A Computationally Efficient Technique for Source Identification Problems in Three-Dimensional Aquifer Systems Using Neural Networks and Simulated Annealing

2006 ◽  
Vol 7 (3) ◽  
pp. 233-240 ◽  
Author(s):  
S. V. N. Rao
Keyword(s):  
Neural Networks ◽  
Simulated Annealing ◽  
Source Identification ◽  
Three Dimensional ◽  
Efficient Technique ◽  
Computationally Efficient ◽  
Identification Problems ◽  
Aquifer Systems

A Fast View Synthesis Implementation Method for Light Field Applications

2021 ◽  
Vol 17 (4) ◽  
pp. 1-20
Author(s):  
Wei Gao ◽  
Linjie Zhou ◽  
Lvfang Tao
Keyword(s):  
Neural Networks ◽  
Light Field ◽  
Three Dimensional ◽  
Super Resolution ◽  
View Synthesis ◽  
Compact Representation ◽  
Light Weight ◽  
Computationally Efficient ◽  
Full Resolution ◽  
Time Systems

View synthesis (VS) for light field images is a very time-consuming task due to the great quantity of involved pixels and intensive computations, which may prevent it from the practical three-dimensional real-time systems. In this article, we propose an acceleration approach for deep learning-based light field view synthesis, which can significantly reduce calculations by using compact-resolution (CR) representation and super-resolution (SR) techniques, as well as light-weight neural networks. The proposed architecture has three cascaded neural networks, including a CR network to generate the compact representation for original input views, a VS network to synthesize new views from down-scaled compact views, and a SR network to reconstruct high-quality views with full resolution. All these networks are jointly trained with the integrated losses of CR, VS, and SR networks. Moreover, due to the redundancy of deep neural networks, we use the efficient light-weight strategy to prune filters for simplification and inference acceleration. Experimental results demonstrate that the proposed method can greatly reduce the processing time and become much more computationally efficient with competitive image quality.

Meshless Collocation Method for Inverse Source Identification Problems

2015 ◽  
Vol 7 (4) ◽  
pp. 496-509 ◽  
Author(s):  
Fuzhang Wang ◽  
Zhaoxing Ma
Keyword(s):  
Collocation Method ◽  
Radial Basis Functions ◽  
Source Identification ◽  
Basis Functions ◽  
Computationally Efficient ◽  
Identification Problems ◽  
Present Scheme ◽  
Numerical Examples ◽  
Meshless Collocation ◽  
Boundary Measurements

AbstractA novel meshless scheme is proposed for inverse source identification problems of Helmholtz-type equations. It is formulated by the non-singular general solutions of the Helmholtz-type equations augmented with radial basis functions. Under this meshless scheme, we can determine smooth source terms from partially accessible boundary measurements with accurate results. Numerical examples are presented to verify validity and accuracy of the present scheme. It is demonstrated that the present scheme is simple, accurate, stable and computationally efficient for inverse smooth source identification problems.

scholarly journals Generation and Annotation of Simulation-Real Ship Images for Convolutional Neural Networks Training and Testing

2021 ◽  
Vol 11 (13) ◽  
pp. 5931
Author(s):  
Ji’an You ◽  
Zhaozheng Hu ◽  
Chao Peng ◽  
Zhiqiang Wang
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Image Annotation ◽  
Three Dimensional ◽  
Image Data ◽  
Detection Algorithm ◽  
Simulation Software ◽  
High Quality ◽  
Annotation Method ◽  
Detection Of Objects

Large amounts of high-quality image data are the basis and premise of the high accuracy detection of objects in the field of convolutional neural networks (CNN). It is challenging to collect various high-quality ship image data based on the marine environment. A novel method based on CNN is proposed to generate a large number of high-quality ship images to address this. We obtained ship images with different perspectives and different sizes by adjusting the ships’ postures and sizes in three-dimensional (3D) simulation software, then 3D ship data were transformed into 2D ship image according to the principle of pinhole imaging. We selected specific experimental scenes as background images, and the target ships of the 2D ship images were superimposed onto the background images to generate “Simulation–Real” ship images (named SRS images hereafter). Additionally, an image annotation method based on SRS images was designed. Finally, the target detection algorithm based on CNN was used to train and test the generated SRS images. The proposed method is suitable for generating a large number of high-quality ship image samples and annotation data of corresponding ship images quickly to significantly improve the accuracy of ship detection. The annotation method proposed is superior to the annotation methods that label images with the image annotation software of Label-me and Label-img in terms of labeling the SRS images.

scholarly journals Identification of Mode Shapes of a Composite Cylinder Using Convolutional Neural Networks

Materials ◽  
2021 ◽  
Vol 14 (11) ◽  
pp. 2801
Author(s):  
Bartosz Miller ◽  
Leonard Ziemiański
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Composite Structures ◽  
Three Dimensional ◽  
Mode Shapes ◽  
Identification Algorithm ◽  
Material Degradation ◽  
Local Material ◽  
Noisy Input ◽  
Shape Vector

The aim of the following paper is to discuss a newly developed approach for the identification of vibration mode shapes of multilayer composite structures. To overcome the limitations of the approaches based on image analysis (two-dimensional structures, high spatial resolution of mode shapes description), convolutional neural networks (CNNs) are applied to create a three-dimensional mode shapes identification algorithm with a significantly reduced number of mode shape vector coordinates. The CNN-based procedure is accurate, effective, and robust to noisy input data. The appearance of local damage is not an obstacle. The change of the material and the occurrence of local material degradation do not affect the accuracy of the method. Moreover, the application of the proposed identification method allows identifying the material degradation occurrence.

scholarly journals Nonlinear effects of locally heterogeneous hydraulic conductivity fields on regional stream–aquifer exchanges

2015 ◽  
Vol 19 (11) ◽  
pp. 4531-4545 ◽  
Author(s):  
J. Zhu ◽  
C. L. Winter ◽  
Z. Wang
Keyword(s):  
Groundwater Flow ◽  
Effective Conductivity ◽  
Model Simulation ◽  
Three Dimensional ◽  
Small Scale ◽  
Heihe River ◽  
Effective Parameters ◽  
Aquifer Systems ◽  
Basin Scale ◽  
Local Grid

Abstract. Computational experiments are performed to evaluate the effects of locally heterogeneous conductivity fields on regional exchanges of water between stream and aquifer systems in the Middle Heihe River basin (MHRB) of northwestern China. The effects are found to be nonlinear in the sense that simulated discharges from aquifers to streams are systematically lower than discharges produced by a base model parameterized with relatively coarse effective conductivity. A similar, but weaker, effect is observed for stream leakage. The study is organized around three hypotheses: (H1) small-scale spatial variations of conductivity significantly affect regional exchanges of water between streams and aquifers in river basins, (H2) aggregating small-scale heterogeneities into regional effective parameters systematically biases estimates of stream–aquifer exchanges, and (H3) the biases result from slow paths in groundwater flow that emerge due to small-scale heterogeneities. The hypotheses are evaluated by comparing stream–aquifer fluxes produced by the base model to fluxes simulated using realizations of the MHRB characterized by local (grid-scale) heterogeneity. Levels of local heterogeneity are manipulated as control variables by adjusting coefficients of variation. All models are implemented using the MODFLOW (Modular Three-dimensional Finite-difference Groundwater Flow Model) simulation environment, and the PEST (parameter estimation) tool is used to calibrate effective conductivities defined over 16 zones within the MHRB. The effective parameters are also used as expected values to develop lognormally distributed conductivity (K) fields on local grid scales. Stream–aquifer exchanges are simulated with K fields at both scales and then compared. Results show that the effects of small-scale heterogeneities significantly influence exchanges with simulations based on local-scale heterogeneities always producing discharges that are less than those produced by the base model. Although aquifer heterogeneities are uncorrelated at local scales, they appear to induce coherent slow paths in groundwater fluxes that in turn reduce aquifer–stream exchanges. Since surface water–groundwater exchanges are critical hydrologic processes in basin-scale water budgets, these results also have implications for water resources management.

Three‐Dimensional Numerical Investigation of Pore Water Pressure and Deformation of Pumped Aquifer Systems

Ground Water ◽  
2019 ◽  
Vol 58 (2) ◽  
pp. 278-290 ◽  
Author(s):  
Yun Zhang ◽  
Xuexin Yan ◽  
Tianliang Yang ◽  
Jichun Wu ◽  
Jianzhong Wu
Keyword(s):  
Numerical Investigation ◽  
Pore Water ◽  
Pore Water Pressure ◽  
Water Pressure ◽  
Three Dimensional ◽  
Aquifer Systems
Sign in / Sign up

Export Citation Format

Share Document