementations, high computation complexity and large storage spaces in practical settings. So the deterministic sparse sensing matrices are desired in some situations. However,it is difficult to guarantee the performance of deterministic sensing matrix by the acknowledged metrics. In this paper, we construct a class of deterministic sparse sensing matrices with statistical versions of restricted isometry property(St RIP) via regular low density parity check(RLDPC) matrices. The key idea of our construction is to achieve small mutual coherence of the matrices by confining the column weights of RLDPC matrices such that St RIP is satisfied. Besides, we prove that the constructed sensing matrices have the same scale of measurement numbers as the dense measurements. We also propose a data gathering method based on RLDPC matrix. Experimental results verify that the constructed sensing matrices have better reconstruction performance, compared to the Gaussian, Bernoulli, and CSLDPC matrices. And we also verify that the data gathering via RLDPC matrix can reduce energy consumption of WSNs.

An Aircraft Trajectory Anomaly Detection Method Based on Deep Mixture Density Network

The timely and accurately detection of abnormal aircraft trajectory is critical to improving flight safety.However,the existing anomaly detection methods based on machine learning cannot well characterize the features of aircraft trajectories.Low anomaly detection accuracy still exists due to the high-dimensionality,heterogeneity and temporality of flight trajectory data.To this end,this paper proposes an abnormal trajectory detection method based on the deep mixture density network(DMDN)to detect flights with unusual data patterns and evaluate flight trajectory safety.The technique consists of two components:Utilization of the deep long short-term memory(LSTM)network to encode features of flight trajectories effectively,and parameterization of the statistical properties of flight trajectory using the Gaussian mixture model(GMM).Experiment results on Guangzhou Baiyun International Airport terminal airspace show that the proposed method can effectively capture the statistical patterns of aircraft trajectories.The model can detect abnormal flights with elevated risks and its performance is superior to two mainstream methods.The proposed model can be used as an assistant decision-making tool for air traffic controllers.

Finite density scaling laws of condensation phase transition in zero-range processes on scale-free networks

The dynamics of zero-range processes on complex networks is expected to be influenced by the topological structure of underlying networks.A real space complete condensation phase transition in the stationary state may occur.We study the finite density effects of the condensation transition in both the stationary and dynamical zero-range processes on scale-free networks.By means of grand canonical ensemble method,we predict analytically the scaling laws of the average occupation number with respect to the finite density for the steady state.We further explore the relaxation dynamics of the condensation phase transition.By applying the hierarchical evolution and scaling ansatz,a scaling law for the relaxation dynamics is predicted.Monte Carlo simulations are performed and the predicted density scaling laws are nicely validated.

A new solution to wireless sensor network density control problem

In this paper, we proposed a scheme based on Monte Carlo algorithm to test whether or not the nodes are redundant for realizing the node density control in the sensor network. The computational complexity is only O(n). We also established the coverage collision detection and back-off mechanism applied in the wireless sensor network. The simulation results show that the system can cover all the interested area with the smallest number of nodes and a coverage void will not appear during the course of state-transition. The coverage collision detection and back-off mechanism proposed in this article can be applied when the nodes have either synchronous or asynchronous mechanism. It also provides a stable stage with the length of the time that can be adjusted.

The effect of topographic density variations on the geoid and orthometric heights in Hong Kong

Utilizing the adopted average topographic density of 2670 kg/m^(3)in the reduction of gravity anomalies introduces errors attributed to topographic density variations,which consequently affect geoid modeling accuracy.Furthermore,the mean gravity along the plumbline within the topography in the definition of Helmert orthometric heights is computed approximately by applying the Poincar e-Prey gravity reduction where the topographic density variations are disregarded.The Helmert orthometric heights of benchmarks are then affected by errors.These errors could be random or systematic depending on the specific geological setting of the region where the leveling network is physically established and/or the geoid model is determined.An example of systematic errors in orthometric heights can be given for large regions characterized by sediment or volcanic deposits,the density of which is substantially lower than the adopted topographic density used in Helmert's definition of heights.The same applies to geoid modeling errors.In this study,we investigate these errors in the Hong Kong territory,where topographic density is about 20%lower than the density of 2670 kg/m^(3).We use the digital rock density model to estimate the effect of topographic density variations on the geoid and orthometric heights.Our results show that this effect on the geoid and Helmert orthometric heights reach maxima of about 2.1 and 0.5 cm,respectively.Both results provide clear evidence that rock density models are essential in physical geodesy applications involving gravimetric geoid modeling and orthometric height determination despite some criticism that could be raised regarding the reliability of these density models.However,in regions dominated by sedimentary and igneous rocks,the geological information is essential in these applications because topographic densities are substantially lower than the average density of 2670 kg/m^(3),thus introducing large systematic errors in geoid and orthometric heights.

Design of Polynomial Fuzzy Neural Network Classifiers Based on Density Fuzzy C-Means and L2-Norm Regularization

In this paper, polynomial fuzzy neural network classifiers (PFNNCs) is proposed by means of density fuzzy c-means and L2-norm regularization. The overall design of PFNNCs was realized by means of fuzzy rules that come in form of three parts, namely premise part, consequence part and aggregation part. The premise part was developed by density fuzzy c-means that helps determine the apex parameters of membership functions, while the consequence part was realized by means of two types of polynomials including linear and quadratic. L2-norm regularization that can alleviate the overfitting problem was exploited to estimate the parameters of polynomials, which constructed the aggregation part. Experimental results of several data sets demonstrate that the proposed classifiers show higher classification accuracy in comparison with some other classifiers reported in the literature.

Estimation of dusk time F-region electron density vertical profiles using LSTM neural networks:A preliminary investigation

The vertical profile of the ionosphere density plays a significant role in the development of low-latitude Equatorial Plasma Bubbles(EPBs),that in turn lead to ionospheric scintillation which can severely degrade precision and availability of critical users of the Global Navigation Satellite System(GNSS).Accurate estimation of ionospheric delays through vertical electron density profiles is vital for mitigating GNSS errors and enhancing location-based services.The objective of this study is to propose a neural network,trained with radio occultation data from the COSMIC-1 mission,that generates average ionospheric electron density profiles during dusk,focusing on the pre-reversal enhancement of the zonal electric field.Results show that the estimated profiles exhibit a clear seasonal pattern,and reproduce adequately the climatological behavior of the ionosphere,thus presenting strong appeal on ionospheric error attenuation.

Modified Benes network architecture for WiMAX LDPC decoder

A modified Benes network is proposed to be used as an optimal shuffle network in worldwide interoperability for microwave access （WiMAX） low density parity check （LDPC） decoders, When the size of the input is not a power of two, the modified Benes network can achieve the most optimal performance. This modified Benes network is non-blocking and can perform any sorts of permutations, so it can support 19 modes specified in the WiMAX system. Furthermore, an efficient algorithm to generate the control signals for all the 2 × 2 switches in this network is derived, which can reduce the hardware complexity and overall latency of the modified Benes network. Synthesis results show that the proposed control signal generator can save 25.4% chip area and the overall network latency can be reduced by 36. 2%.

Node deployment strategy optimization for wireless sensor network with mobile base station

The optimization of network performance in a movement-assisted data gathering scheme was studied by analyzing the energy consumption of wireless sensor network with node uniform distribution. A theoretically analytical method for avoiding energy hole was proposed. It is proved that if the densities of sensor nodes working at the same time are alternate between dormancy and work with non-uniform node distribution. The efficiency of network can increase by several times and the residual energy of network is nearly zero when the network lifetime ends.

Data driven particle size estimation of hematite grinding process using stochastic configuration network with robust technique

As a production quality index of hematite grinding process,particle size(PS)is hard to be measured in real time.To achieve the PS estimation,this paper proposes a novel data driven model of PS using stochastic configuration network(SCN)with robust technique,namely,robust SCN(RSCN).Firstly,this paper proves the universal approximation property of RSCN with weighted least squares technique.Secondly,three robust algorithms are presented by employing M-estimation with Huber loss function,M-estimation with interquartile range(IQR)and nonparametric kernel density estimation(NKDE)function respectively to set the penalty weight.Comparison experiments are first carried out based on the UCI standard data sets to verify the effectiveness of these methods,and then the data-driven PS model based on the robust algorithms are established and verified.Experimental results show that the RSCN has an excellent performance for the PS estimation.

Spatiotemporal Patterns of Road Network and Road Development Pri-ority in Three Parallel Rivers Region in Yunnan,China:An Evaluation Based on Modified Kernel Distance Estimate

Road network is a critical component of public infrastructure,and the supporting system of social and economic development.Based on a modified kernel density estimate(KDE)algorithm,this study evaluated the road service capacity provided by a road network composed of multi-level roads(i.e.national,provincial,county and rural roads),by taking account of the differences of effect extent and intensity for roads of different levels.Summarized at town scale,the population burden and the annual rural economic income of unit road service capacity were used as the surrogates of social and economic demands for road service.This method was applied to the road network of the Three Parallel River Region,the northwestern Yunnan Province,China to evaluate the development of road network in this region.In results,the total road length of this region in 2005 was 3.70×104km,and the length ratio between national,provincial,county and rural roads was 1∶2∶8∶47.From 1989 to 2005,the regional road service capacity increased by 13.1%,of which the contributions from the national,provincial,county and rural roads were 11.1%,19.4%,22.6%,and 67.8%,respectively,revealing the effect of′All Village Accessible′policy of road development in the mountainous regions in the last decade.The spatial patterns of population burden and economic requirement of unit road service suggested that the areas farther away from the national and provincial roads have higher road development priority(RDP).Based on the modified KDE model and the framework of RDP evaluation,this study provided a useful approach for developing an optimal plan of road development at regional scale.

Serviceability evaluation of water supply networks under seismic loads utilizing their operational physical mechanism

The serviceability of water supply networks(WSNs)under seismic loads has significant importance for estimating the probable losses and the impact of diminished functionality on affected communities.The innovation presented in this paper is suggesting a new strategy to evaluate the seismic serviceability of WSNs,utilizing their operational physical mechanism.On one hand,this method can obtain the seismic serviceability of each node as well as entire WSNs.On the other hand,this method can dynamically reflect the propagation of randomness from ground motions to WSNs.First,a finite element model is established to capture the seismic response of buried pipe networks,and a leakage model is suggested to obtain the leakage area of WSNs.Second,the transient flow analysis of WSNs with or without leakage is derived to obtain dynamic water flow and pressure.Third,the seismic serviceability of WSNs is analyzed based on the probability density evolution method(PDEM).Finally,the seismic serviceability of a real WSN in Mianzhu city is assessed to illustrate the method.The case study shows that randomness from the ground motions can obviously affect the leakage state and the probability density of the nodal head during earthquakes.

Linearized Controller Design for the Output Probability Density Functions of Non-Gaussian Stochastic Systems

This paper presents a linearized approach for the controller design of the shape of output probability density functions for general stochastic systems. A square root approximation to an output probability density function is realized by a set of B-spline functions. This generally produces a nonlinear state space model for the weights of the B-spline approximation. A linearized model is therefore obtained and embedded into a performance function that measures the tracking error of the output probability density function with respect to a given distribution. By using this performance function as a Lyapunov function for the closed loop system, a feedback control input has been obtained which guarantees closed loop stability and realizes perfect tracking. The algorithm described in this paper has been tested on a simulated example and desired results have been achieved.

Automated Building Block Extraction and Building Density Classification Using Aerial Imagery and LiDAR Data

This paper examines the utility of high-resolution airborne RGB orthophotos and LiDAR data for mapping residential land uses within the spatial limits of suburb of Athens, Greece. Modem remote sensors deliver ample information from the AOI （area of interest） for the estimation of 2D indicators or with the inclusion of elevation data 3D indicators for the classification of urban land. In this research, two of these indicators, BCR （building coverage ratio） and FAR （floor area ratio） are automatically evaluated. In the pre-processing step, the low resolution elevation data are fused with the high resolution optical data through a mean-shift based discontinuity preserving smoothing algorithm. The outcome is an nDSM （normalized digital surface model） comprised of upsampled elevation data with considerable improvement regarding region filling and ＂straightness＂ of elevation discontinuities. Following this step, a MFNN （multilayer feedforward neural network） is used to classify all pixels of the AOI into building or non-building categories. The information derived from the BCR and FAR building indicators, adapted to landscape characteristics of the test area is used to propose two new indices and an automatic post-classification based on the density of buildings.