Search

‎This study suggests a novel approach for calibrating European option pricing model by a hybrid model based on the optimized artificial neural network and Black-Scholes model‎. ‎In this model‎, ‎the inputs of the artificial neural network are the Black-Scholes equations with different maturity dates and strike prices‎. ‎The presented calibration process involves training the neural network on historical option prices and adjusting its parameters using the Levenberg-Marquardt optimization algorithm‎. ‎The resulting hybrid model shows superior accuracy and efficiency in option pricing on both in sample and out of sample dataset‎.

A solar air heater (SAH) is a unique form of solar thermal collector that utilizes solar energy emitted from the sun to produce heated air. Various experimental and theoretical investigations have been undertaken to improve the poor thermal performance of SAHs. The difficulties related to these studies drew attention toward a reliable soft computing technique exemplified by the Artificial Neural Network (ANN) technique. The current work applied actual meteorological data from Miskolc City, Hungary, to an ANN model with the structure of a Multi-layer Perceptron (MLP) to forecast the energy performance of a V-corrugated solar-powered air heater. Seven input parameters and one output parameter make up the ANN structure, with a single hidden layer. For the purpose of selecting the most effective network for predicting output parameters, ten neurons have been assessed. The suggested ANN model was trained with 336 data sets using the Levenberg-Marquardt (LM) learning technique. The comparison of anticipated and real thermal performance values shows a very good agreement. The statistical error analysis showed that the optimal ANN model structure of 7-8-1 can reliably and accurately predict SAH's thermal performance and thus it can save both time and cost. [ABSTRACT FROM AUTHOR]

In this study, an artificial neural network (ANN) and an adaptive neuro-fuzzy inference system (ANFIS) were used to predict the adsorption potential of an adsorbent for the removal of chromium (VI) from an aqueous solution. Four operational variables were studied to assess their impact on the adsorption study in the ANFIS model: initial Ni (II) concentration (mg/L), pH, contact duration (min), and adsorbent dose (mg/L). To build the ANN model, 70% of the data was used for training and 15% for testing and validation. The network was trained using feedforward propagation and the Levenberg–Marquardt algorithm. The regression coefficients (R2) for the ANFIS and ANN models were 0.99 and 0.98, respectively. The results show good agreement between the model-predicted and experimental data, indicating that the models are appropriate and compatible. The RMSE between the predicted and observed removal percentage values for the ANFIS model was 0.008, whereas the RMSE for the ANN model was 0.06. The AARE values between the predicted and experimental removal percentage values for the ANFIS and ANN models were determined to be 0.009 and 0.045, respectively. The MSE vales between the predicted and experimental removal percentages for the ANFIS and ANN models were found to be 0.002 and 0.035, respectively. The optimum conditions were as follows: pH 6, an initial concentration of 275 mg/L, a contact time of 60 min, and a dosage of 12.5 mg/L; the absorption was 91.00%. [ABSTRACT FROM AUTHOR]

Active Banks in the recent economic environment are obliged to encounter in a massive gamut of risks which are closely following them. If cash is regarded as cash at hand, then Liquidity risk is a kind of loss which arises of lack of fund or more specifically endured loss originating from inability of funding required capital in a reasonable way or selling off assets or being forced to have them pledged in order to cover solicited or unsolicited commitments. Hence Liquidity risk is comprised of economic loss incurred due to of providing cash and is deemed vital for operational activities of enterprises. Liquidity Mismatch in banks or maturity mismatch of sensitive assets to cash or debt may culminate in divergent of cash inflow or outflow during elapse of time which is actually stressed as Liquidity risk. Quarterly performance of 23 quoted banks in either Tehran Stock Exchange or Iran Farabourse are executed to model forecasted Banks’ Liquidity risk by means of implementing Artificial Neural Network algorithms. Applying genetic algorithm and Levenberg algorithm helped utilizing the best Training method and subsequently by facilitating Principal Component Analysis (PCA) method, we managed to optimize independent variables. Finally having hidden layers been determined and exercising calculations by Bayesian network model, the Artificial neural network is modeled and tested. All the mentioned process is performed by MATLAB software. Eventually fulfilling the asserted stages, a robust model for anticipating listed banks’ Liquidity risk is developed and findings of models for forcasted data is elaborated.

Liquid-solid fluidization technique is being applied where low-grade coal or minerals enrichment is mostly density-based. Static and dynamic behavior of particles in a fluid medium has been extensively investigated over the years because of its dynamic applications across various industries. In this work, bed characterization studies and experiments have been conducted to study coal washing ability of the liquid-solid fluidized bed separator. Results have been recorded in terms of ash rejection%, combustible recovery% and separation efficiency%. Minimum fluidization velocity and pressure drop values have been predicted using existing theoretical correlations and compared with the experimental values. A three-layered (4:5:3) feedforward back-propagation (FFBP) neural network model was developed using Levenberg-Marquardt algorithm, LOGSIG and MSE as training, transfer and performance functions respectively. Garson's algorithm and connection weight approach have been employed for sensitivity analysis to interpret the neural network results physically. Coefficients of correlation, all R (including training, validation & testing datasets) obtained for outputs ash rejection (R = 0.9960), combustible recovery (R = 0.9952) and separation efficiency (R = 0.9944) suggest that predicted values are in agreement with the experimental values and the developed model is a good fit. [ABSTRACT FROM AUTHOR]

The purpose of this study is to investigate the computational fluid dynamics to find the effects of Reynolds number, different volume fractions of aluminum oxide nanofluid and different heat fluxes in heat transfer performance (Nusselt number) in a helical tube. This simulation was investigated at Reynolds number range 2000 and 10,000 and volumetric fraction range 1% and 4% of aluminum oxide nanofluid and constant heat fluxes of 4000–6000 W/m2. The single-phase model was used to model the nanofluid and the feasible k-ε model was used to simulate the turbulent flow. Then, perceptron artificial neural networks with the Levenberg–Marquardt algorithm were used to predict the Nusselt number such that input parameters include Reynolds number, nanoparticle volume fraction and output or target was considered Nusselt number for the network. The results show that with increasing the volume fraction of aluminum oxide nanofluid and Reynolds number, the Nusselt number increases by about 20.35%. Also, by increasing the constant heat flux from 4000–6000 W/m2, the Nusselt number increases by 18.75%. The results of the artificial neural network show that the topology 2-10-1 is very successful in predicting the Nusselt number so that the minimum mean squared error for the data allocated to the training and validation sections were 0.024449627 and 0.117025052, respectively, which are obtained under optimal epochs 19 and 9. The value of the correlation coefficient obtained in predicting the Nusselt number is 0.944416302. [ABSTRACT FROM AUTHOR]

In this study, an artificial neural network (ANN) and an adaptive neuro-fuzzy inference system (ANFIS) were used to predict the adsorption potential of an adsorbent for the removal of chromium (VI) from an aqueous solution. Four operational variables were studied to assess their impact on the adsorption study in the ANFIS model: initial Ni (II) concentration (mg/L), pH, contact duration (min), and adsorbent dose (mg/L). To build the ANN model, 70% of the data was used for training and 15% for testing and validation. The network was trained using feedforward propagation and the Levenberg–Marquardt algorithm. The regression coefficients (R2) for the ANFIS and ANN models were 0.99 and 0.98, respectively. The results show good agreement between the model-predicted and experimental data, indicating that the models are appropriate and compatible. The RMSE between the predicted and observed removal percentage values for the ANFIS model was 0.008, whereas the RMSE for the ANN model was 0.06. The AARE values between the predicted and experimental removal percentage values for the ANFIS and ANN models were determined to be 0.009 and 0.045, respectively. The MSE vales between the predicted and experimental removal percentages for the ANFIS and ANN models were found to be 0.002 and 0.035, respectively. The optimum conditions were as follows: pH 6, an initial concentration of 275 mg/L, a contact time of 60 min, and a dosage of 12.5 mg/L; the absorption was 91.00%.

The state of Uttarakhand has several prime population centers, and it is considered to be among the most seismically active regions of India. The article presents Artificial Neural Network-based prediction models using Multilayer Perceptron technique for the Himalayan earthquakes specifically for the region of Uttarakhand. Feed Forward Back Propagation Levenberg–Marquardt algorithm-based prediction models are developed for assessing the Peak Ground Acceleration (PGA) and Significant Duration (SD) with the availability of independent parameters such as moment magnitude (Mw), focal depth (F), epicentral distance (E), hypocentral distance (H), and site class (SC) considering either rock or soil site. Two PGA models were developed having high correlation (R) of 0.896 and 0.916 respectively whereas the developed SD model showed correlation value of 0.873. The higher accuracy of the models was ensured by objectivity function (OBJ) values of 0.011 and 0.006 for the two PGA models respectively and 3.6 for the SD model. The developed models are compared with available prediction equations, and it is inferred that the models yield higher accuracy in predicting the earthquake parameters for Uttarakhand state of India. However, it should be noted that the models are suitable for magnitudes (Mw) between 3.0 and 7.0 and for hypocentral distance between 9 and 254 km. [ABSTRACT FROM AUTHOR]

Since global solar radiation (GSR) is an important parameter for the design, installation, and operation of solar energy-based systems, it is important to have precise information about it. As the indicating devices are expensive and their requirements such as operation and maintenance should be carried out, the measurement of solar radiation cannot be frequently taken. On the other hand, the measurements of different meteorological parameters such as relative humidity and ground surface temperature are more prevalent in meteorology stations. Therefore, the estimation of solar radiation is a significant parameter for the areas where the measurements could not be performed and to complete the missing information in databases. Many different models, software, and simulation programs are utilized to calculate solar radiation data, provide an economic advantage, and obtain high accuracy. The main purpose of this study is to perform an estimation of solar radiation in Adana, where is on the east of the Mediterranean in Turkey, by using an artificial neural network (ANN) model. The best estimation performance is obtained by optimizing the neuron numbers used in the network's hidden layer with the trial and error method. With this aim, hourly data including wind speed, wind direction, humidity, actual pressure, and average temperature are taken as inputs while solar radiation is taken as a target. All these data, which is for 2018, has taken from the Turkish State Meteorological Service. A linear correlation coefficient value has been obtained to be about 0.87313 with the mean square error (MSE) of 5.8262x107 W/m2 for the testing data set. The ANN's testing/validation results show that it has a low MSE, indicating the accuracy and adequacy of the network model. Besides, the predicted ANN output is evaluated to be remarkably close to the measured target data by considering the linear correlation coefficient. [ABSTRACT FROM AUTHOR]

Objectives. Given the burgeoning impacts of climatic variability on human health, suitable computational paradigms are used to explore the subsequent ergonomic repercussions. The artificial neural network (ANN), in particular, exhibits near-accurate input–output mapping. However, employment of the ANN to trace the inter-dependencies between the climatic and human thermoregulatory parameters in real-world fuzzy problem landscapes is relatively inadequate. In the present study, the ANN models examined the relationships between climatic, behavioral and intrinsic input factors and the thermoregulatory outputs, namely, sweating and the evaporative heat transfer at the skin surface (Esk). Methods. The data were obtained from nearly 1800 subjects who were exposed to a hot and humid climate outdoors. The ANN models were trained using the Levenberg–Marquardt algorithm combined with Bayesian regularization. Results. The predictability of the ANN models was statistically substantiated. The clothing insulation factor was not included as an input parameter, given its similar values. Intriguingly, the ANN results indicated that fabrics with similar thermal resistances could still affect Esk, plausibly owing to the temporal variation in the evaporative resistance of fabrics among individuals. Conclusion. The reasonably accurate results affirmed the suitability of ANN as a pragmatic technique that could elucidate heat-induced ergonomic challenges. [ABSTRACT FROM AUTHOR]

The objectives of current investigation are (1) to find out wavelength of maximum absorbance (λmax) for combined cyclosporin A and etodolac solution followed by selection of mobile phase suitable for the RP-HPLC method, (2) to define analytical target profile and critical analytical attributes (CAAs) for the analytical quality by design, (3) to screen critical method parameters with the help of full factorial design followed by optimization with face-centered central composite design (CCD) approach-driven artificial neural network (ANN)-linked with the Levenberg–Marquardt (LM) algorithm for finding the RP-HPLC conditions, (4) to perform validation of analytical procedures (trueness, linearity, precision, robustness, specificity and sensitivity) using combined drug solution, and (5) to determine drug entrapment efficiency value in dual drug-loaded nanocapsules/emulsions, percentage recovery value in human plasma spiked with two drugs and solution state stability analysis at different stress conditions for substantiating the double-stage systematically optimized RP-HPLC method conditions. Through isobestic point and scouting step, 205 nm and ACN:H2O mixture (74:26) were selected respectively as the λmax and mobile phase. The ANN topology (3:10:4) indicating the input, hidden and output layers were generated by taking the 20 trials produced from the face-centered CCD model. The ANN-linked LM model produced minimal differences between predicted and observed values of output parameters (or CAAs), low mean squared error and higher correlation coefficient values in comparison to the respective values produced by face-centered CCD model. The optimized RP-HPLC method could be applied to analyze two drugs concurrently in different formulations, human plasma and solution state stability checking. [ABSTRACT FROM AUTHOR]

The aim of this study was to make predictions for soil cone index using artificial neural networks (ANNs), adaptive neuro-fuzzy inference system (ANFIS) and a regression model. Field tests were conducted on three soil textures and obtained results were analyzed by application of a factorial experiment based on a Randomized Complete Block Design with five replications. The four independent variables of percentage of soil moisture content, soil bulk density, electrical conductivity and sampling depth were used to predict soil cone index by ANNs, ANFIS and a regression model. The ANNs design was that of back propagation multilayer networks. Predictions of soil cone index with ANFIS were made using the hybrid learning model. Comparison of results acquired from ANNs, ANFIS and regression models showed that the ANFIS model could predict soil cone index values more accurately than ANNs and regression models. Considering the ANFIS model, a novel result on soil compaction modeling, relative error (ε), and regression coefficient (R2) were calculated at 2.54% and 0.979, respectively.

The measurement of reverberation time is an essential procedure for the characterization of the acoustic performance of rooms. The values returned by these measurements allow us to predict how the sound will be transformed by the walls and furnishings of the rooms. The measurement of the reverberation time is not an easy procedure to carry out and requires the use of a space in an exclusive way. In fact, it is necessary to use instruments that reproduce a sound source and instruments for recording the response of the space. In this work, an automatic procedure for estimating the reverberation time based on the use of artificial neural networks was developed. Previously selected sounds were played, and joint sound recordings were made. The recorded sounds were processed with the extraction of characteristics, then they were labeled by associating to each sound the value of the reverberation time in octave bands of that specific room. The obtained dataset was used as input for the training of an algorithm based on artificial neural networks. The results returned by the predictive model suggest using this methodology to estimate the reverberation time of any closed space, using simple audio recordings without having to perform standard measurements or calculate the integration explicitly. [ABSTRACT FROM AUTHOR]

The accuracy of short-term electricity load forecasting is of great interest since it allows avoiding unexpected blackouts and lowering operating costs. In this paper, we aim to implement the artificial neural networks to model and forecast the half-hourly electric load demand in Tunisia over the period 2000–2008. To improve the quality of forecasts, the proposed artificial neural network model uses not only past electric load values as inputs, but also climatic and calendar variables. To determine the optimal structure of the neural network model, this paper employs the pattern search algorithm. Moreover, the neural network model is equipped with the Levenberg–Marquardt learning algorithm. Our findings confirm the performance of this algorithm to the view of evaluation indicators since the mean absolute percentage error values range between 1.1 and 3.4%. The analysis also shows the superiority of the Levenberg–Marquardt algorithm compared to the resilient back propagation algorithm and the conjugate gradient algorithm. In the light of the current research, we stress the aptness of the proposed artificial neural network model in forecasting short-term electricity demand. [ABSTRACT FROM AUTHOR]

Research community has a growing interest in neural networks because of their practical applications in many fields for accurate modeling and prediction of the complex behavior of systems arising from engineering, economics, business, financial and metrological fields. Artificial neural networks (ANN) are very flexible function approximations tool used as universal modeling based on the separating of the past dynamics into clusters, in which we construct local models to capture the potential growth of the series depends on the previously known values. In this study, rain data of five major cities of Sindh province of Pakistan is considered, and summer rainfall of these five synoptic stations are statistically evaluated for prediction. The nonlinear autoregressive network with exogenous inputs (NARX) model for a time series is analyzed to evaluate the pattern of precipitation. We train a highly nonlinear NARX network model from randomly generated initial weights that converged to the best solution with the help of the Levenberg - Marquardt algorithm. A multi-step ahead NARX response time predictor is developed for rain forecasting. The performance of the NARX model is viable to capture nonlinear behavior with a high value of correlation coefficient R ranging from 0.70 to 0.99 for different synoptic stations. The results calculated using the proposed NARX neural network time series approach are accurate and reliable based on the coefficient of correlation and mean square error indices for rainfall forecasting. [ABSTRACT FROM AUTHOR]

This paper presents modeling of artificial neural network (ANN) to forecast the suspended sediment discharges (SSD) during flood events in two different catchments in the Seybouse basin, northeastern Algeria. This study was carried out on hourly SSD and water discharge data during flood events from a period of 31 years in the Ressoul catchment and of 28 years in the Mellah catchment. The ANNs were trained according to two different algorithms: the Levenberg–Marquardt algorithm (LM) and the Quasi-Newton algorithm (BFGS). Seven input combinations were trained for the SSD prediction. The performance results indicated that both algorithms provided satisfactory simulations according to the determination coefficient (R2) and root mean squared error (RMSE) performance criteria, with priority to the BFGS algorithm; the coefficient of determination using the LM algorithm varies between 51.0 and 90.2%, whereas using the BFGS algorithm it varies between 54.3 and 93.5% in both studied catchments, with calculated improvement for all seven developed networks with the best improvement in the Ressoul catchment presented in ANN06 with Δ R 2 4.23% and Δ RMSE 1.74‰, and with the best improvement presented in ANN05 with Δ R 2 6.07% and Δ RMSE 0.71‰ in the Mellah catchment. The analysis showed that the use of Quasi-Newton method performed better than the Levenberg–Marquardt in both studied areas. [ABSTRACT FROM AUTHOR]

The problem related to speech recognition system becomes challenging if vocabularies are having too many similar-sounding words. To overcome these types of challenges, an effective speech recognition system using artificial neural network (ANN) with optimization technique is proposed. In this system, distinct words spoken by different people are considered as input speech signal. The features of these input speech signals are extracted using amplitude modulation spectrogram. The extracted features are then the input to the ANN for training. The trained ANN inputs are used for predicting the isolated words during testing. In this work, the default structure of ANN is redesigned using Levenberg–Marquardt algorithm, to retrieve optimal prediction rate with accuracy. The hidden layers and neurons of the hidden layers are further optimized using the opposition artificial bee colony optimization technique. The outcome of the system demonstrates that the sensitivity, specificity, and accuracy of the proposed technique is 90.41%, 99.66%, and 99.36%, respectively, which is better than all the existing methods. [ABSTRACT FROM AUTHOR]

Artificial Neural Network (ANN)-Genetic Algorithm (GA) interface and Response Surface Methodology (RSM) have been compared as tools for simulation and optimization of gmelina seed oil extraction process. A multi-layer feed-forward Levenberg Marquardt back-propagation algorithm was incorporated for developing a predictive model which was optimized using GA. Design Expert simulation and optimization tools were also incorporated for a detailed simulation and optimization of the same process using Response surface methodology (RSM). It was found that oil yield increased with rise in temperature, time and volume of solvent but decreased with increase in seed particle size. The maximum oil yield obtained using the numerical optimization techniques show that 49.2% were predicted by the RSM at the optimum conditions of; 60 °C temperature, extraction time 60 min, 150 μm seed particle size, 150 ml solvent volume and 49.8% by ANN-GA at extraction temperature 40 °C, extraction time 40 min, 200 μm seed particle size, 100 ml solvent volume, respectively. The prediction accuracy of both models were more than 95%. Models validation experiments indicate that the predicted and the actual were in close agreement. The extract was analyzed to examine its physico-chemical properties (acid value, iodine value, peroxide value, viscosity, saponification value, moisture and ash content, refractive index, smoke, flash and fire points and specific gravity) and structural elucidation by standard methods and instrumental techniques. Results revealed that the oil is non-drying and edible. Desaturation of the oil further reveal its potential in alkyd resin synthesis.

This paper presents diagnostic and prognostic analysis of oil and gas pipeline industries with allowable corrosion rate using artificial neural networks approach. The results revealed sand deposit, carbon dioxide (CO2) partial pressure, pipe age, diameter and length, temperature, flow velocity of the fluid, fluid pressure, chloride contents and pH value of its environment as the relevant parameters affecting corrosion of oil and gas pipeline in this region. Condition prediction of steel pipes used for the transmission of oil and gas varies 0.02 mm/yr to 0.10 mm/yr. The training of the neural network was performed using Levenberg-Marquardt algorithm and optimal regression coefficient was equal to 0.99, for the network 10-40-1. Also, the results show a remarkable agreement with the field measurement. A corrosion severity level of two (0.01 mm/yr to 0.10 mm/yr) oil and gas pipelines was established from the analysis. Keywords: Artificial neural network, Levenberg-Marquardt algorithm, condition prediction, oil and gas data

The measurement of reverberation time is an essential procedure for the characterization of the acoustic performance of rooms. The values returned by these measurements allow us to predict how the sound will be transformed by the walls and furnishings of the rooms. The measurement of the reverberation time is not an easy procedure to carry out and requires the use of a space in an exclusive way. In fact, it is necessary to use instruments that reproduce a sound source and instruments for recording the response of the space. In this work, an automatic procedure for estimating the reverberation time based on the use of artificial neural networks was developed. Previously selected sounds were played, and joint sound recordings were made. The recorded sounds were processed with the extraction of characteristics, then they were labeled by associating to each sound the value of the reverberation time in octave bands of that specific room. The obtained dataset was used as input for the training of an algorithm based on artificial neural networks. The results returned by the predictive model suggest using this methodology to estimate the reverberation time of any closed space, using simple audio recordings without having to perform standard measurements or calculate the integration explicitly.

The objective of present work is to predict the thermal performance of wire screen porous bed solar air heater using artificial neural network (ANN) technique. This paper also describes the experimental study of porous bed solar air heaters (SAH). Analysis has been performed for two types of porous bed solar air heaters: unidirectional flow and cross flow. The actual experimental data for thermal efficiency of these solar air heaters have been used for developing ANN model and trained with Levenberg-Marquardt (LM) learning algorithm. For an optimal topology the number of neurons in hidden layer is found thirteen (LM-13).The actual experimental values of thermal efficiency of porous bed solar air heaters have been compared with the ANN predicted values. The value of coeffi- cient of determination of proposed network is found as 0.9994 and 0.9964 for unidirectional flow and cross flow types of collector respectively at LM-13. For unidirectional flow SAH, the values of root mean square error, mean absolute error and mean relative percentage error are found to be 0.16359, 0.104235 and 0.24676 respectively, whereas, for cross flow SAH, these values are 0.27693, 0.03428, and 0.36213 respectively. It is concluded that the ANN can be used as an appropriate method for the prediction of thermal performance of porous bed solar air heaters. [ABSTRACT FROM AUTHOR]

This paper presents diagnostic and prognostic analysis of oil and gas pipeline industries with allowable corrosion rate using artificial neural networks approach. The results revealed sand deposit, carbon dioxide (CO2) partial pressure, pipe age, diameter and length, temperature, flow velocity of the fluid, fluid pressure, chloride contents and pH value of its environment as the relevant parameters affecting corrosion of oil and gas pipeline in this region. Condition prediction of steel pipes used for the transmission of oil and gas varies 0.02 mm/yr to 0.10 mm/yr. The training of the neural network was performed using Levenberg-Marquardt algorithm and optimal regression coefficient was equal to 0.99, for the network 10-40-1. Also, the results show a remarkable agreement with the field measurement. A corrosion severity level of two (0.01 mm/yr to 0.10 mm/yr) oil and gas pipelines was established from the analysis. [ABSTRACT FROM AUTHOR]

Accurate knowledge of net surface radiation (NSR) is required to understand the soil-vegetation-atmosphere feedbacks. However, NSR is seldom measured due to the technical and economical limitations associated with direct measurements. An artificial neural network (ANN) technique with Levenberg–Marquardt learning algorithm was used to estimate NSR for a tropical mangrove forest of Indian Sundarban with routinely measured meteorological variables. The root mean square error (RMSE), mean absolute error (MAE), modelling efficiency (ME), coefficient of residual mass (CRM) and coefficient of determination (R2) between ANN estimated and measured NSR were 37 W m−2, 26 W m−2, 0.95, 0.017 and 0.97 respectively under all-weather conditions. Thus, the ANN estimated NSR values presented in this study are comparable to those reported in literature. Further, a detailed study on the estimated NSR for cloudy skies was also analysed. ANN estimated NSR values were compared with in situ measurements for cloudy days and non-cloudy days. The RMSE, MAE and CRM of the model decrease to half when considering the non-cloudy days. Thus, the results demonstrate that major source error in estimating NSR comes from the cloudy skies. Sensitivity of input variables to NSR was further analysed.

The aim of this study was to estimate suspended sediment by the ANN model, DT with CART algorithm and different types of SRC, in ten stations from the Lorestan Province of Iran. The results showed that the accuracy of ANN with Levenberg-Marquardt back propagation algorithm is more than the two other models, especially in high discharges. Comparison of different intervals in models showed that running models with monthly data,resulted in smaller error and better estimated results. Moreover, results showed that using Minimum Variance Unbiased Estimator (MVUE) bias correction factor modified the SRC results, especially in monthly time steps in almost all stations. Hence, it can be said that if because of advantages such as simplicity, SRC models are preferred, it is better that MSRC (modified sediment rating curve) is used in monthly period.