Browsing by Author "Noori, Roohollah"

Now showing 1 - 2 of 2

A reduced-order based CE-QUAL-W2 model for simulation of nitrate concentration in dam reservoirs
(2015-11-01)
Noori, Roohollah
;
Yeh, Hund-Der
;
Ashrafi, Khosro
;
Rezazadeh, Najmeh
;
Bateni, Sayed M.
When the number of computational grids increases, water quality simulation complexities arise. Therefore, using a reduced order framework to express the variations of the objective parameter may facilitate the simulation task and also the interpretation of computational results. In this regard, a new reduced-order approach was proposed to link a water quality simulator model (CE-QUAL-W2, W2) with a data reduction technique (proper orthogonal decomposition, POD). The W2 model simulated spatio-temporal variations of nitrate in the Karkheh Reservoir, Iran. Thereafter, the POD model reduced the dimensions of simulated nitrate in the computational grids. The performance of the developed reduced-order model (ROM) results was evaluated through the comparison of the regenerated nitrate data by the model, and the simulated ones by W2. Findings indicated that the first four modes among 1825 computed ones by ROM conserved approximately over 91% of the nitrate variations. It means that the ROM was capable of showing the spatio-temporal variations of nitrate in the reservoir using the first few modes. Finally, confirmation of ROM indicated that the error of order of magnitude was less than 0.001, for nitrate ROM to regenerate nitrate data using 100 basis functions. (C) 2015 Elsevier B.V. All rights reserved.
Uncertainty analysis of support vector machine for online prediction of five-day biochemical oxygen demand
(2015-08-01)
Noori, Roohollah
;
Yeh, Hund-Der
;
Abbasi, Maryam
;
Kachoosangi, Fatemeh Torabi
;
Moazami, Saber
Uncertainty is considered as one of the most important limitations for applying the results of artificial intelligence techniques (AI) in water quality management to obtain appropriate control strategies. In this research, a proper methodology was proposed to determine the uncertainty of support vector machine (SVM) for the prediction of five-day biochemical oxygen demand (BOD5). In this regard, the SVM model was calibrated using different records for many times (here, 1000 times), to investigate model performance according to calibration pattern changes. Therefore, to implement the random selection of calibration patterns for several times, an alternative database was required. By this methodology, the parameters of SVM model will be obtained 1000 times, giving various predicted BOD5 values each time. To evaluate the SVM model\'s uncertainty, the percentage of observed data bracketed by 95 percent predicted uncertainties (95PPU) and the band width of 95 percent confidence intervals (d-factor) were selected. Findings indicated that the SVM model was more sensitive to capacity parameter (C) than to kernel parameter (Gamma) and error tolerance (Epsilon). Besides, results showed that the SVM model had acceptable uncertainty in BOD5 prediction. It is notified that the novelty of the presented methodology is beyond a mere application to water resources, and can also be used in other fields of sciences and engineering. (C) 2015 Elsevier B.V. All rights reserved.