Neural Network Residual Kriging Research Articles

Flight Load Calculation Using Neural Network Residual Kriging

Flight load calculation, an important step in aircraft design and optimization, typically involves millions of computations and requires significant computing resources and time. Improving the efficiency of flight load calculations while maintaining accuracy is therefore of great significance for shortening research and development cycles. This study investigated and compared multiple algorithms, including the neural network model, the Kriging surrogate model, and the neural network residual Kriging (NNRK) model, for flight load analysis. The accuracies of all models were confirmed through evaluation, with NNRK being the most efficient, making it highly suitable for flight load analysis. The flight load data of a civil aircraft, including the total weight, the center of gravity, the pitch moment of inertia, the altitude, the Mach number, the airspeed, the velocity pressure, the pitch rate, the load factor, and the angle of attack as input parameters, were used as sample data to establish models, for predicting wing loads under different flight conditions. The accuracies of all regressions were confirmed through evaluation, with NNRK being the most efficient. The flight load calculation shows that NNRK can significantly improve analysis efficiency and provide new insights into efficient and comprehensive flight load analysis.

Predicting regional spatial distribution of soil texture in floodplains using remote sensing data: A case of southeastern Iran

Soil texture is a physical property of soil and knowledge on its spatial distribution is essential for many agricultural and environmental activities especially in alluvial plains. This study aimed to predict the spatial distribution of soil fractions (i.e. percentages of sand, silt, and clay) in Sistan floodplain on a regional scale (area: 1500 km2). Random forest (RF), regression kriging-neural network residual kriging (RKNNRK), neural network residual kriging (NNRK), regression kriging (RK), and cokriging (COK) methods were used to map soil texture components over the region. Soil fractions were measured for 160 soil samples taken from the surface layer (0–30 cm) of various soil series in agriculture land of Sistan floodplain. The additive log-ratio (alr) transformation was applied to transform texture components prior to prediction. Remote sensing data including Landsat 8′ Bands (1–8), Band 4 to Band 8 ratio, Band 4 to Band 3 ratio, NDVI, GSI, Brightness Index, and Clay Index were used as auxiliary variables for interpolation of soil fractions. 80% of actual data was used for prediction and 20% of data was used for validation. The performance of methods used was evaluated using RMSE, ME and MAE criteria. The results showed that the RKNNRK model has the highest accuracy for prediction of sand (RMSE = 15.04%) and clay (RMSE = 8.77%) contents while the most accurate model for predicting silt content is NNRK (RMSE = 12.68%). RK and COK performed worse than NNRK and RKNNRK. A relatively high value of RMSE obtained for sand (17.89%), silt (14.15%), and clay (8.89%) contents by the RF model. This could be due to the low relief of study area, regional scale effects, low density of sampling points and high heterogeneity of soil texture components in floodplains. Our findings revealed that RKNNRK and NNRK models, when combined with remote sensing data, produce more accurate results and therefore can be used for appropriate mapping of soil fractions in floodplains and on a regional scale.

On the Performance of Neural Network Residual Kriging in Radio Environment Mapping

This paper addresses the research question: can feedforward neural network (FFNN)-based path loss modeling improve the accuracy of Kriging? Radio propagation factors, which consist of path loss and shadowing, can accurately be obtained via crowdsourcing with Kriging. In most works on Kriging-aided radio environment mapping, measurement datasets are first regressed via linear path loss modeling to ensure spatial stationarity of the shadowing. However, in practical situations, the path loss often contains an anisotropy owing to terrain and obstacle effects. Thus, Kriging may not perform an optimal interpolation because of the errors in path loss modeling. In this paper, an FFNN is used for path loss modeling. Then, ordinary Kriging is applied to interpolate the shadowing. We first evaluate the performance of this method in a case where the transmitter is fixed. It is shown that this method does not improve Kriging in a large-scale and fixed transmitter system; although the FFNN outperforms OLS in path loss modeling. Then, this method is extended to distributed wireless networks where transmitters are arbitrarily located, such as in mobile ad hoc networks (MANETs) and vehicular ad hoc networks (VANETs). The results of a measurement-based experiment show that the FFNN is capable of improving Kriging in such a distributed network case.

High variation topsoil pollution forecasting in the Russian Subarctic: Using artificial neural networks combined with residual kriging

The work deals with the application of artificial neural networks combined with residual kriging (ANNRK) to the spatial prediction of the anomaly distributed chemical element Chromium (Cr). In the work, we examined and compared two neural networks: generalized regression neural network (GRNN) and multi-layer perceptron (MLP) as well as two combined techniques: generalized regression neural network residual kriging (GRNNRK) and multi-layer perceptron residual kriging (MLPRK). The case study is based on the real measurements of surface contamination by Cr in subarctic city Novy Urengoy, Russia. The networks structures have been chosen during a computer simulation based on a minimization of the root mean square error (RMSE). Different prediction approaches are compared by a Spearman's rank correlation coefficient, the mean absolute error (MAE), and RMSE. MLPRK and GRNNRK show the best predictive accuracy comparing to kriging and even to MLP and GRNN, that is hybrid models are more accurate than solo models. The most significant improvement in RMSE (15.5% compared to kriging) is observed in the MLPRK model. The proposed hybrid approach improves the high variation topsoil spatial pollution forecasting, which might be utilized in the environmental modeling.

Accurate modelling of lossy SIW resonators using a neural network residual kriging approach

Accurate modelling of lossy SIW resonators using a neural network residual kriging approach

An artificial neural network residual kriging based surrogate model for curvilinearly stiffened panel optimization

We have performed a design optimization of a stiffened panel with curvilinear stiffeners using an artificial neural network (ANN) residual kriging based surrogate modeling approach. The ANN residual kriging based surrogate modeling involves two steps. In the first step, we approximate the objective function using ANN. In the next step we use kriging to model the residue. We optimize the panel in an iterative way. Each iteration involves two steps-shape optimization and size optimization. For both shape and size optimization, we use ANN residual kriging based surrogate model. At each optimization step, we do an initial sampling and fit an ANN residual kriging model for the objective function. Then we keep updating this surrogate model using an adaptive sampling algorithm until the minimum value of the objective function converges. The comparison of the design obtained using our optimization scheme with that obtained using a traditional genetic algorithm (GA) based optimization scheme shows satisfactory agreement. However, with this surrogate model based approach we reach optimum design with less computation effort as compared to the GA based approach which does not use any surrogate model.

Estimating Spatial Precipitation Using Regression Kriging and Artificial Neural Network Residual Kriging (RKNNRK) Hybrid Approach

A hybrid model, combining regression kriging and neural network residual kriging (RKNNRK), is developed for determining spatial precipitation distribution. The RKNNRK model is compared with current spatial interpolation models, including simple kriging (SK), ordinary kriging (OK), universal kriging (UK), regression kriging (RK) and neural network residual kriging (NNRK). Results show that hybrid models, including RK, NNRK and RKNNRK, performed better than SK, OK and UK, based on the coefficient of efficiency (CE), coefficient of determination (r2), index of agreement (d), mean squared relative error (MSRE), mean absolute error (MAE), root-mean-square error (RMSE), and mean squared error (MSE). Of the six spatial interpolation models, the RKNNRK model was the most accurate, and the NNRK model was the second best.

Creating an advanced backpropagation neural network toolbox within GIS software

An artificial neural network (ANN) toolbox is created within GIS software for spatial interpolation, which will help GIS users to train and test ANNs, perform spatial analysis, and display results as a single process. The performance is compared to that of the open source Fast Artificial Neural Network library and conventional interpolation methods by creating digital elevation models (DEMs) given that nearly exact solutions exist. Simulation results show that the advanced backpropagations such as iRprop speed up the learning, while they can get stuck in a local minimum depending on initial weight sets. Besides, the division of input–output examples into training and test data affects the accuracy, particularly when the distribution of the examples is skewed and peaked, and the number of data is small. ANNs, however, show the similar performance to inversed distance weighted or kriging and outperform polynomial interpolations as a global interpolation method in high-dimensional data. In addition, the neural network residual kriging (NNRK) model, which combines the ANN toolbox and kriging within GIS software, is performed. The NNRK outperforms conventional methods and well captures global trends and local variations. A key outcome of this work is that the ANN toolbox created within the de facto standard GIS software is applicable to various spatial analysis including hazard risk assessment over a large area, in particular when there are multiple potential causes, the relationship between risk factors and hazard events is not clear, and the number of available data is small given its performance for DEM generation.

Wavelet analysis residual kriging vs. neural network residual kriging

This paper deals with the problem of spatial data mapping. A new method based on wavelet interpolation and geostatistical prediction (kriging) is proposed. The method – wavelet analysis residual kriging (WARK) – is developed in order to assess the problems rising for highly variable data in presence of spatial trends. In these cases stationary prediction models have very limited application. Wavelet analysis is used to model large-scale structures and kriging of the remaining residuals focuses on small-scale peculiarities. WARK is able to model spatial pattern which features multiscale structure. In the present work WARK is applied to the rainfall data and the results of validation are compared with the ones obtained from neural network residual kriging (NNRK). NNRK is also a residual-based method, which uses artificial neural network to model large-scale non-linear trends. The comparison of the results demonstrates the high quality performance of WARK in predicting hot spots, reproducing global statistical characteristics of the distribution and spatial correlation structure.

Modeling Porosity Distribution in the A'nan Oilfield: Use of Geological Quantification, Neural Networks, and Geostatistics

Summary A'nan Oilfield is located in the northeast of the Erlian Basin in North China. The porosity distribution of the oil-bearing stratum is primarily controlled by complex distribution patterns of sedimentary lithofacies and diagenetic facies. This paper describes a methodology to provide a porosity model for the A'nan Oilfield using limited well porosity data, with the incorporation of the conceptual reservoir architecture. Neural network residual kriging or simulation is employed to tackle the problem. The integrated technique is developed based on a combined use of radial basis function neural networks and geostatistics. It has the flexibility of neural networks in handling high-dimensional data, the exactitude property of kriging and the ability to perform stochastic simulation via the use of kriging variance. The results of this study show that the integrated technique provides a realistic description of porosity honoring both the well data and the conceptual framework of the geological interpretations. The technique is fast, straightforward and does not require any tedious cross-correlation modeling. It is of great benefit to reservoir geologists and engineers.

ARTIFICIAL NEURAL NETWORKS AND SPATIAL ESTIMATION OF CHERNOBYL FALLOUT

The present work continues advanced spatial data analysis of surface contamination by radionuclides after severe nuclear accident on Chernobyl NPP. Feedforward neural networks are used for the Cs137 and Sr90 radionuclides prediction mapping and spatial estimations. Neural networks are used to model complex trends over the entire region. Residuals are analyzed with the help of geostatistical approach within the framework of NNRK (neural network residual kriging) model. Another set of data is used to validate obtained results.