Prediction of peak ground acceleration of Iran's tectonic regions using a hybrid soft computing technique

Gandomi, Mostafa; Soltanpour, Mohsen; Zolfaghari, Mohammad Reza; Gandomi, Amir H.

doi:10.1016/j.gsf.2014.10.004

Cited by 41 publications

(15 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The performance of the RVM, ELM and the MARS models were assessed in terms of their coefficient of correlation (R), root-MEAN-SQUARE-ERROR (RMSE), mean absolute error (MAE) and the Performance Index (q). The equations for the determination of R, RMSE, MAE and q (Gandomi et al 2014) were as follows:…”

Section: Basis Function [B M (X)] Coefficient (C M )mentioning

confidence: 99%

“…As described in previous studies (e.g. (Goyal et al 2014;Kişi 2006;Pandey and Pandey 2013), the evaporative loss (E) was our target (objective) variable. The predictor datasets used were randomly sampled to generate two different subsets, viz for the training (70 %) and testing (30 %) phases.…”

Section: Introductionmentioning

confidence: 99%

“…It arguably correct that process-driven models require large number of predictor datasets that are not easily available in topographically diverse terrains, the parameters of such models need calibration based on field observations and further fine-tuning is required to downscale the outputs of Global Climate Models to local-scales processes especially in practical decision-support Goyal et al 2014). However, data-based models that utilize machine learning algorithms as an alternative tool for prediction of E offer more promising solutions.…”

Section: Introductionmentioning

confidence: 99%

“…(Deo and Ş ahin 2015a, b;Ş ahin 2012;Ş ahin et al 2014;Tiwari and Adamowski 2013)). Traditional models based on multilinear regression (MLR) and auto-regressive integrand moving average (ARMA) frameworks are common (Adamowski 2008;Goyal et al 2014;Raman and Sunilkumar 1995;Young 1999). However, the MLR and ARIMA models have significant drawbacks as both assume linear dependence of the objective variable on predictor data which is not always true in hydrological time-series involving rainfall and evaporation.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Estimation of monthly evaporative loss using relevance vector machine, extreme learning machine and multivariate adaptive regression spline models

Deo

Samui

Kim

2015

Stoch Environ Res Risk Assess

122

View full text Add to dashboard Cite

The forecasting of evaporative loss (E) is vital for water resource management and understanding of hydrological process for farming practices, ecosystem management and hydrologic engineering. This study has developed three machine learning algorithms, namely the relevance vector machine (RVM), extreme learning machine (ELM) and multivariate adaptive regression spline (MARS) for the prediction of E using five predictor variables, incident solar radiation (S), maximum temperature (T max ), minimum temperature (T min ), atmospheric vapor pressure (VP) and precipitation (P). The RVM model is based on the Bayesian formulation of a linear model with appropriate prior that results in sparse representations. The ELM model is computationally efficient algorithm based on Single Layer Feedforward Neural Network with hidden neurons that randomly choose input weights and the MARS model is built on flexible regression algorithm that generally divides solution space into intervals of predictor variables and fits splines (basis functions) to each interval. By utilizing random sampling process, the predictor data were partitioned into the training phase (70 % of data) and testing phase (remainder 30 %). The equations for the prediction of monthly E were formulated. The RVM model was devised using the radial basis function, while the ELM model comprised of 5 inputs and 10 hidden neurons and used the radial basis activation function, and the MARS model utilized 15 basis functions. The decomposition of variance among the predictor dataset of the MARS model yielded the largest magnitude of the Generalized Cross Validation statistic (&0.03) when the T max was used as an input, followed by the relatively lower value (&0.028, 0.019) for inputs defined by the S and VP. This confirmed that the prediction of E utilized the largest contributions of the predictive features from the T max , verified emphatically by sensitivity analysis test. The model performance statistics yielded correlation coefficients of 0.979 (RVM), 0.977 (ELM) and 0.974 (MARS), Root-Mean-Square-Errors of 9.306, 9.714 and 10.457 and Mean-Absolute-Error of 0.034, 0.035 and 0.038. Despite the small differences in the overall prediction skill, the RVM model appeared to be more accurate in prediction of E. It is therefore advocated that the RVM model can be employed as a promising machine learning tool for the prediction of evaporative loss.

show abstract

Section: Basis Function [B M (X)] Coefficient (C M )mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Estimation of monthly evaporative loss using relevance vector machine, extreme learning machine and multivariate adaptive regression spline models

Deo

Samui

Kim

2015

Stoch Environ Res Risk Assess

122

View full text Add to dashboard Cite

show abstract

“…These range from the Genetic Algorithm, to the Evolutionary Algorithms and end with the swarm optimization procedures. An interesting example of the use of the heuristic method for learning ANN, is the procedure for the prediction of peak ground acceleration that is described in [11]. In this work, the authors applied a well-known derivatively-free global optimisation algorithm (based on a simulated annealing metaheuristic) so as to improve the neural networks efficiency.…”

Section: Introductionmentioning

confidence: 99%

Training Neural Networks with Krill Herd Algorithm

Kowalski

źUkasik

2015

Neural Process Lett

View full text Add to dashboard Cite

In recent times, several new metaheuristic algorithms based on natural phenomena have been made available to researchers. One of these is that of the Krill Herd Algorithm (KHA) procedure. It contains many interesting mechanisms. The purpose of this article is to compare the KHA optimization algorithm used for learning an artificial neural network (ANN), with other heuristic methods and with more conventional procedures. The proposed ANN training method has been verified for the classification task. For that purpose benchmark examples drawn from the UCI Machine Learning Repository were employed with Classification Error and Sum of Square Errors being used as evaluation criteria. It has been concluded that the application of KHA offers promising performance-both in terms of aforementioned metrics, as well as time needed for ANN training.

show abstract

Classification Methods and Its Applications in Infrastructure Management

2022

Automation and Computational Intelligence for Road Maintenance and Management

View full text Add to dashboard Cite

Prediction of peak ground acceleration of Iran's tectonic regions using a hybrid soft computing technique

Cited by 41 publications

References 34 publications

Estimation of monthly evaporative loss using relevance vector machine, extreme learning machine and multivariate adaptive regression spline models

Estimation of monthly evaporative loss using relevance vector machine, extreme learning machine and multivariate adaptive regression spline models

Training Neural Networks with Krill Herd Algorithm

Classification Methods and Its Applications in Infrastructure Management

Contact Info

Product

Resources

About