Wavelet based relevance vector machine model for monthly runoff prediction

2018 ◽  
Vol 54 (2) ◽  
pp. 134-141 ◽  
Author(s):  
Fang Ruiming
Keyword(s):  
Historical Data ◽  
Relevance Vector Machine ◽  
Machine Model ◽  
Inverse Transform ◽  
Minjiang River ◽  
Proposed Model ◽  
Runoff Prediction ◽  
Variation Characteristics ◽  
Predicted Values ◽  
Monthly Runoff

Abstract In this study, wavelet transform (WT) and a relevance vector machine (RVM) are integrated to predict monthly runoff. First, the WT method is adopted to decompose the monthly runoff time series into subsequences of different scales, and the variation characteristics, especially the periodicity of the runoff, are analyzed. Then, the regression model of RVM is established in each subsequence. Finally, the prediction results of each subsequence are integrated to obtain the final predicted values of monthly runoff through wavelet inverse transform. The proposed model was tested using the historical data of Minjiang River; the results show that compared with the RVM model, the WT-RVM model has better precision and can be applied in the prediction of monthly runoff.

scholarly journals A Compound Approach for Monthly Runoff Forecasting Based on Multiscale Analysis and Deep Network with Sequential Structure

Water ◽  
2020 ◽  
Vol 12 (8) ◽  
pp. 2274 ◽  
Author(s):  
Shi Chen ◽  
Shuning Dong ◽  
Zhiguo Cao ◽  
Junting Guo
Keyword(s):  
Water Resource Management ◽  
Sequential Structure ◽  
Runoff Forecasting ◽  
Mode Decomposition ◽  
Proposed Model ◽  
Runoff Series ◽  
Efficiency And Effectiveness ◽  
Predicted Values ◽  
Monthly Runoff ◽  
Gated Recurrent Unit

Accurate runoff forecasting is of great significance for the optimization of water resource management and regulation. Given such a challenge, a novel compound approach combining time-varying filtering-based empirical mode decomposition (TVFEMD), sample entropy (SE)-based subseries recombination, and the newly developed deep sequential structure incorporating convolutional neural network (CNN) into a gated recurrent unit network (GRU) is proposed for monthly runoff forecasting. Firstly, the runoff series is disintegrated into a collection of subseries adopting TVFEMD, considering the volatility of runoff series caused by complex environmental and human factors. The subseries recombination strategy based on SE and recombination criterion is employed to reconstruct the subseries possessing the approximate complexity. Subsequently, the newly developed deep sequential structure based on CNN and GRU (CNNGRU) is applied to predict all the preprocessed subseries. Eventually, the predicted values obtained above are aggregated to deduce the ultimate prediction results. To testify to the efficiency and effectiveness of the proposed approach, eight relevant contrastive models were applied to the monthly runoff series collected from Baishan reservoir, where the experimental results demonstrated that the evaluation metrics obtained by the proposed model achieved an average index decrease of 44.35% compared with all the contrast models.

Estimation of CO2 Diffusivity in Brine by Use of the Genetic Algorithm and Mixed Kernels-Based Support Vector Machine Model

2018 ◽  
Vol 141 (4) ◽  
Author(s):  
Qihong Feng ◽  
Ronghao Cui ◽  
Sen Wang ◽  
Jin Zhang ◽  
Zhe Jiang
Keyword(s):  
Genetic Algorithm ◽  
Support Vector Machine ◽  
Diffusion Coefficient ◽  
Co2 Storage ◽  
Co2 Injection ◽  
Support Vector ◽  
Hybrid Technique ◽  
Machine Model ◽  
Proposed Model ◽  
Wide Range

Diffusion coefficient of carbon dioxide (CO2), a significant parameter describing the mass transfer process, exerts a profound influence on the safety of CO2 storage in depleted reservoirs, saline aquifers, and marine ecosystems. However, experimental determination of diffusion coefficient in CO2-brine system is time-consuming and complex because the procedure requires sophisticated laboratory equipment and reasonable interpretation methods. To facilitate the acquisition of more accurate values, an intelligent model, termed MKSVM-GA, is developed using a hybrid technique of support vector machine (SVM), mixed kernels (MK), and genetic algorithm (GA). Confirmed by the statistical evaluation indicators, our proposed model exhibits excellent performance with high accuracy and strong robustness in a wide range of temperatures (273–473.15 K), pressures (0.1–49.3 MPa), and viscosities (0.139–1.950 mPa·s). Our results show that the proposed model is more applicable than the artificial neural network (ANN) model at this sample size, which is superior to four commonly used traditional empirical correlations. The technique presented in this study can provide a fast and precise prediction of CO2 diffusivity in brine at reservoir conditions for the engineering design and the technical risk assessment during the process of CO2 injection.

Assessment of the Efficiency of Aliquat 336+Rice Bran Oil for Separation of Acrylic Acid from Aqueous Solution Using Reactive Extraction

2018 ◽  
Vol 16 (9) ◽  
Author(s):  
Himangshu Mondal ◽  
Kanti Kumar Athankar ◽  
Kailas L. Wasewar
Keyword(s):  
Acrylic Acid ◽  
Rice Bran ◽  
Renewable Resources ◽  
Extraction Efficiency ◽  
Process Development ◽  
Rice Bran Oil ◽  
Reactive Extraction ◽  
Aliquat 336 ◽  
Proposed Model ◽  
Predicted Values

Abstract Biomass is an attractive target in process development for the emerging renewable resources based bio-refinery industry. Due to the ample range of application of acrylic acid, its production through bio-route received more awareness in scientific fraternity. In this view, an attempted was made to study the reactive extraction of acrylic acid with aliquat 336 in rice bran oil. Moreover, Box-Behnken matrix was employed to corroborate the effects of process variables viz. concentration of acrylic acid [CAA]aq, concentration of aliquat 336 [CR4N+Cl], and temperature on the extraction efficiency (η%). In physical extraction, average extraction efficiency was found in the order as: 43.55 > 35.36 > 29.14 at 303 K, 323 K, and 343 K respectively in rice bran oil. The correlation coefficient, R2 = 0.988 % indicates the appropriateness of proposed model to predict the extraction efficiency in terms of independent variables, and the predicted values were found in close agreement with that of experimental results. Further, R2(Pred) = 0.806 is in reasonable agreement with the R2(Adj) = 0.972. The optimum conditions for extraction of acrylic acid using aliquat 336 as an extractant in rice bran oil are [CAA]aq = 0.0.5 (mol/kg); [CR4N+Cl] = 1.98 (mol/kg); temperature = 323 K and the model predicted extraction efficiency 77.5 % was found to be an excellent fit with the experimental value 75 %. Further, number of theoretical stages was found to be 3 and S/F ratio 0.247.

Prediction of Design Hourly Volume on Rural Roads

2020 ◽  
pp. 036119812096556
Author(s):  
Miloš Petković ◽  
Vladan Tubić ◽  
Nemanja Stepanović
Keyword(s):  
Coefficient Of Determination ◽  
Rural Roads ◽  
The Road ◽  
Annual Average Daily Traffic ◽  
Proposed Model ◽  
Traffic Volumes ◽  
Implementation Costs ◽  
On The Road ◽  
Predicted Values ◽  
Design Hourly Volume

Design hourly volume (DHV) represents one of the most significant parameters in the procedures of developing and evaluating road designs. DHV values can be accurately and precisely calculated only on the road sections with the implemented automatic traffic counters (ATCs) which constantly monitor the traffic volume. Unfortunately, many road sections do not contain ATCs primarily because of the implementation costs. Consequently, for many years, the DHV values have been defined on the basis of occasional counting and the factors related to traffic flow variability over time. However, it has been determined that this approach has significant limitations and that the predicted values considerably deviate from the actual values. Therefore, the main objective of this paper is to develop a model which will enable DHV prediction on rural roads in cases of insufficient data. The suggested model is based on the correlation between DHVs and the parameters defining the characteristics of traffic flows, that is, the relationship between the traffic volumes on design working days and non-working days, and annual average daily traffic. The results of the conducted research indicate that the application of the proposed model enables the prediction of DHV values with a significant level of data accuracy and reliability. The coefficient of determination (R2) shows that more than 98% of the variance of the calculated DHVs was explained by the observed DHV values, while the mean error ranged from 4.86% to 7.84% depending on the number of hours for which DHV was predicted.

Determination of Recrystallization Kinetics Model of 30Cr2Ni4MoV Steel Based on Dislocation Density

2017 ◽  
Vol 263 ◽  
pp. 59-66
Author(s):  
Peng Zhou ◽  
Qing Xian Ma
Keyword(s):  
Dislocation Density ◽  
Model Comparison ◽  
Kinetics Model ◽  
Structure Evolution ◽  
Metallographic Analysis ◽  
Recrystallization Kinetics ◽  
Proposed Model ◽  
Different Temperatures ◽  
Predicted Values ◽  
Experimental Values

A new model to predict the structure evolution of 30Cr2Ni4MoV steel is proposed based on the dislocation density in this research. Hot compression of 30Cr2Ni4MoV steel is carried out on Gleeble 1500 at different temperatures from 1233 K to 1473 K with a strain rate of 0.01 s-1 and the deformed samples are immediately quenched by water to frozen the austenite structure. The recrystallization kinetics model of 30Cr2Ni4MoV steel is successfully established by inverse analysis of the flow curve based on the relation between flow stress and dislocation density. In order to validate the proposed model, comparison between the predicted values and experimental values obtained by metallographic analysis is implemented. It is shown that the predicted results agree with the experimental results well.

scholarly journals An Ensemble Hybrid forecasting Model for Annual Runoff Based on Sample Entropy, Secondary Decomposition, and Long Short-Term Memory Neural Network

2021 ◽  
Author(s):  
Wenchuan Wang ◽  
Yu-jin Du ◽  
Kwok-wing Chau ◽  
Dong-mei Xu ◽  
Chang-jun Liu ◽  
...  
Keyword(s):  
Water Resources ◽  
Short Term Memory ◽  
Learning Algorithm ◽  
Sample Entropy ◽  
Annual Runoff ◽  
Intrinsic Mode Functions ◽  
Proposed Model ◽  
Runoff Series ◽  
Runoff Prediction ◽  
Quantitative Indexes

Abstract Accurate and consistent annual runoff prediction in regions is a hot topic in the management, optimization, and monitoring of water resources. A novel prediction model (ESMD-SE-WPD-LSTM) is presented in this study. Firstly, the extreme-point symmetric mode decomposition (ESMD) is used to produce several intrinsic mode functions (IMF) and a residual (Res) by decomposing the original runoff series. Secondly, the sample entropy (SE) method is employed to measure the complexity of each IMF. Thirdly, we adopt wavelet packet decomposition (WPD) to further decompose the IMF with the maximum SE into several appropriate components and detailed components. Then the LSTM model, a deep learning algorithm based recurrent approach, is employed to predict all components obtained in the previous step. Finally, the forecasting results of all components are aggregated to generate the final prediction. The proposed model, which is applied to five annual series from different areas in China, is evaluated based on four quantitative indexes (R, NSEC, MAPE and RMSE). The results indicate that the ESMD-SE-WPD-LSTM outperforms other benchmark models in terms of four quantitative indexes. Hence the proposed model can provide higher accuracy and consistency for annual runoff prediction, making it an efficient instrument for scientific management and planning of water resources.

scholarly journals Using Markov Chains to Predict Productivity of Maize in Iraq for the Period (2019-2025)

2021 ◽  
Vol 8 (5) ◽  
pp. 1
Author(s):  
L.A.F. Al-Ani ◽  
A.D.K. Alhiyali
Keyword(s):  
Markov Chains ◽  
Historical Data ◽  
Unit Area ◽  
Recent Past ◽  
Predictive Values ◽  
The Third ◽  
Predictive Methods ◽  
Horizontal Expansion ◽  
Predicted Values ◽  
The Impact

The research aims to predict the productivity of one of the most important major crops in Iraq, which is Maize, using Markov chains, which is one of the most important predictive methods that depend on relatively recent historical data and based mainly on previous data that is not far away. This is the advantage that Markov chains have, as relying on somewhat old historical data may negatively affect the predicted values. The results of the research showed the superiority of the third state to predict the productivity of Maize depending on the availability of Markov chains prediction conditions for this state. The results of the research also showed the continued decline in productivity for the coming years, as well as the impact of the predictive values on changes in the cultivated area more than changes in production, which confirms the existence of horizontal expansion at the expense of vertical expansion, that is, there is no intensification of production per unit area. The research also found that the actual values of productivity have approached the estimated values of the following years, and the matter applies to the convergence of these results for the subsequent years with the previous years, which confirms the accuracy of the method of Markov chains, in other words that what happened in the recent past had a clear impact in the future near.

scholarly journals A New Multiparameter Model for Multiaxial Fatigue Life Prediction of Rubber Materials

Polymers ◽  
2020 ◽  
Vol 12 (5) ◽  
pp. 1194
Author(s):  
Rafael Tobajas ◽  
Daniel Elduque ◽  
Elena Ibarz ◽  
Carlos Javierre ◽  
Luis Gracia
Keyword(s):  
Fatigue Life ◽  
Life Prediction ◽  
Experimental Testing ◽  
Experimental Tests ◽  
Relevant Information ◽  
Fatigue Tests ◽  
Multiaxial Fatigue ◽  
Fatigue Life Prediction ◽  
Proposed Model ◽  
Predicted Values

Most of the mechanical components manufactured in rubber materials experience fluctuating loads, which cause material fatigue, significantly reducing their life. Different models have been used to approach this problem. However, most of them just provide life prediction only valid for each of the specific studied material and type of specimen used for the experimental testing. This work focuses on the development of a new generalized model of multiaxial fatigue for rubber materials, introducing a multiparameter variable to improve fatigue life prediction by considering simultaneously relevant information concerning stresses, strains, and strain energies. The model is verified through its correlation with several published fatigue tests for different rubber materials. The proposed model has been compared with more than 20 different parameters used in the specialized literature, calculating the value of the R2 coefficient by comparing the predicted values of every model, with the experimental ones. The obtained results show a significant improvement in the fatigue life prediction. The proposed model does not aim to be a universal and definitive approach for elastomer fatigue, but it provides a reliable general tool that can be used for processing data obtained from experimental tests carried out under different conditions.

Sign in / Sign up

Export Citation Format

Share Document