Updating the neural network sediment load models using different sensitivity analysis methods: a regional application

Abstract The amount of transported sediment load by streams is a vital but high nonlinear dynamic process in water resources management. In the current paper, two optimum predictive models subjected to artificial neural network (ANN) were developed. The employed inputs were then prioritized using diverse sensitivity analysis (SA) methods to address new updated but more efficient ANN structures. The models were found through the 263 processed datasets of three rivers in Idaho, USA using nine different measured flow and sediment variables (e.g., channel geometry, geomorphology, hydraulic) for a period of 11 years. The used parameters were selected based on the prior knowledge of the conventional analyses in which the effect of suspended load on bed load was also investigated. Analyzed accuracy performances using different criteria exhibited improved predictability in updated models which can lead to an advanced understanding of used parameters. Despite different SA methods being employed in evaluating model parameters, almost similar results were observed and then verified using relevant sensitivity indices. It was demonstrated that the ranked parameters using SA due to covering more uncertainties can be more reliable. Evaluated models using sensitivity indices showed that contribution of suspended load on predicted bed load is not significant.

Download Full-text

Data Mining using Artificial Neural Network POS_NEG Rules

INTERNATIONAL JOURNAL OF COMPUTERS & TECHNOLOGY ◽

10.24297/ijct.v11i6.3046 ◽

2013 ◽

Vol 11 (6) ◽

pp. 2709-2714

Author(s):

Pushkar Shinde ◽

Dr. Varsha Patil

Keyword(s):

Neural Network ◽

Data Mining ◽

Sensitivity Analysis ◽

Artificial Neural Network ◽

Backpropagation Algorithm ◽

The Neural Network ◽

Artificial Neural ◽

Using Data ◽

Artificial Neural Network Ann ◽

Sensitivity Method

Diabetes patients are increasing in number so it is necessary to predict , treat and diagnose the disease. Data Mining can help to provide knowledge about this disease. The knowledge extracted using Data Mining can help in treating and preventing the disease. Artificial Neural Network (ANN) can be used to create an classifier from the data. The neural network is trained using backpropagation algorithm The knowledge stored in the neural network is used to predict the disease. The knowledge stored in neural network is extracted using Pos-Neg sensitivity method. The knowledge extracted is in form of sensitivity analysis to analyze the disease and in turn help in treating the disease.

Download Full-text

Sobol′ Sensitivity Analysis Using a Neural Network Model of a LB-LOCA in the ZION Nuclear Power Plant With CATHARE-2 V2.5 Code

Volume 4: Thermal Hydraulics ◽

10.1115/icone21-15674 ◽

2013 ◽

Author(s):

Fabrice Fouet ◽

Pierre Probst

Keyword(s):

Neural Network ◽

Sensitivity Analysis ◽

Nuclear Power ◽

Uncertainty Propagation ◽

Correlation Coefficients ◽

Computer Code ◽

Numerical Application ◽

Loss Of Coolant Accident ◽

Input Parameters ◽

Artificial Neural Network Ann

In nuclear safety, the Best-Estimate (BE) codes may be used in safety demonstration and licensing, provided that uncertainties are added to the relevant output parameters before comparing them with the acceptance criteria. The uncertainty of output parameters, which comes mainly from the lack of knowledge of the input parameters, is evaluated by estimating the 95% percentile with a high degree of confidence. IRSN, technical support of the French Safety Authority, developed a method of uncertainty propagation. This method has been tested with the BE code used is CATHARE-2 V2.5 in order to evaluate the Peak Cladding Temperature (PCT) of the fuel during a Large Break Loss Of Coolant Accident (LB-LOCA) event, starting from a large number of input parameters. A sensitivity analysis is needed in order to limit the number of input parameters and to quantify the influence of each one on the response variability of the numerical model. Generally, the Global Sensitivity Analysis (GSA) is done with linear correlation coefficients. This paper presents a new approach to perform a more accurate GSA to determine and to classify the main uncertain parameters: the Sobol′ methodology. The GSA requires simulating many sets of parameters to propagate uncertainties correctly, which makes of it a time-consuming approach. Therefore, it is natural to replace the complex computer code by an approximate mathematical model, called response surface or surrogate model. We have tested Artificial Neural Network (ANN) methodology for its construction and the Sobol′ methodology for the GSA. The paper presents a numerical application of the previously described methodology on the ZION reactor, a Westinghouse 4-loop PWR, which has been retained for the BEMUSE international problem [8]. The output is the first maximum PCT of the fuel which depends on 54 input parameters. This application outlined that the methodology could be applied to high-dimensional complex problems.

Download Full-text

A Model on the Correlation between Composition and Mechanical Properties of Mg-Al-Zn Alloys by Using Artificial Neural Network

Materials Science Forum ◽

10.4028/www.scientific.net/msf.488-489.793 ◽

2005 ◽

Vol 488-489 ◽

pp. 793-796 ◽

Cited By ~ 1

Author(s):

Hai Ding Liu ◽

Ai Tao Tang ◽

Fu Sheng Pan ◽

Ru Lin Zuo ◽

Ling Yun Wang

Keyword(s):

Neural Network ◽

Mechanical Properties ◽

Artificial Neural Network ◽

Magnesium Alloys ◽

Tensile Yield Strength ◽

Data Set ◽

The Neural Network ◽

Artificial Neural ◽

Prediction Of Mechanical Properties ◽

Artificial Neural Network Ann

A model was developed for the analysis and prediction of correlation between composition and mechanical properties of Mg-Al-Zn (AZ) magnesium alloys by applying artificial neural network (ANN). The input parameters of the neural network (NN) are alloy composition. The outputs of the NN model are important mechanical properties, including ultimate tensile strength, tensile yield strength and elongation. The model is based on multilayer feedforward neural network. The NN was trained with comprehensive data set collected from domestic and foreign literature. A very good performance of the neural network was achieved. The model can be used for the simulation and prediction of mechanical properties of AZ system magnesium alloys as functions of composition.

Download Full-text

Neural Networks Applied to Estimating Subglacial Topography and Glacier Volume

Journal of Climate ◽

10.1175/2008jcli2572.1 ◽

2009 ◽

Vol 22 (8) ◽

pp. 2146-2160 ◽

Cited By ~ 48

Author(s):

Garry K. C. Clarke ◽

Etienne Berthier ◽

Christian G. Schoof ◽

Alexander H. Jarosch

Keyword(s):

Neural Network ◽

Regional Scale ◽

Ice Thickness ◽

Ice Dynamics ◽

Ice Caps ◽

Mountain Glaciers ◽

The Neural Network ◽

Glacier Ice ◽

Subglacial Topography ◽

Artificial Neural Network Ann

Abstract To predict the rate and consequences of shrinkage of the earth’s mountain glaciers and ice caps, it is necessary to have improved regional-scale models of mountain glaciation and better knowledge of the subglacial topography upon which these models must operate. The problem of estimating glacier ice thickness is addressed by developing an artificial neural network (ANN) approach that uses calculations performed on a digital elevation model (DEM) and on a mask of the present-day ice cover. Because suitable data from real glaciers are lacking, the ANN is trained by substituting the known topography of ice-denuded regions adjacent to the ice-covered regions of interest, and this known topography is hidden by imagining it to be ice-covered. For this training it is assumed that the topography is flooded to various levels by horizontal lake-like glaciers. The validity of this assumption and the estimation skill of the trained ANN is tested by predicting ice thickness for four 50 km × 50 km regions that are currently ice free but that have been partially glaciated using a numerical ice dynamics model. In this manner, predictions of ice thickness based on the neural network can be compared to the modeled ice thickness and the performance of the neural network can be evaluated and improved. From the results, thus far, it is found that ANN depth estimates can yield plausible subglacial topography with a representative rms elevation error of ±70 m and remarkably good estimates of ice volume.

Download Full-text

Prediction Model of Iron Ore Pellet Ambient Strength and Sensitivity Analysis on the Influence Factors

Metals ◽

10.3390/met8080593 ◽

2018 ◽

Vol 8 (8) ◽

pp. 593 ◽

Cited By ~ 1

Author(s):

Qiangjian Gao ◽

Yingyi Zhang ◽

Xin Jiang ◽

Haiyan Zheng ◽

Fengman Shen

Keyword(s):

Neural Network ◽

Sensitivity Analysis ◽

Prediction Model ◽

Bp Neural Network ◽

Back Propagation ◽

Influence Factors ◽

Principal Component ◽

Bp Network ◽

Input Variables ◽

Artificial Neural Network Ann

The Ambient Compressive Strength (CS) of pellets, influenced by several factors, is regarded as a criterion to assess pellets during metallurgical processes. A prediction model based on Artificial Neural Network (ANN) was proposed in order to provide a reliable and economic control strategy for CS in pellet production and to forecast and control pellet CS. The dimensionality of 19 influence factors of CS was considered and reduced by Principal Component Analysis (PCA). The PCA variables were then used as the input variables for the Back Propagation (BP) neural network, which was upgraded by Genetic Algorithm (GA), with CS as the output variable. After training and testing with production data, the PCA-GA-BP neural network was established. Additionally, the sensitivity analysis of input variables was calculated to obtain a detailed influence on pellet CS. It has been found that prediction accuracy of the PCA-GA-BP network mentioned here is 96.4%, indicating that the ANN network is effective to predict CS in the pelletizing process.

Download Full-text

Comprehensive global sensitivity analysis of a repository model using different types of transformations and metamodeling techniques

10.5194/egusphere-egu21-6131 ◽

2021 ◽

Author(s):

Sabine M. Spiessl ◽

Dirk-A. Becker ◽

Sergei Kucherenko

Keyword(s):

Sensitivity Analysis ◽

Global Sensitivity Analysis ◽

Higher Order ◽

Model Parameters ◽

High Dimensional Model Representation ◽

Model Output ◽

Global Sensitivity ◽

Sparse Polynomial ◽

Sensitivity Indices ◽

Highly Nonlinear

Due to their highly nonlinear, non-monotonic or even discontinuous behavior, sensitivity analysis of final repository models can be a demanding task. Most of the output of repository models is typically distributed over several orders of magnitude and highly skewed. Many values of a probabilistic investigation are very low or even zero. Although this is desirable in view of repository safety it can distort the evidence of sensitivity analysis. For the safety assessment of the system, the highest values of outputs are mainly essential and if those are only a few, their dependence on specific parameters may appear insignificant. By applying a transformation, different model output values are differently weighed, according to their magnitude, in sensitivity analysis. Probabilistic methods of higher-order sensitivity analysis, applied on appropriately transformed model output values, provide a possibility for more robust identification of relevant parameters and their interactions. This type of sensitivity analysis is typically done by decomposing the total unconditional variance of the model output into partial variances corresponding to different terms in the ANOVA decomposition. From this, sensitivity indices of increasing order can be computed. The key indices used most often are the first-order index (SI1) and the total-order index (SIT). SI1 refers to the individual impact of one parameter on the model and SIT represents the total effect of one parameter on the output in interactions with all other parameters. The second-order sensitivity indices (SI2) describe the interactions between two model parameters.In this work global sensitivity analysis has been performed with three different kinds of output transformations (log, shifted and Box-Cox transformation) and two metamodeling approaches, namely the Random-Sampling High Dimensional Model Representation (RS-HDMR) [1] and the Bayesian Sparse PCE (BSPCE) [2] approaches. Both approaches are implemented in the SobolGSA software [3, 4] which was used in this work. We analyzed the time-dependent output with two approaches for sensitivity analysis, i.e., the pointwise and generalized approaches. With the pointwise approach, the output at each time step is analyzed independently. The generalized approach considers averaged output contributions at all previous time steps in the analysis of the current step. Obtained results indicate that robustness can be improved by using appropriate transformations and choice of coefficients for the transformation and the metamodel.[1] M. Zuniga, S. Kucherenko, N. Shah (2013). Metamodelling with independent and dependent inputs. Computer Physics Communications, 184 (6): 1570-1580.[2] Q. Shao, A. Younes, M. Fahs, T.A. Mara (2017). Bayesian sparse polynomial chaos expansion for global sensitivity analysis. Computer Methods in Applied Mechanics and Engineering, 318: 474-496.[3] S. M. Spiessl, S. Kucherenko, D.-A. Becker, O. Zaccheus (2018). Higher-order sensitivity analysis of a final repository model with discontinuous behaviour. Reliability Engineering and System Safety, doi: https://doi.org/10.1016/j.ress.2018.12.004.[4] SobolGSA software (2021). User manual https://www.imperial.ac.uk/process-systems-engineering/research/free-software/sobolgsa-software/.

Download Full-text

Artificial Neural Networks and Learning Techniques

Psychology and Mental Health ◽

10.4018/978-1-5225-0159-6.ch004 ◽

2016 ◽

pp. 89-112

Author(s):

Pushpendu Kar ◽

Anusua Das

Keyword(s):

Neural Network ◽

Neural Networks ◽

Artificial Neural Networks ◽

Research Work ◽

The Neural Network ◽

Learning Techniques ◽

Learning Procedure ◽

Processing Component ◽

Artificial Neural ◽

Artificial Neural Network Ann

The recent craze for artificial neural networks has spread its roots towards the development of neuroscience, pattern recognition, machine learning and artificial intelligence. The theoretical neuroscience is basically converging towards the basic concept that the brain acts as a complex and decentralized computer which can perform rigorous calculations in a different approach compared to the conventional digital computers. The motivation behind the study of neural networks is due to their similarity in the structure of the human central nervous system. The elementary processing component of an Artificial Neural Network (ANN) is called as ‘Neuron'. A large number of neurons interconnected with each other mimic the biological neural network and form an ANN. Learning is an inevitable process that can be used to train an ANN. We can only transfer knowledge to the neural network by the learning procedure. This chapter presents the detailed concepts of artificial neural networks in addition to some significant aspects on the present research work.

Download Full-text

ANN-Based Wheat Chlorophyll Density Estimation Using Canopy Hyperspectral Vegetation Indices

Key Engineering Materials ◽

10.4028/www.scientific.net/kem.500.243 ◽

2012 ◽

Vol 500 ◽

pp. 243-249

Author(s):

Da Cheng Wang ◽

Luo Rui Sen ◽

Ji Hua Wang ◽

Cun Jun Li ◽

Dong Yan Zhang ◽

...

Keyword(s):

Neural Network ◽

Statistical Method ◽

Prediction Models ◽

Vegetation Indices ◽

Remote Sensing Data ◽

Leaf Chlorophyll ◽

The Neural Network ◽

Spectral Vegetation Indices ◽

Artificial Neural Network Ann ◽

Traditional Statistical Method

Canopy leaf Chlorophyll Density is a key index for evaluating crop potential photosynthetic efficiency and nutritional stress. Leaf Chlorophyll Density estimate using canopy hyperspectral vegetation indices provides a rapid and non-destructive method to evaluate yield predictions. A systematic comparison of two approaches to estimate Chlorophyll Density using 6 spectral vegetation indices (VIs) was presented in this study. In this study, the traditional statistical method based on power regression analyses was compared to the emerging computationally powerful techniques based on artificial neural network (ANN). The regression models of TCARI 、SAVI 、MSAVI and RDVIgreen were found to be more suitable for predicting Chlorophyll Density when only traditional statistical method was used especially TCARI and RDVI. ANN method was more appropriate to develop prediction models. The comparisons between these two methods were based on analysis of the statistic parameters. Results obtained using Root Mean Square Error (RMSE) for ANNs were significantly lower than the traditional method. From this analysis it is concluded that the neural network is more robust to train and estimate crop Chlorophyll Density from remote sensing data.

Download Full-text

Research of Intelligent Substation Condition Monitoring Based on the Neural Network

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.325-326.692 ◽

2013 ◽

Vol 325-326 ◽

pp. 692-696

Author(s):

Da Peng Chai ◽

Qiang Qiang Xue ◽

Ling Mei Wang ◽

Xing Yong Zhao

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Fault Diagnosis ◽

Electric Power ◽

Monitoring System ◽

Condition Monitoring ◽

Power Equipment ◽

The Neural Network ◽

Condition Monitoring System ◽

Artificial Neural Network Ann

The substation electric power equipment condition monitoring is the basis of intelligent substation. This paper analyzes the composition of the substation electric power equipment condition monitoring system and monitoring parameters, and with the transformer condition monitoring as an example, this paper proposes fault diagnosis methods of electric power equipment using artificial neural network(ANN).

Download Full-text

Sensitivity analysis and the challenges posed by multiple approaches: a multifaceted mess

10.5194/egusphere-egu2020-6626 ◽

2020 ◽

Author(s):

Monica Riva ◽

Aronne Dell'Oca ◽

Alberto Guadagnini

Keyword(s):

Sensitivity Analysis ◽

Model Calibration ◽

Global Sensitivity Analysis ◽

System Model ◽

Model Parameters ◽

Model Output ◽

Multiple Model ◽

Total Uncertainty ◽

Global Sensitivity ◽

Sensitivity Indices

Modern models of environmental and industrial systems have reached a relatively high level of complexity. The latter aspect could hamper an unambiguous understanding of the functioning of a model, i.e., how it drives relationships and dependencies among inputs and outputs of interest. Sensitivity Analysis tools can be employed to examine this issue.Global sensitivity analysis (GSA) approaches rest on the evaluation of sensitivity across the entire support within which system model parameters are supposed to vary. In this broad context, it is important to note that the definition of a sensitivity metric must be linked to the nature of the question(s) the GSA is meant to address. These include, for example: (i) which are the most important model parameters with respect to given model output(s)?; (ii) could we set some parameter(s) (thus assisting model calibration) at prescribed value(s) without significantly affecting model results?; (iii) at which space/time locations can one expect the highest sensitivity of model output(s) to model parameters and/or knowledge of which parameter(s) could be most beneficial for model calibration?The variance-based Sobol&#8217; Indices (e.g., Sobol, 2001) represent one of the most widespread GSA metrics, quantifying the average reduction in the variance of a model output stemming from knowledge of the input. Amongst other techniques, Dell&#8217;Oca et al. [2017] proposed a moment-based GSA approach which enables one to quantify the influence of uncertain model parameters on the (statistical) moments of a target model output.Here, we embed in these sensitivity indices the effect of uncertainties both in the system model conceptualization and in the ensuing model(s) parameters. The study is grounded on the observation that physical processes and natural systems within which they take place are complex, rendering target state variables amenable to multiple interpretations and mathematical descriptions. As such, predictions and uncertainty analyses based on a single model formulation can result in statistical bias and possible misrepresentation of the total uncertainty, thus justifying the assessment of multiple model system conceptualizations. We then introduce copula-based sensitivity metrics which allow characterizing the global (with respect to the input) value of the sensitivity and the degree of variability (across the whole range of the input values) of the sensitivity for each value that the prescribed model output can possibly undertake, as driven by a governing model. In this sense, such an approach to sensitivity is global with respect to model input(s) and local with respect to model output, thus enabling one to discriminate the relevance of an input across the entire range of values of the modeling goal of interest. The methodology is demonstrated in the context of flow and reactive transport scenarios.&#160;ReferencesSobol, I. M., 2001. Global sensitivity indices for nonlinear mathematical models and their Monte Carlo estimates. Math. Comput. Sim., 55, 271-280.Dell&#8217;Oca, A., Riva, M., Guadagnini, A., 2017. Moment-based metrics for global sensitivity analysis of hydrological systems. Hydr. Earth Syst. Sci., 21, 6219-6234.

Download Full-text