Search

Overpressure is always considered as a severe problem in the oil industry. Besides creating life risks through serious accidents while drilling, failure to correctly identify high-pressure intervals causes a significant increase in costs and prolongs the drilling process. Kazhdumi Formation in the Abadan Plain is considered as a high-pressure formation in several wells. Various reasons can cause overpressure problem. Hydrocarbon generation is one cause of abnormal pressure in source rocks. Understanding hydrocarbon generation potential can be a helpful approach since the Kazhdumi Formation is considered as a probable source rock in this area. In this paper, in order to better understand the problem of abnormal pressure in Kazhdumi Formation, geochemical concepts and tools have been applied. To that way, 1D petroleum system modeling of five wells was done, and the thermal maturity level of Kazhdumi Formation was determined and then, compared with drilling records. The results indicate that in wells where this formation has sufficient organic matter and has reached an early mature level, there is an abnormal pressure problem. Otherwise, this formation does not show abnormal pressure. Also, geochemical data are not available in all drilled wells, which makes impossible the assessing of hydrocarbon generation role. Therefore, petrophysical well logs (sonic (DT), neutron (NPHI), density (RHOB), spectral gamma ray (SGR), and resistivity (RES)) as well as 137 sets of geochemical data belonging to 13 wells from 7 oilfields in the Abadan Plain were used to predict geochemical indicators. Using artificial neural networks, geochemical data of a well in Abadan Plain were predicted. This selected well has a high-pressure problem in Kazhdumi Formation, but no geochemical data are available in this well. The results of predicted geochemical data show that the high-pressure phenomenon in this well may also be due to hydrocarbon generation. The precise understanding of the abnormal pressure, resulting from hydrocarbons generation, requires comprehensive studies and a full investigation of the studied area. However, the results of this paper help to predict approximately the behavior of the source rocks before drilling. Acquiring this overview will aid in reducing drilling hazards and costs. [ABSTRACT FROM AUTHOR]

In order to mitigate/prevent the risks of landslides, one of the essential tools that can be used to manage and plan the development of human settlements is landslide susceptibility. The two metaheuristic algorithms explored in this paper are the SCE and VSA algorithms used to optimize the artificial neural network (ANN) model. By integrating the two algorithms with the artificial neural network model, we try to determine its optimum computational parameters in order to generate the landslide susceptibility mapping for the Kurdistan province in Iran. Sixteen causative factors of landslides are included in the spatial database. The landslide susceptibility maps were generated in a GIS medium, and in order to evaluate the employed predictive models, the criterion of the area under the curve (AUC) was employed. This investigation includes 1072 landslide events, which are divided as follows: one-third as testing data and two-thirds as training data (i.e., a 75:25 ratio). The results indicate that after using the abovementioned algorithms, the AUC increased noticeably from 0.708 to 0.788 for SCE-MLP and from 0.744 to 0.818 for VSA-MLP in the training phase. The criterion of the area under the curve was utilized in order to evaluate the accuracy of the employed probabilistic models. Incidentally, the comparable AUCs calculated for the VSA-MLP testing databases and the obtained AUCs were 0.818, 0.801, 0.791, 0.786, 0.784, 0.778, 0.777, 0.776, 0.754 and 0.744, respectively for population size in training databases equal to 50, 350, 500, 150, 450, 200, 400, 300, 100 to and 250. Also, in case of SCE-MLP, the training and testing AUC were found (0.878, 0.865, 0.851, 0.850, 0.819, 0.816, 0.815, 0.781, 0.760, and 0.756) and (0.788, 0.782, 0.759, 0.744, 0.727, 0.720, 0.718, 0.713 and 0.708). The best fit for swarm size conditions of the SCE-MLP and VSA-MLP model showed 150 and 350, respectively. The acquired results indicate that the VSA-ANN model has a better predictive capability in optimization of the structure of the artificial neural network model and computational parameters in comparison with the SCE-ANN. [ABSTRACT FROM AUTHOR]

The ionosphere is the upper part of the Earth's atmosphere, which is considered to be approximately 70 to 1000 km above the Earth's surface. Ionosphere modeling has been one of the goals of spatial geodesy since 1970. In many ionosphere modeling using satellite measurements such as GPS, total electron content (TEC) are used as observational input data. In recent years, modeling and prediction of the TEC have been considered by researchers with methods that have high speed and accuracy. One of the branches that has been able to show good capabilities in the field of estimation and modeling is machine learning methods (ML). Machine learning includes fuzzy inference systems (FIS), artificial neural networks (ANNs), genetic algorithms (GAs), support vector machines (SVMs), and evolutionary communications (ECs). Since 1993, with the advancement of computer technology, many new and hybrid algorithms, such as the adaptive neuro-fuzzy inference system (ANFIS), have been developed in ML. Another new effective approach in ML is the support vector regression (SVR) method. The SVR is a kernel-based ML method for classification and regression in which the risk of incorrect classification is minimized. The structure of an SVR network has a lot in common with the ANN, and the main difference is practically in the way of the training algorithm. In general, this method is divided into linear and nonlinear modes. In this paper, the TEC of the ionosphere is modeled and evaluated with ML models. Support vector regression (SVR) and artificial neural network (ANN) methods are used for local TEC modeling. In both models, the latitude and longitude of the GPS stations, day of the year (DOY), hours, AP, KP, DST, and F10.7 are considered an input vectors. Also, the value of VTEC is considered as the output of the models. The main innovation of this paper is in evaluating the effect of different physical parameters on the accuracy of ML models. Using observations of 15 GPS stations in the northwest of Iran from 193 to 228 in 2012, new models are evaluated. Also, the results of the new models are compared with the results of the global ionosphere map (GIM), the IRI2016, and NeQuick empirical models in two internal and one external control station. Statistical indices of root mean square error (RMSE), relative error, dVTEC, and correlation coefficient are used to evaluate the error of the models. Sensitivity analysis of SVR and ANN models to input parameters is performed and the importance of each physical parameter in spatio-temporal modeling of the ionosphere is investigated. The results obtained from this paper show that in both high and low geomagnetic and solar activities, the SVR model in internal control stations has a higher accuracy than other models. But at the external control station, the error of the SVR model is much higher than other models. Determining the parameters of the kernel function using observations at the territory of the studied network is the reason. Also, the sensitivity of SVR and ANN models is increased to the physical parameters F10.7, KP, DST, and AP, respectively. For precise local ionosphere modeling, the effect of these parameters must also be considered. [ABSTRACT FROM AUTHOR]

Rainfall prediction is vital for the management of available water resources. Accordingly, this study used large lagged climate indices to predict rainfall in Iran's Sefidrood basin. A radial basis function neural network (RBFNN) and a multilayer perceptron (MLP) network were used to predict monthly rainfall. The models were trained using the naked mole rat (NMR) algorithm, firefly algorithm (FFA), genetic algorithm (GA), and particle swarm optimization (PSO) algorithm. Large lagged climate indices, as well as three hybrid models, i.e., inclusive multiple model (IMM)-MLP, IMM-RBFNN, and the simple average method (SAM), were then employed to predict rainfall. This paper aims to predict rainfall using large climate indices, ensemble models, and optimized artificial neural network models. Also, the paper considers the uncertainty resources in the modeling process. The inputs were selected using a new input selection method, namely a hybrid gamma test (GT). The GT was integrated with the NMR algorithm to create a new test for determining the best input scenario. Therefore, the main innovations of this study were the introduction of the new ensemble and the new hybrid GT, as well as the new MLP and RBFNN models. The introduced ensemble models of the current study are not only useful for rainfall prediction but also can be used to predict other metrological parameters. The uncertainty of the model parameters and input data were also analysed. It was found that the IMM-MLP model reduced the root mean square error (RMSE) of the IMM-RBFNN, SAM, MLP-NMR, RBFNN-NMR, MLP-FFA, RBFNN-FFA, MLP-PSO, RBFNN-PSO, MLP-GA, and RBFNN-GA, MLP, and RBFNN models by 12%, 25%, 31%, 55%, 60%, 62%, 66%, 69%, 70%, 71%, 72%, and 72%, respectively. The IMMs, such as the IMM-MLP, IMM-RBFNN, and SAM, outperformed standalone models. The uncertainty bound of the multiple inclusive models was narrower than that of the standalone MLP and RBFNN models. The MLP-NMR model decreased the RMSE of the RBFNN-NMR, RBFNN-FFA, RBFNN-PSO, and RBFNN models by 15%, 26%, 37%, 42%, and 45%, respectively. The proposed ensemble models were robust tools for combining standalone models to predict hydrological variables. [ABSTRACT FROM AUTHOR]

Clean solar energy is one of the best sources of energy. Solar power plants can generate electricity in Iran due to their large number of sunny days. This paper presents a short-term forecasting approach based on artificial neural networks (ANNs) for selected solar power plants in Iran and ranks the input variables of the neural network according to their importance. Two solar power plants in Hamadan province (Amirkabir and Khalij-Fars) were selected for the project. The output of solar power plants is dependent on weather conditions. Solar radiation on the horizontal plane, air temperature, air pressure, day length, number of sunny hours, cloudiness, and airborne dust particles are considered input variables in this study to predict solar power plant output. Forecasting model selection is based on considering zero and nonzero quantities of target variables. The results show that solar production forecasting based on meteorological parameters in the Khalij-Fars is more accurate than Amirkabir. The global solar radiation, air temperature, number of sunny hours, day length, airborne dust particles, cloudiness, air pressure, and dummy variables1 are the order of the most important inputs to solar power generation. Results show simultaneous influences of radiation and temperature on solar power plant production. [ABSTRACT FROM AUTHOR]

In line with the growing global trend towards energy efficiency in buildings, this paper introduces a predictive model based on an artificial neural network model to rate the performance of windows in terms of saved heating and cooling loads. A four-story building representing the conventional type of residential apartments in Iran for four climates of cold, hot and humid, hot and arid, and temperate was selected for simulation. An artificial neural network model was developed based on ten variables of U-factor, SHGC, emissivity, monthly average dry bulb temperature, monthly average percent humidity, monthly average wind speed, monthly average direct solar radiation, monthly average diffuse solar radiation, orientation, and month as the input variables. The developed ANN model computes the amount of saved heating or cooling loads as a result of using a window with defined parameters. The best architecture of 10–10-1 with MAPE, RMSE, and R2 values of 1.4%, 0.008, and 0.985, respectively showed an acceptable predictive performance of the model. The predictions of this model, in line with the four levels of window performance defined in this paper, which range from excellent performance to weak performance, constitute the final rating of a window. The rated performance of the windows used in this study showed that the performance of a window can vary in cold and hot months, and windows should be rated according to the climate in which they are being used. [ABSTRACT FROM AUTHOR]

This paper evaluates a comparison between three machine learning algorithms (MLAs), namely support vector machine (SVM), multilayer perceptron artificial neural network (MLP-ANN) and random forest (RF), in landslide susceptibility mapping and addresses a optimization algorithm to optimize the performance of a MLA to yield more accurate and reliable results. A genetic algorithm (GA) approach as a part of evolutionary algorithms was utilized in order to optimize the performance of best model among three utilized MLAs. The study area (Tarom–Khalkhal sub-basin) is located in North-West of Iran with mountainous nature (western part of Alborz Mountains), wherein numerous landslide occurrences were recorded. In this case, fifteen predisposing factors, gathered from aerial images and field surveys, were considered to generate the final landslide susceptibility models. The validation procedure was conducted with taking advantage of confusion matrices for different algorithms. Finally, landslide susceptibility maps were generated and evaluated through receiver operator characteristic (ROC) curves. RF algorithm showed the best performance; therefore, hybridized genetic random forest (GRF) was employed in order to optimize the hyperparameters (number of trees, number splits and depth) of the model, which can affect the performance of model. As a result, GRF has best performance among all mentioned algorithms with AUC = 0.93. As a conclusion, genetic algorithm was found to be suitable in optimizing the performance of machine learning algorithms, which is crucial when it comes to landslide susceptibility mapping. [ABSTRACT FROM AUTHOR]

In this paper, daily and monthly runoff discharge forecasts are improved by developing an ensemble model based on the Bayesian maximum entropy (BME), which integrates the outcomes of several single-source simulation models. The performance of the developed ensemble model in daily and monthly discharge forecasting is evaluated by comparing its results with those obtained from 12 other ensemble models, including simple averaging (SA), weighted averaging (WA), Bayesian model averaging (BMA), the best model in last time step (BMLS), artificial neural network (ANN), artificial neural network-based on differenced data, error analysis (EA), wavelet-artificial neural network (Wavelet-ANN), multi-model super ensemble (MMSE), modified multi-model super ensemble (MMMSE), Kriging and an ensemble model based on K-means clustering. Six models, namely artificial neural network (ANN), auto-regressive integrated moving average (ARIMA), adaptive neuro-fuzzy inference system (ANFIS), support vector regression (SVR), M5tree, and Wavelet-ANN, are used as single-source forecasting models. These models provide the inputs of the ensemble models. After analyzing different hydrologic variables, the best set of predictors is chosen for the single-source models. Then, the single-source models are calibrated and validated and the ones with the best performances are selected for being used in the ensemble phase. The performance of the models is evaluated by applying them to two different case studies of the Liqvan watershed, a sub-watershed of Lake Urmia catchment in the north-west of Iran, and the Latyan watershed, in the east of Tehran, Iran. The results show that the ensemble models, especially the BME and ANN-based ensemble models, significantly improve both monthly and daily river discharge forecasts. The values of the performance criteria of Nash–Sutcliffe efficiency (NSE) and coefficient of determination (R2) in forecasting the extreme values of monthly runoff discharge, using the best single-source model, are respectively 0.787 and 0.869. The corresponding values for the best ensemble model are 0.933 and 0.962, respectively. For the daily runoff discharge forecast, the values of the mentioned performance criteria for the best single-source model are respectively 0.874 and 0.877, while corresponding values for the best ensemble model are 0.927 and 0.935, respectively. [ABSTRACT FROM AUTHOR]

Due to the underlying uncertainty in the groundwater level (GWL) modeling, point prediction of the GWLs does not provide sufficient information for decision making and management purposes. Thus, estimating prediction intervals (PIs) for groundwater modeling can be an important step in sustainable water resources management. In this paper, PIs were estimated for GWL of selected piezometers of the Ardebil plain located in northwest of Iran and the Qorveh–Dehgolan plain located in west of Iran, using bootstrap methods based on artificial neural networks (ANNs). For this purpose, the classic feedforward neural network (FFNN) and deep learning (DL)-based long short-term memory (LSTM) were used as ANN bases and the classic bootstrap and moving blocks bootstrap (MBB) as the bootstrap variations. Monthly GWL data of some piezometers as well as hydrologic data of the related stations from both plains were used for the training and validation of the models. The results showed that the LSTM outperforms the seasonal auto regressive integrated moving average model with exogeneous data (SARIMAX), which is a linear model, and classic FFNN in point prediction task. Moreover, in terms of PIs model performance, the LSTM-based MBB (MBLSTM) achieved an average of 30% lower coverage width criterion (CWC) than the FFNN-based MBB (MBFN) and average of 40% lower CWC than the FFNN-based classic bootstrap (BFN). In addition, PIs estimated for piezometers situated in areas with high transmissivity resulted in 55% lower CWC than PIs estimated for piezometers, which are located in areas with lower transmissivity. [ABSTRACT FROM AUTHOR]

This paper evaluates several efficiency indexes of hydropower energy generation in Iran's Karkheh Basin water reservoir system (i.e., Seymareh and Karkheh Rivers) under climate change based on the system dynamics approach. The climate change effects are investigated with simulations of surface temperature and rainfall driven by downscaled climate projections from atmosphere–ocean circulation models in the current literature, and the models with the highest correlation and lowest error for rainfall and temperature in the 1976–2005 baseline period are identified. Rainfall and temperature are projected over two future periods, 2040–2069 and 2070–2099, and are downscaled to basin scale. Results project that the basin temperature over future periods will be higher than in the baseline period. Downscaled results under climate change indicate that rainfall will not follow a specific pattern. An artificial neural network applied to predict runoff indicates that the runoff and flood peak will decrease. Software is implemented to simulate the operation of hydropower reservoirs in baseline and future periods. Five reservoir operation states are considered, with simulation results of energy production showing that runoff and energy production have a complex pattern. Seven indexes of hydropower reservoir efficiency are also calculated for the five operation states corresponding to targets of energy production. [ABSTRACT FROM AUTHOR]

This paper studies the application of two machine learning methods to model precipitable water vapor (PWV) using observations of 23 GPS stations from the local GPS network of north-west of Iran in 2011. In a first step, the zenith tropospheric delay (ZTD) and zenith hydrostatic delay (ZHD) is calculated with the Bernese GNSS software and Saastamoinen model as revised by Davis, respectively. Then, by subtracting the ZHD from the ZTD, the zenith wet delay (ZWD) is obtained at each GPS station, for all times. In a second step, ZWD is modeled by two different machine learning methods, based on the latitude, longitude, DOY, time, relative humidity, temperature and pressure. After training a Support Vector Machine (SVM) and an Artificial Neural Network (ANN), ZWD temporal and spatial variations are estimated. Using the formula by Bevis, the ZWD can be converted to PWV at any time and space, for each machine learning method. The accuracy of the two new models is evaluated using control stations, exterior and radiosonde station, whose observations were not used in the training step. Also, all the results of the SVM and ANN are compared with a voxel-based tomography (VBT) model. In the control and exterior stations, ZWD estimated by the SVM (ZWD SVM) and ANN (ZWD ANN) is compared with the ZWD obtained from the GPS (ZWD GPS). Also, in the control and exterior stations, precise point positioning (PPP) is used to evaluate the accuracy of the new models. In the radiosonde station, the PWV of the new models (PWV SVM , PWV ANN) is compared with the radiosonde PWV (PWV radiosonde) and voxel-based PWV (PWV VBT). The averaged relative error of the SVM, ANN and VBT models in the control stations is 10.50%, 12.71% and 12.91%, respectively. For SVM, ANN and VBT models, the averaged RMSE at the control stations is 1.87 (mm), 2.22 (mm) and 2.29 (mm), respectively. Analysis of the results of PWV estimated by the SVM, ANN and VBT, as well as the surface precipitation obtained from meteorological stations, indicate the high accuracy of the SVM in comparison with the ANN and VBT model. In the results shown in this paper, the SVM has the best ability to accurately estimate ZWD and PWV, using local GPS network observations. [ABSTRACT FROM AUTHOR]

With the increase of the world population, the worries and concerns for food supply increase too. Wheat, as one of the most important agricultural products, which is widely consumed all over the world, has a very important role in people's nutrition, particularly among Iranians, the diet of whom is highly dependent on bread. Product forecasting is critical for any country so that decisions about storage, import or export, etc. can be planned. In this paper, several univariate time series models and the Artificial Neural Network (ANN) model are used to forecast wheat production in Iran. Annual wheat production, total annual precipitation, total applied fertilizer, population, and wheat cultivated area data were used in the period between 1961-1962 to 2018-2019. With the minimum values of 1.45894, 1.00329, 1.0448, and 1.09742 obtained for RMSE, AIC, HQC, and SIBC criteria, respectively, Autoregressive Integrated Moving Average (ARIMA) (1,1,1) was selected as the best univariate model. In testing the ANN models, total annual precipitation, total applied fertilizer, population, and wheat cultivated, area as input variables, and wheat production, as output variable, were used. Among several NN models, the Multilayer Perceptron Neural Network (MLP-NN) model with five hidden layers had the lowest MSE= 0.153 and was chosen in this study. Comparison between the ANN model and the ARIMA (1,1,1) model showed that RMSE= 0.391, MSE= 0.153, and MAPE= 0.4231 in the ANN model were much lower than that of the ARIMA (1,1,1) model. The results showed the power of ANN models to predict wheat production using efficient parameters, as compared to the ARIMA model. [ABSTRACT FROM AUTHOR]

Moving toward environmental sustainability in the fruit production systems needs accurate monitoring of the systems in terms of energy flow. In this regard, using regression models (i.e., Cobb–Douglas), Multiple Linear Regression (MLR)), and Artificial Neural Network (ANN), this paper examined the energy flow in the pomegranate orchards in Iran. Unlike other similar studies, in the current research, the cross-validation technique was employed to evaluate how choosing datasets would modify the behavior of the models. The results demonstrated that the total energy consumption and energy efficiency of the pomegranate production were 13,634.13 MJ ha−1 and 1.01, respectively. The results also indicated that among investigated MLR models, the pure-quadratic model had the best performance. Besides, among 13 evaluated ANN-training algorithms, the Bayesian regulation algorithm had the highest accuracy in prediction and the best model consisted of one hidden layer with three neurons (5–3–1 topology) with logarithm sigmoid activation function. The results highlighted that the ANN model (R2 = 0.91) outweighs the MLR model (R2 = 0.86). The results also approved that the proposed ANN model was capable to use different datasets with high generalizability. The results of sensitivity analysis claimed the significant role of water and fuel consumption and consequently, the importance of establishing management policies to optimizing the use of these inputs in the pomegranate orchards. [ABSTRACT FROM AUTHOR]

Regarding the ability of data mining algorithms for post-processing the output of climate models, and on the other hand, the successful application of multi-model ensemble approaches in climate forecasts, in this paper, some important data mining algorithms are evaluated for the monthly forecast of precipitation over Iran. For this purpose, four European climate models, from DWD, ECMWF, CMCC and Meteo-France, with six lead times, are used to be post-processed by applying four different algorithms including artificial neural networks, support vector regression, decision tree and random forests. Based on the proposed approach, 72 different models are provided for 12 months, each month with six lead times. The approach is applied for the monthly forecast of precipitation over Iran. According to the results, the neural network and random forest methods performed better than the decision tree and the support vector machine. This advantage preserved for all months of the year. Also, the proposed multi-model approach outperformed any of the individual European models. [ABSTRACT FROM AUTHOR]

As a frequent natural disaster, landslides incur significant economic and human losses worldwide. The main idea of this paper is to propose novel integrative models for landslide susceptibility evaluation in a prone area of Chaharmahal va Bakhtiari Province in Iran. To do this, four metaheuristic techniques, namely chimp optimization algorithm (ChOA), crow search algorithm (CSA), satin bowerbird optimization (SBO), and water cycle algorithm (WCA) are used to supervise the training of an artificial neural network (ANN). A spatial database is created by 170 historical landslides and 14 most common conditioning factors. The models are optimized in terms of hyper-parameters and elite ones are then used to produce the susceptibility maps. During the training phase, all models could acquire a reliable understanding of the landslide pattern. The obtained accuracy index of area under the receiving operating characteristic curve (AUROC) showed that the maps produced by the WCA-ANN (AUROC = 0.925) and SBO-ANN (AUROC = 0.900) are more accurate than those of the ChOA-ANN (AUROC = 0.851) and CSA-ANN (AUROC = 0.855). Considering this assessment, the suggested hybrid models are reliable enough for landslide susceptibility modeling. Accordingly, the generated susceptibility map can be used for urban planning and generating alert systems over the studied area. [ABSTRACT FROM AUTHOR]

Machine learning approaches are increasingly being employed to forecast the key characteristics of strong ground motions, including the challenging classification of Pulse-Like (PL) ground motions. The PL ground motions are characterized by their impulsive nature and have the potential to cause significant damage to structures. The classification of PL ground motions continues to be a significant challenge due to the absence of consensus on their definition and categorization. This paper investigates the potential benefits of several Machine Learning Classifiers (MLCs) algorithms such as decision tree, random forest, logistic regression, naive Bayes, support vector machine, K-nearest neighbor, ensemble model, and artificial neural network models for predicting PL and Non-Pulse-Like (NPL) ground motions. In this regard, a dataset comprising 200 near-fault ground motions records compiled from active tectonic regions like Taiwan, Turkey, Iran, and Japan, was divided into 2 portions, with 75% used to train the model and the remaining 25% used for testing. Plots of performance metrics, confusion matrix, and receiver operating curve indicate that the ensemble classifier outperforms the other classifier with 86.2% accuracy and the lowest misclassification of PL and NPL ground motions. Additionally, the trained MLC has been compared with the existing ground motion classification models to further assess the accuracy of the different classifiers in the present study. [ABSTRACT FROM AUTHOR]

This paper investigates the prediction of future earthquakes that would occur with magnitude 5.5 or greater using adaptive neuro-fuzzy inference system (ANFIS). For this purpose, the earthquake data between 1950 and 2013 that had been recorded in the region with 2°E longitude and 4°N latitude in Iran has been used. Thereupon, three algorithms including grid partition (GP), subtractive clustering (SC) and fuzzy C-means (FCM) were used to develop models with the structure of ANFIS. Since the earthquake data for the specified region had been reported on different magnitude scales, suitable relationships were determined to convert the magnitude scales into moment magnitude and all records uniformed based on the relationships. The uniform data were used to calculate seismicity indicators, and ANFIS was developed based on considered algorithms. The results showed that ANFIS-FCM with a high accuracy was able to predict earthquake magnitude. [ABSTRACT FROM AUTHOR]

As a threat for transportation system, traffic crashes have a wide range of social consequences for governments. Traffic crashes are increasing in developing countries and Iran as a developing country is not immune from this risk. There are several researches in the literature to predict traffic crash severity based on artificial neural networks (ANNs), support vector machines and decision trees. This paper attempts to investigate the crash injury severity of rural roads by using a hybrid clustering and classification approach to compare the performance of classification algorithms before and after applying the clustering. In this paper, a novel rule-based genetic algorithm (GA) is proposed to predict crash injury severity, which is evaluated by performance criteria in comparison with classification algorithms like ANN. The results obtained from analysis of 13,673 crashes (5600 property damage, 778 fatal crashes, 4690 slight injuries and 2605 severe injuries) on rural roads in Tehran Province of Iran during 2011–2013 revealed that the proposed GA method outperforms other classification algorithms based on classification metrics like precision (86%), recall (88%) and accuracy (87%). Moreover, the proposed GA method has the highest level of interpretation, is easy to understand and provides feedback to analysts. [ABSTRACT FROM PUBLISHER]

Changes in amount and frequency of runoff are caused by interaction of the climatic and anthropogenic factors in human-nature system. Those part of the runoff variations caused by anthropogenic loadings are more manageable compared with climate effects occurring over a long period. In this paper, we propose a framework to decompose the effect of anthropogenic and climatic time series on streamflow. To fulfill this task, anthropogenic time series attribution (ATSA) method is introduced. ATSA employs the output of climate elasticity (CE) method to extract human-affected time series and naturalizes the annual streamflow. In other words, ATSA makes it possible to exploit CE output in time series analysis. Furthermore, temporal downscaling process performed by a hybrid discrete wavelet transform and artificial neural network (DWT-ANN) enhances the temporal resolution of ATSA. We applied ATSA framework on Urmia Lake (northwest of Iran) inflow over the 1972–2010 period. CE application indicated that the contribution of climatic and anthropogenic factors in reduction of the mean inflow to the lake is about 60 and 40%, respectively. ATSA also revealed how human exploitation affected the time series of the lake inflow. Roughly, 14,000 MCM of the lake inflow reduction was attributed to the anthropogenic impacts between 1995 and 2010 such that the removal of anthropogenic loading could have led to rising water level up to 1275.5 meters above the sea level (i.e., 1.4 m above the ecological level) in 2010. Furthermore, the effect of de-trended inflow time series was investigated via DWT-ANN. Trend-free pre-whitening Mann-Kendall (TFPW-MK) test indicated significant increase in temperature, potential evapotranspiration, population, reservoir capacity, irrigated area, and the number of wells, over 39 years of the study period. [ABSTRACT FROM AUTHOR]

This paper presents the construction of prediction intervals (PIs) associated with the Emotional Artificial Neural Network (EANN) via the Lower Upper Bound Estimation method (LUBE) and the classic Bootstrap method for the Suspended Sediment Load (SSL) modeling. As point prediction conveys no information about modeling reliability, PIs were applied. The constructed PIs via the EANN were also compared to those of the classic feed-forward Neural Network (FFNN) model. It was attempted to construct the PIs of the SSL modeling in both daily and monthly scales for two watersheds, Upper Rio Grande River, in the United States and the Lighvanchai River in Iran. The PIs were quantified via coverage and width criteria. In the LUBE method, Genetic Algorithm (GA) constructed the PIs by minimizing the cost function of Combinational coverage Width-based Criterion (CWC). Comparison of the results indicated that the criterion of the CWC for PIs of EANN was up to 72% and 78% lower than that to the PIs of the FFNN, respectively, in the LUBE and Bootstrap methods, which showed the reliability of the EANN. In addition, obtained results via the LUBE and the Bootstrap techniques denoted the lower level of uncertainty of the LUBE method. Comparing the CWC criterion of both methods indicated that for the LUBE method, CWC was up to 39% lower than that for the Bootstrap method. Also, the PIs of the FFNN for the Lighvanchai river modeling showed reliable results with CWC of 56% lower than Upper Rio Grande River, but PIs of the EANN led to lower level of uncertainty in Upper Rio Grande River modeling. [ABSTRACT FROM AUTHOR]

Analysing the navigation behaviour in a built environment without a particular destination is a complicated issue when simulating pedestrian behaviour. This navigation is called exploratory navigation. This paper aims to investigate the spatial characteristics of a built environment which affect exploratory navigation. It focuses on visibility graph analysis (VGA) and uses the artificial neural network (ANN) for predicting navigation behaviours of visitors in museums. The movement data of visitors in the Islamic Revolution and Iran-Iraq War Museum (IRIIWM) in Tehran, Iran are collected from an observational study. The neural network analyzes the movement features of visitors and produces one single route containing all important movement characteristics of actual visitors. The results show that the network chooses its next target based on spatial visibility, visual perception, distance to a particular section, direction change, visual connectivity, and visual integration. The turn patterns and visual attractors also affect exploratory navigation. [ABSTRACT FROM AUTHOR]

Accurately predicting the particle size distribution of a muck-pile after blasting is always an important subject for mining industry. Adaptive neuro-fuzzy inference system (ANFIS) has emerged as a synergic intelligent system. The main contribution of this paper is to optimize the premise and consequent parameters of ANFIS by firefly algorithm (FFA) and genetic algorithm (GA). To the best of our knowledge, no research has been published that assesses FFA and GA with ANFIS for fragmentation prediction and no research has tested the efficiency of these models to predict the fragmentation in different time scales as of yet. To show the effectiveness of the proposed ANFIS-FFA and ANFIS-GA models, their modelling accuracy has been compared with ANFIS, support vector regression (SVR) and artificial neural network (ANN). Intelligence predictions of fragmentation by ANFIS-FFA, ANFIS-GA, ANFIS, SVR and ANN are compared with observed values of fragmentation available in 88 blasting event of two quarry mines, Iran. According to the results, both ANFIS-FFA and ANFIS-GA prediction models performed satisfactorily; however, the lowest root mean square error (RMSE) and the highest correlation of determination (R2) values were obtained from ANFIS-GA model. The values of R2 and RMSE obtained from ANFIS-GA, ANFIS-FFA, ANFIS, SVR and ANN models were equal to (0.989, 0.974), (0.981, 1.249), (0.956, 1.591), (0.924, 2.016) and (0.948, 2.554), respectively. Consequently, the proposed ANFIS-GA model has the potential to be used for predicting aims on other fields. [ABSTRACT FROM AUTHOR]

A reliable forecast of the prices of agricultural commodities can help to allocate resources optimally, enhance efficiency and farmer income, and alleviate fluctuations. Given the importance of accurate forecasts, the present paper investigates how one can forecast greenhouse tomato prices at one, two, three, and six-month horizons using different support vector machines and artificial neural network algorithms. The data on variables affecting the price of greenhouse tomatoes were collected through a field study for a shortterm period from November 2014 to January 2017. The wholesale price of the crop was drawn from a market study for this period. The results show that the trend forecasted through General Regression Neural Network along with activating function of reciprocal is more efficient to estimate the training data. The Epsilon-SVR SVM acquisition pattern alongside the linear activating function was taken into consideration to estimate the testing data in an efficient way for two-month, three-month or biannual periods. [ABSTRACT FROM AUTHOR]

Landslide susceptibility map (LSM) provide useful tool for decision makers in hazard mitigation concerns. In the present paper, a novel hybrid block-based neural network model (HBNN) for the purpose of producing high-resolution LSM was developed. This hybrid approach was found through the mixture of expert modular structures and divide-and-conquer strategy incorporated with genetic algorithm (GA). The introduced HBNN then was applied on southern part of Guilan province (north of Iran) using 14 causative factors covering topographic and geomorphologic features, and geological and tectonical factors as well as hydrology, land data, and climate conditions. The landslide inventory map was provided using a synergy work from monitored events, interpretation of aerial photographs, and carried out geotechnical investigations in the area as well as field surveys. To insight, the predictability of proposed HBNN was compared with two developed models using multilayer perceptrons (MLPs) and generalized feed forward neural network (GFFN). The generated LSM was validated using receiver operating characteristic (ROC) curves, statistical error indices, and sensitivity and weight analyses as well as monitored landslides. Based on the compared metrics, HBNN with 86.52% and 90.15% in prediction and success rate as well as 89.36% for precision-recall curve demonstrated more consistent tool for future landslide susceptibility zonation. This implies on capability of developed HBNN in producing higher resolution and more reliable LSM for urban and land-use planners. [ABSTRACT FROM AUTHOR]

Short-term load forecasting for small power systems, namely zonal STLF, is one of the issues in the load forecasting area which has vital value for electricity market competitors like retailers and ISO. This paper discusses the common problems related to short term load forecasting which are particularly raised in the small power systems. Identifying bad data which constitute a large portion of load data in these systems, choosing a proper manner for selecting ANN training data, and requirements which should be considered in the structure of zonal STLF to facilitate its employing to different power systems are investigated in this paper. Here, a comprehensive model which considers these problems as well as the generality of structure and the simplicity of implementation is proposed. This model is tested on Isfahan power system which is one of the regional power companies of Iran national power system. The results show that this structure can be implemented effectively and have an acceptable error in spite of large amount of bad data among historical data. [ABSTRACT FROM AUTHOR]

The use of freely accessible Sentinel-1 synthetic aperture radar (S-1 SAR) and Sentinel-2 multispectral instrument (S-2 MSI) data are currently a feasible way of mapping forest aboveground biomass (AGB) over large areas. Despite the extensive mapping of forest AGB by remote sensing, how to effectively combine different sensors data, selecting the proper statistical modelling method, and variable screening are still poorly understood. This paper presents a framework for Sentinel-based AGB estimation through the use of four variable screening techniques, namely, genetic algorithm (GA), least absolute shrinkage and selection operator (LASSO), boruta, and removal-based; and three statistical modelling methods including multiple linear regression (MLR), artificial neural network (ANN), and random forest (RF). These methods were examined across two forested sites with different levels of human activity (highly-degraded: HD and minorly-degraded: MD) in Zagros coppice oak forests. We used backscatter coefficients and texture metrics of S-1 SAR, in addition to raw bands, simple band ratios, vegetation indices and texture metrics of S-2 MSI to extract 53 explanatory variables. Our findings showed that GA and removal-based variable screening techniques outperformed the others and RF and MLR statistical modelling methods obtained the best results. The use of different variable screening techniques and modelling methods demonstrated higher accuracies of AGB estimates for the MD site compared to the HD site. S-2 MSI (Coefficient of determination (R2) = 0.76 and Root Mean Square Error (RMSE) = 35.08% of the mean) provided a higher accuracy than S-1 SAR (R2 = 0.42 and RMSE = 52.94% of the mean). Overall, the study demonstrates encouraging results in the retrieval and predictive mapping of the AGB of Zagros forests using the freely accessible Sentinel imagery. [ABSTRACT FROM AUTHOR]

Due to the spatial-temporal inadequacy of large-scale general circulation models (GCMs), linking large-scale GCM data with small-scale local climatic data has found great interest. In this paper, in order to downscale minimum and maximum temperatures and precipitation predictands, the performance of three statistical downscaling techniques including Long Ashton Research Station-Weather Generator (LARS-WG), statistical downscaling model (SDSM), and artificial neural network (ANN) was compared based on Intergovernmental Panel on Climate Change-Fifth Assessment Report (IPCC-AR5) in northwest Iran. For this purpose, a nonparametric test named Mann-Whitney test, Spearman correlation coefficient, and the root mean square error (RMSE) were utilized to assess the efficiency of downscaling models. To scrutinize the climate change impacts, periods of 1961–1990 and 1991–2005 were considered as the baseline and verification periods, respectively. The findings revealed the superior performance of the ANN model for minimum and maximum temperatures, while for precipitation predictand, the SDSM represented the best performance among the models. Simulation results for future temperature indicated an ascending trend as 0.1–1.3 °C, 0.3–1.7 °C, and 0.5–2.1 °C for LARS-WG, SDSM, and ANN techniques, respectively. On the other hand, simulation outputs for the precipitation indicated a descending trend of 10–30% in future precipitation of the region according to downscaling models under Representative Concentration Pathway 8.5 (RCP8.5) pessimistic scenario of Hadley Center Coupled Model version 3 (HadCM3) GCM model. [ABSTRACT FROM AUTHOR]

The aim of this paper is to investigate the ability of artificial neural network (ANN) models for post-processing the monthly precipitation forecasts under North American multi-model ensemble (NMME) project and proposing a new multi-model ensemble neural network (MME-NN) model. Monthly precipitation hindcasts of eight models from NMME project are considered in this study. Multi-layer perceptron neural networks are employed for post-processing the output of the models in comparison with PERSIANN-CDR climatology data. Also, utilizing a multi-criteria decision-making approach, NMME models are ranked for each month. The study is implemented over Iran and detailed discussions are provided. The results indicate that the skill of NMME models is different for each month and for each region of the country. Also, it is shown that the neural network outperforms all NMME models for all months. By using the ranking of the models, for each month, the NMME models are ordered based on their skill and a monthly rank is devoted for each model. [ABSTRACT FROM AUTHOR]

In recent years, new techniques and algorithms such as Artificial Neural Networks (ANNs), Fuzzy Inference Systems (FIS) and Genetic Algorithm (GA) have been used as alternative statistical tools in modeling and forecasting issues. These methods have been extensively used in the field of geosciences and atmospheric physics. The main purpose of this paper is to combine FIS and ANNs for local modeling of the ionosphere Total Electron Content (TEC) in Iran. An Adaptive Neuro-Fuzzy Inference System (ANFIS) is developed for TEC modeling. Also, Multi-Layer Perceptron ANN (MLP-ANN) and ANN based on Radial Base Functions (RBF) have been designed for analyzing ANFIS results. Observations of 29 Global Positioning System (GPS) stations from the Iranian Permanent GPS Network (IPGN) have been used in 3 different seasons in 2015 and 2016. These stations are located at geomagnetic low latitudes region. Out of these 29 stations, 24 stations for training and 5 stations for testing and validating were selected. The relative and absolute errors have been used to evaluate the accuracy of the proposed model. Also, the results of this paper are compared with the International Reference Ionosphere model (IRI2016). The maximum values of the average relative error for RBF, MLP-ANN, ANFIS and IRI2016 methods are 13.88%, 11.79%, 10.06%, and 18.34%, respectively. Also, the maximum values of the average absolute error for these methods are 2.38, 2.21, 1.5 and 3.36 TECU, respectively. Comparison of diurnal predicted TEC from the ANFIS, RBF, MLP-ANN and IRI2016 models with GPS-TEC revealed that the ANFIS provides more accurate predictions than the other methods in the test area. [ABSTRACT FROM AUTHOR]

Predictive models have been widely used in different engineering fields, as well as in petroleum engineering. Due to the development of high-performance computer systems, the accuracy and complexity of predictive models have been increased significantly. One of the common methods for prediction is artificial neural network (ANN). ANN models in combination with optimization algorithms provide a powerful and fast tool for the prediction and optimization of processes which take a large amount of time if they are simulated using common simulation technics. In the present paper, to predict penetration rate during drilling process, several ANN models were developed based on the data obtained from drilling of a gas well located in south of Iran. Regarding the R2 and RMSE values of the developed models, the best model was selected for prediction of penetration rate. In the next step, artificial bee colony algorithm was used for optimization of the parameters which are effective on rate of penetration (ROP). Results showed that the model is accurate enough for being used in the prediction and optimization of ROP in drilling operations. [ABSTRACT FROM AUTHOR]

In this paper, an attempt was made to find out two empirical relationships incorporating linear multivariate regression (LMR) and gene expression programming (GEP) for predicting the blast-induced ground vibration (BIGV) at the Sarcheshmeh copper mine in south of Iran. For this purpose, five types of effective parameters in the blasting operation including the distance from the blasting block, the burden, the spacing, the specific charge, and the charge per delay were considered as the input data while the output parameter was the BIGV. The correlation coefficient and root mean squared error for the LMR were 0.70 and 3.18 respectively, while the values for the GEP were 0.91 and 2.67 respectively. Also, for evaluating the validation of these two methods, a feed-forward artificial neural network (ANN) with a 5-20-1 structure has been used for predicting the BIGV. Comparisons of these parameters revealed that both methods successfully suggested two empirical relationships for predicting the BIGV in the case study. However, the GEP was found to be more reliable and more reasonable. [ABSTRACT FROM AUTHOR]

Tunnel construction in urban areas causes ground displacement which may distort and damage overlying buildings and municipal utilities. It is therefore extremely important to predict tunneling-induced ground movements in tunneling projects. To predict the tunneling-induced ground movements, artificial neural networks (ANNs) have been used as flexible non-linear approximation functions. These methods, however, have significant limitations that decrease their accuracy and applicability. To overcome these problems, the use of optimization algorithms to train ANNs is of advantage. In this paper, a hybrid particle swarm optimization (PSO) algorithm-based ANN is developed to predict the maximum surface settlement and inflection points in transverse and longitudinal directions. Subsequently, the transverse and longitudinal troughs were obtained by means of empirical equations and 3D surface settlement troughs were ploted. For this purpose, extensive data consisting of measured settlements from 123 settlement markers, geotechnical properties and tunneling parameters were collected from the Karaj Urban Railway Project in Iran. The optimum values of PSO parameters were determined with the help of sensitivity analysis. On the other hand, to find the optimal architecture of the network, trial-and-error method was used. The final hybrid model including eight inputs, a hidden layer and three outputs was used to predict transverse and longitudinal tunneling-induced ground movements. The results demonstrated that the proposed model can very accurately predict three-dimensional ground movements induced by tunneling. [ABSTRACT FROM AUTHOR]

The direct measurement of uniaxial compressive strength (UCS) as one of the main important rock engineering parameters is destructive, cumbersome, difficult and costly. Therefore, the prediction of this parameter using simpler, cheaper indirect methods is of interest. In this paper, the UCS was predicted using a developed hybrid intelligent model including generalized feedforward neural network (GFFN) incorporated with imperialist competitive algorithm (ICA). To find the optimum model, 197 sets including rock class, density, porosity, P-wave velocity, point load index and water absorption from almost all over quarries of Iran were compiled. The efficiency and performance of GFFN and hybrid ICA-GFFN models subjected to different error criteria and established confusion matrixes were compared to multilayer perceptron (MLP) and radial basis function (RBF) neural network models as well as conducted multivariate regression. The hybrid ICA-GFFN with 11.37%, 14.27% and 22.74% improvement in correct classification rate over than GFFN, RBF and MLP demonstrated superior predictability level. The results indicated that the developed ICA-GFFN model as a feasible and accurate enough tool can effectively be applied for UCS prediction purposes. Using the sensitivity analyses, the P-wave velocity and rock class were identified as the most and least influences factors on predicted UCS. [ABSTRACT FROM AUTHOR]

In this paper, artificial neural network (ANN) was used for statistically downscale the outputs of general circulation models (GCMs) to assess future changes of precipitation and mean temperature in Tabriz synoptic station at north-west of Iran. Since one of the significant subjects in statistical downscaling of GCMs is to select the most dominant large scale climate variables (predictors) among huge number of potential predictors, the predictors screening methods including decision tree, mutual information (MI) and correlation coefficient (CC) were used to statistically downscale mean monthly precipitation and temperature. Three GCMs were used, including Can-ESM2 and BNU-ESM from IPCC AR5 models and CGCM3 from IPCC AR4 models. The results of downscaling in the base period (1951–2000) indicated that among feature extraction methods decision tree had superiority to MI and CC techniques. Therefore, the future projection of precipitation and mean temperature during 2020–2060 was implemented using ANN-based simulation according to the most efficient downscaling model (i.e., decision tree-based calibration). Different results according to different GCMs and scenarios were obtained for precipitation projection. In this way, the Can-ESM2 model under RCP8.5 showed 29.78% decrease in annual precipitation and CGCM3 model under B1 indicated 1.06% increase of annual precipitation. Temperature projection outcomes denoted that annual mean temperature will increase over the region and the most increase in mean temperature was determined by BNU-ESM model under RCP8.5. [ABSTRACT FROM AUTHOR]

Highlights • The paper presents a practical method for assessing pavement layers condition. • Decreasing the limitation of using costly structural assessment devices (FWD). • Strong relation between structural parameters and pavement performance indices. • Project field survey was conducted, using FWD, RSP and visual survey (PASER). • The superiority of ANNs over regression models was investigated. Abstract Evaluation of pavement condition, which determines pavement maintenance and rehabilitation necessities, is inevitable using structural or non-structural methods. Since factors such as cost and time required for testing limit the use of structural assessment devices, the development of cost-effective methods should be investigated. In this paper, a practical solution has been presented for pavement structural evaluation which is considered as a useful method for assessing pavement layers condition and identifying rehabilitation needs. With this in mind, we developed a relationship between deflection bowl parameters derived from Falling Weight Deflectometer (FWD) and two pavement performance indices, International Roughness Index (IRI) and Pavement Surface Evaluation and Rating index (PASER), by the use of Artificial Neural Network (ANN) and regression models. To obtain the required data, project field surveys were conducted from 318 sections of the main roads of Kermanshah and Ilam provinces in Iran. The results show that our model provides a satisfactory correlation between IRI, PASER, and structural indices which are based on deflection measurements. By comparing the results of ANN and regression models, the superiority of ANN performance over non-intelligent models is appreciable. The findings of this study indicate that using both IRI and PASER indices leads to accurate structural pavement evaluation. [ABSTRACT FROM AUTHOR]

Predictions of sediment load are required in a wide spectrum of problems such as design of the dead volume of a dam, sediment transport in the river, design of stable channels, and dredging needs. Researchers have used the regression between sediment concentration and water discharge. Such relationships are obtained through the application of regression analysis in many studies. Unfortunately, in the classical regression approach to determine sediment concentration-water discharge relationships, internal uncertainties are not taken explicitly into consideration. Therefore, researchers look for non-linear methods to estimate sediment load such as artificial neural network (ANN) methods to solve non-linear problems. The main purpose of this paper is to optimize the ANN connection weights with novel social-based algorithm (SBA) to realize the sediment in Maroon river. The SBA tries to capture several people in different types of countries. They try to reach high levels. The approach illustrated feed-forward neural network optimization for sediment estimation of four Maroon river stations in Iran, which was called FF-SBA. Three inputs were presented in each station: length of river, discharge and debit. Sediment parameter on the same station is measured as the output parameter. Results of optimization algorithms such as the genetic algorithm, particle swarm optimization and imperialist competitive algorithm were compared with the SBA results, and it was found that the FF-SBA model exhibited more capability, flexibility, and accuracy in sediment training, testing, and forecasting steps for the Maroon river in Iran. [ABSTRACT FROM AUTHOR]

Energy as a production process input has an effective role on economic indicators such as gross domestic production (GDP). Limitations in fossil fuel and nuclear energy sources urge utilizing renewable energies. In this paper, the impact of renewable energy consumption on economic welfare indicators (i.e. GDP, GDP per capita, annual income of urban households, and annual income of rural households) is investigated. For this purpose, 41 annual data sets are collected, from 1971 to 2011, mostly from Iran's Statistical Yearbook and Iran's Balance Sheet. Artificial neural networks (ANNs) are used for forecasting the effect of renewable energy consumption on economic welfare indicators. Advantages in using the proposed ANN-based method are demonstrated by comparing its results with the multi-layer regression (MLR) model. The comparison between the artificial neural network and the multi-layer regression model demonstrates that the artificial neural network has more accurate results than the multi-layer regression model. Both ANN and MLR models show significant effect of using renewable energies on the economic welfare. Results demonstrate the importance of using the proposed model for policy makers in implementing new policies for renewable energies. The ANN prediction results show that GDP, GDP per capita, annual income of urban households, and annual income of rural households will grow by 35.63%, 62.59%, 167.61% and 143.19%, respectively, from 2007 to 2016. [ABSTRACT FROM AUTHOR]

Background: Forecasting methods are used in various fields including the health problems. This study aims to use the Artificial Neural Network (ANN) method for predicting coronavirus disease 2019 (COVID-19) cases in Iran. Materials and Methods: This is a descriptive, analytical, and comparative study to predict the time series of COVID-19 cases in Iran from May 2020 to May 2021. An ANN model was used for forecast ing, which had three Input, output, and intermediate layers. The network training was conducted by the Levenberg-Marquardt algorithm. The forecasting accuracy was measured by calculating the mean absolute percentage error. Results: The mean absolute error of the designed ANN model was 6 and its accuracy was 94%. Conclusion: The ANN has high accuracy in forecasting the number of COVID-19 cases in Iran. The outputs of this model can be used as a basis for decisions in controlling the COVID-19. [ABSTRACT FROM AUTHOR]

Introduction: Most heart diseases show symptoms on ECG, but diagnosing heart disease with ECG requires the knowledge and experience of medical specialized. Because these specialists may not always be available, it is necessary to design tools to diagnose heart disease in these situations. Objective: In this paper, a two-stage approach based on artificial neural networks is designed to diagnose heart disease using ECG information. Method: To design the proposed approach, first ECG information for 861 refers to a number of medical centers in Arak city is collected and and data consulted is proccesed by specialists. Then 154 features from ECG as input variables in proposed approach has been specified. In the first stage of approach, an artificial neural network is designed to detect the status of the ECG in two situation as usable and unusable. Then, in the second stage, using the usable ECG information, an artificial neural network is designed to diagnose the presence or absence of heart disease. Finally, the performance of the two-stage approach is evaluated and its accuracy and precision in determining the status of the ECG as well as the disease status is determined. Results In the proposed approach, the neural network for the determining of ECG status has an precision of 97.1% and an accuracy of 97.3%, and also the neural network for the diagnosis of heart disease has an precision of 95.8% and an accuracy of 95.4%. Conclusion: Considering the high effeciency of the proposed approach in the determining of ECG status and also diagnosing heart disease, it is possible to use this approach as a reliable assistant to assist the treatment staff. [ABSTRACT FROM AUTHOR]

Determination of petrophysical parameters by using available data has a specific importance in exploration and production studies for oil and gas industries. Modeling of corrected permeability as a petrophysical parameter can help in decision making processes. The objective of this study is to construct a comprehensive and quantitative characterization of a carbonate gas reservoir in marine gas field. Artificial neural network is applied for prediction of permeability in accordance with other petrophysical parameters at well location. Correlation coefficient for this method is 84 %. In the study, the geological reservoir model is developed in two steps: First, the structure skeleton of the field is constructed, and then, reservoir property is distributed within it by applying new stochastic methods. Permeability is modeled by three techniques: kriging, sequential Gaussian simulation (SGS) and collocated co-simulation using modeled effective porosity as 3D secondary variable. This paper enhances the characterization of the reservoir by improving the modeling of permeability through a new algorithm called collocated co-simulation. Kriging is very simple in modeling the reservoir permeability, and also, original distribution of the data changes considerably in this model. In addition, the SGS model is noisy and heterogeneous, but it retains the original distribution of the data. However, the addition of a 3D secondary variable in third method resulted in a much more reliable model of permeability. [ABSTRACT FROM AUTHOR]

Background: Psychopathology research mainly focused on the cross-sectional and longitudinal associations between personality and psychiatric disorders without considering the moment-to-moment dynamics of personality in response to environmental situations. The present study aimed to both cluster a young sample according to three mixed clinical conditions (poor sleep quality, depression, and somatization) and to predict the derived clusters by maladaptive personality traits and sex differences using a deep machine learning approach. Methods: A sample of 839 adults aged 18-40 years (64% female) from the west of Iran were clustered according to the mixed clinical conditions using the cluster analysis techniques. An Artificial Neural Network (ANN) modeling is used to predict the derived clusters by maladaptive personality traits and biological gender. A receiver operating characteristic (ROC) curve was used to identify independent variables with high sensitivity specific to the derived clusters. Results: The cluster analysis techniques suggested a fully stable and acceptable four-cluster solution for Depressed Poor Sleepers, Nonclinical Good Sleepers, Subclinical Poor Sleepers, and Clinical Poor Sleepers. The ANN model led to the identification of one hidden layer with two hidden units. The results of Area under the ROC Curve were relatively to completely acceptable, ranging from.726 to.855. Anhedonia, perceptual dysregulation, depressivity, anxiousness, and unusual beliefs are the most valuable traits with importance higher than 70%. Conclusion: The machine learning approach can be well used to predict mixed clinical conditions by maladaptive personality traits. Future research can test the complexity of normal personality traits connected to mixed clinical conditions. [ABSTRACT FROM AUTHOR]

This article addresses the class imbalance problem in urban gain modelling (UGM) of Tabriz and Isfahan megacities in Iran by proposing novel cost-sensitive machine learning models, namely costsensitive support vector machine (CSVM), random forest (CRF) and artificial neural network (CANN). Random sampling, a frequently utilized method, fails to effectively tackle this issue by biasing models towards no change samples, which outnumber change samples. The results showed that CRF exhibited the highest accuracy (AUC = 0.560), followed by CANN (AUC = 0.557) and CSVM (AUC = 0.448) in Isfahan. In Tabriz, CRF (AUC = 0.809) and CANN (AUC = 0.818) excelled, outperforming balanced sampling models constructed with ANN, RF and SVM with the AUROC of ANN and RF boosted by 15% and 2% in validation. By emphasizing the significance of addressing class imbalance appropriately, this research highlights the improvement in modelling outcomes achievable through the cost-sensitive models especially in Tabriz case. [ABSTRACT FROM AUTHOR]

Locations prone to landslides must be identified and mapped to prevent landslide-related damage and casualties. Machine learning approaches have proven effective for such tasks and have thus been widely applied. However, owing to the rapid development of data-driven approaches, deep learning methods that can exhibit enhanced prediction accuracies have not been fully evaluated. Several researchers have compared different methods without optimizing them, whereas others optimized a single method using different algorithms and compared them. In this study, the performances of different fully optimized methods for landslide susceptibility mapping within the landslide-prone Kermanshah province of Iran were compared. The models, i.e., convolutional neural networks (CNNs), deep neural networks (DNNs), and support vector machine (SVM) frameworks were developed using 14 conditioning factors and a landslide inventory containing 110 historical landslide points. The models were optimized to maximize the area under the receiver operating characteristic curve (AUC), while maintaining their stability. The results showed that the CNN (accuracy = 0.88, root mean square error (RMSE) = 0.37220, and AUC = 0.88) outperformed the DNN (accuracy = 0.79, RMSE = 0.40364, and AUC = 0.82) and SVM (accuracy = 0.80, RMSE = 0.42827, and AUC = 0.80) models using the same testing dataset. Moreover, the CNN model exhibiting the highest robustness among the three models, given its smallest AUC difference between the training and testing datasets. Notably, the dataset used in this study had a low spatial accuracy and limited sample points, and thus, the CNN approach can be considered useful for susceptibility assessment in other landslide-prone regions worldwide, particularly areas with poor data quality and quantity. The most important conditioning factors for all models were rainfall and the distances from roads and drainages. [ABSTRACT FROM AUTHOR]

In this paper, a number of classical and intelligent methods, including interquartile, autoregressive integrated moving average (ARIMA), artificial neural network (ANN) and support vector machine (SVM), have been proposed to quantify potential thermal anomalies around the time of the 11 August 2012 Varzeghan, Iran, earthquake (Mw = 6.4). The duration of the data set, which is comprised of Aqua-MODIS land surface temperature (LST) night-time snapshot images, is 62 days. In order to quantify variations of LST data obtained from satellite images, the air temperature (AT) data derived from the meteorological station close to the earthquake epicenter has been taken into account. For the models examined here, results indicate the following: (i) ARIMA models, which are the most widely used in the time series community for short-term forecasting, are quickly and easily implemented, and can efficiently act through linear solutions, (ii) A multilayer perceptron (MLP) feed-forward neural network can be a suitable non-parametric method to detect the anomalous changes of a non-linear time series such as variations of LST. (iii) Since SVMs are often used due to their many advantages for classification and regression tasks, it can be shown that, if the difference between the predicted value using the SVM method and the observed value exceeds the pre-defined threshold value, then the observed value could be regarded as an anomaly. (iv) ANN and SVM methods could be powerful tools in modeling complex phenomena such as earthquake precursor time series where we may not know what the underlying data generating process is. There is good agreement in the results obtained from the different methods for quantifying potential anomalies in a given LST time series. This paper indicates that the detection of the potential thermal anomalies derive credibility from the overall efficiencies and potentialities of the four integrated methods. [ABSTRACT FROM AUTHOR]

Mining and related industries are widely considered as having unfavorable effects on environment in terms of magnitude and diversity. As a matter of fact, groundwater and soil pollution are noted to be the worst environmental problems related to the mining industry because of the pyrite oxidation, acid mine drainage generation, release and transport of the heavy metals. Acid mine drainage (AMD) containing heavy metals including Manganese (Mn), Copper (Cu), Lead (Pb), and Iron (Fe), is harmful for the human and aquatic environment. Metal pollution assessment using cost-effective methods, will be a crucial task in designing a remediation strategy. The aim of this paper is to predict the heavy metals included in the AMD using support vector machine (SVM). In addition, the obtained results are compared with those of the general regression neural network (GRNN). Results indicated that the SVM approach is faster and is more precise than the GRNN method in prediction of heavy metals. The results obtained from this paper can be considered as an easy and cost-effective method to monitor groundwater and surface water affected by AMD. [ABSTRACT FROM AUTHOR]

Available water quality indices have some limitations such as incorporating a limited number of water quality variables and providing deterministic outputs. This paper presents a hybrid probabilistic water quality index by utilizing fuzzy inference systems (FIS), Bayesian networks (BNs), and probabilistic neural networks (PNNs). The outputs of two traditional water quality indices, namely the indices proposed by the National Sanitation Foundation and the Canadian Council of Ministers of the Environment, are selected as inputs of the FIS. The FIS is trained based on the opinions of several water quality experts. Then the trained FIS is used in a Monte Carlo analysis to provide the required input-output data for training both the BN and PNN. The trained BN and PNN can be used for probabilistic water quality assessment using water quality monitoring data. The efficiency and applicability of the proposed methodology is evaluated using water quality data obtained from water quality monitoring system of the Jajrood River in Iran. [ABSTRACT FROM AUTHOR]

In this paper, a recursive training procedure with forgetting factor is proposed for on-line calibration of temporal neural networks. The forgetting factor discounts old measurements through an on-line model calibration. The forgetting factor approach enables the recursive algorithm to reduce the effect of the older error data by multiplying the error data by a discounting factor. The proposed procedure is used to calibrate a temporal neural network for reservoir inflow modeling. The mean monthly inflow of the Karoon-III reservoir dam in the south-western part of Iran is used to test the performance of the proposed approach. An autoregressive moving average (ARMA) model is also applied to the same data. The temporal neural network, which is trained with the proposed approach, has shown a significant improvement in the forecast accuracy in comparison with the network trained by the conventional method. It is also demonstrated that the neural network trained with forgetting factor results in better forecasts compared to the statistical ARMA model, which has been calibrated through this approach. [ABSTRACT FROM AUTHOR]

Buildings account for a major part of Total Energy Consumption (TEC) in comparison to that of industry and other sections. The opening and envelope material can affect their TEC. Accordingly, this paper aims to study the effects of the window to external wall ratio (WWR) and the application of recycled panels as the building envelope on the total energy consumption in a one-floor residential building located in Iran and characterized by a semi-arid climate. To follow the sustainability criterion, we designed two concrete panels for the external walls' envelope including a porous concrete panel and recycled ash concrete panel. The WWR varies between 5% to 95% and the optimal WWRs are separately presented for all the months. To develop the models, we used Design Builder software which its simulations are validated via field observations. For all the panels, the least energy consumption is obtained when the WWR is 5%. However, due to lighting issues, the most optimal WWR is calculated as 45-55% based on the results of the numerical simulations. Further, it is proved that the recycled ash concrete panel outperforms the porous concrete panel in terms of minimum energy consumption. Hence, it is recommended to use eco-friendly material as the external walls envelop with the WWR below 50%. The numerical simulations provided 240 data points for each panel which is exploited to develop an ANN model. The results suggested that the ANN models predict the TEC based on the month and WWR with high accuracy. [ABSTRACT FROM AUTHOR]

This paper investigates the simultaneous use of in-situ hydrologic measurements in combination with two different artificial intelligent (AI) methods, namely, Adaptive Neuro Fuzzy Inference System (ANFIS) and Artificial Neural Network (ANN), for developing enhanced long-term streamflow forecasting models. To enhance the reliability of the proposed models' outputs, a sub-basin method using the regionalization approach is proposed. Furthermore, to accelerate the training process and achieve more accurate handling of seasonal changes, a parameter representing seasonal variations is introduced. The models are applied to the mountainous Talezang basin, southwestern Iran, for which there is a 14-year series of monthly in-situ data records and snow cover area data obtained from the Moderate Resolution Imaging Spectroradiometer (MODIS). The results indicate that the use of the sub-basin approach significantly improves both AI methods' performances. Moreover, it is deduced that the use of seasonal information and satellite data has a great impact on the model performance and accuracy. Comparing the long-term flow forecasts of both models showed that the ANFIS model is superior to the ANN. [ABSTRACT FROM AUTHOR]

The planning of future supplies of agricultural water is beset by uncertainties stemming from inaccuracies in general circulation models, assumed greenhouse gases emissions scenarios (GHGESs), imperfect models employed for estimating reservoir inflows and approximate methods for estimating agricultural water demand. The uncertainty of providing agricultural water under climate change was assessed, relying on simulations involving baseline (1971–2000) and future periods (2040–2069 and 2070–2099). Climatic variables were simulated using six atmosphere–ocean general circulation models (AOGCMs) driven by GHGESs A2 and B2 in the Aidoghmoush basin, Iran. Projection of reservoir inflow was performed using the IHACRES model and artificial neural network (ANNs). Agricultural water demand was calculated using the FAO–Penman–Monteith and Hargreaves-Samani (HS) methods. Eight modelling scenarios were considered based on combinations of AOGCMs, GHGESs, reservoir inflow and agricultural water demand projections. Reservoir operation rules were calculated with a particle swarm optimisation algorithm. The results show that agricultural water demand will increase in future periods compared with the baseline period. The operation rule derived from the combination of the HS and ANN models (under GHGES A2) showed the best performance in 2040–2069 by achieving the highest reliability (93%) of water supply. The operation rule derived from the combination of HS and ANN models (under GHGES B2) achieved the highest reliability (95%) of water supply in 2070–2099. The results provide adjusted reservoir operation rules under uncertainty caused by climate change and related impacts on water resources management. [ABSTRACT FROM AUTHOR]