Search

This paper employs machine learning algorithms to detect tax evasion and analyzes tax data. With the development of commercial businesses, traditional algorithms are not appropriate for solving the tax evasion detection problem. Hence, other algorithms with acceptable speed, precision, analysis, and data decisions must be used. In the case of assets and tax assessment, the integration of machine learning models with meta-heuristic algorithms increases accuracy due to optimal parameters. In this paper, intelligent machine learning algorithms are used to solve tax evasion detection. This research uses an improved particle swarm optimization (IPSO) algorithm to improve the multilayer perceptron neural network by finding the optimal weight and improving support vector machine (SVM) classifiers with optimal parameters. The IPSO-MLP and IPSO-SVM models using the IPSO algorithm are used as new models for tax evasion detection. Our proposed system applies the dataset collected from the general administration of tax affairs of West Azerbaijan province of Iran with 1500 samples for the tax evasion detection problem. The evaluations show that the IPSO-MLP model has a higher accuracy rate than the IPSO-SVM model and logistic regression. Moreover, the IPSO-MLP model has higher accuracy than SVM, Naive Bayes, k-nearest neighbor, C5.0 decision tree, and AdaBoost. The accuracy of IPSO-MLP and IPSO-SVM models is 93.68% and 92.24%, respectively. [ABSTRACT FROM AUTHOR]

Increase of nonlinear loads in industries has resulted in high levels of harmonic currents and consequently harmonic voltages in power networks. Harmonics have several negative effects such as higher energy losses and equipment life reduction. To reduce the levels of harmonics in power networks, different methods of harmonic suppression have been employed. The basic idea in all of these methods is to prevent harmonics from flowing into a power network at customer sides and the point of common coupling (PCC). Due to the costs, none of the existing mitigating methods result in a harmonic-free power system. The remaining harmonic currents, which rotate in a power network according to the system impedances, may not necessarily result in an optimum harmonic power flow in terms of harmonic undesirable results such as harmonic losses or harmonic over voltage/current due to possible resonances. This paper proposes a new method to control the flow of the remaining harmonics at a power system level such that the effects of harmonics such as losses are optimized. This task is achieved by the use of series active power filters controlled in a different manner from their conventional methods. In this new application, the series active power injects a controlled harmonic voltage into a power system (e.g., a line, transformer, or other elements) to control the harmonic current (power) flow such that the overall performance of the power system is improved in terms of harmonic effects. The series active power filter in this new application is named as harmonic power flow controller (HPFC). In this paper, the theory, structure, applications, and the basics of the control method of a HPFC are described. To investigate the effects of the HPFC on the power network harmonics, an HPFC is used in the 14-busbar IEEE test system. To make the proposal more practical, an HPFC is designed for Iran north-west transmission system to alleviate the harmonic problem in this region. Simulations are carried out to show the effectiveness of the HPFC. Simulation results show that the HPFC can control the harmonic currents (power) and voltage consequently. In this paper, several control algorithms for an HPFC are also considered to achieve the desired harmonic voltages levels. [ABSTRACT FROM AUTHOR]

In this study, a new water and power cogeneration plant, employing photovoltaic (PV) and photovoltaic–thermal (PVT) panels simultaneously, is designed and optimized for a village struggling to provide energy and potable water in Iran. The system includes a solar energy unit to generate clean electricity and heat, and a reverse osmosis unit to produce drinking water. Techno-economic optimization is performed by implementing a genetic algorithm, and a comprehensive water and energy management strategy is designed and presented in detail, expandable for future works. A new method, the logarithmic model, is used to calculate the depth of discharge (DOD) of lithium-ion batteries, which was previously a fixed and predetermined value in previous papers. Various indices, the constraints of the optimization process, are also introduced to measure the reliabilities of different units. The effects of the system components on total cost are investigated and a comprehensive sensitivity analysis is performed to find the best solution to increase the penetration of renewable-energy systems. The results reveal that considering the depth of discharge of batteries and water storage tank capacity as decision variables reduces the system's life-cycle cost (by 5.1% for changeable DODs). Furthermore, the simultaneous use of PV and PVT panels decreases the life-cycle cost considerably by ≤19% compared with the use of only PVT panels. Additionally, the cost of the battery causes a decrease in the cost of electricity storage and the cost of producing and storing fresh water. [ABSTRACT FROM AUTHOR]

Groundwater potential fields may be modeled by appropriate hydraulic equations governing aquifers, but these require a large amount of data not often available and subject to uncertainty. This paper approaches relative groundwater potential fields by integrating information derived from 11 data layers representing different distributed properties, but the emerging relativistic capability on deriving potential fields is not identical to hydraulics based one. Each of data layers has partial information and compared with one another, the layers are not homogeneous and not directly amenable to integration. One framework in the state-of-the-art of such problems is to use a catastrophe fuzzy membership function to capture and integrate the inherent information, but the decisions on the type of catastrophe function and the fuzzy-like membership intervals employ expert judgment. The paper builds on existing methodology to overcome this shortfall by the iterative identification of the type of catastrophe and using the Jenks optimization method to identify the break points in the data. The results project a new capability, according to which non-dimensional groundwater potential fields are an outcome of different catastrophes. For instance, in the study of non-dimensional groundwater potential fields of the aquifer along Sufichay (the River Sufi), the potential field combines contributions from two cusp catastrophes, one swallowtail catastrophe, two butterfly catastrophes and six wigwam catastrophes. The results provide anecdotal, but significant, evidence that the estimated potential field is fit for purpose. [ABSTRACT FROM AUTHOR]

Automation has attracted interest from the industry sector for its potential to improve energy efficiency, cost efficiency, and environmental performance. By elevating the LoA to the highest degree, associated costs will grow accordingly and its implementation will be far more complicated. This will also result in losing workers and decreasing environmental pollutants. On the other hand, increasing power consumption at high levels of automation leads to the production of greenhouse gases. This paper aims to increase the level of automation (LoA) considering the concept of sustainability. This study presents fuzzy multi-objective programming to determine the optimal LoA considering sustainability factors to achieve competitive advantages. To solve the model, the Zimmermann max-min approach was adopted and a cosmetics factory in Iran was chosen to optimize LoA according to this model. The results showed that it is possible to improve the LoA and also consider sustainability factors with the available resources without using the highest LoA. This study can help managers optimize the LoA in their organizations considering the current resources and sustainability issues, and control the company's return on investment and cost of overhead. They can run the model with every definition of LoA proposed till now. This research can benefit the environment and the workers' health in the production line by reducing environmental pollutants and prevent the dismissal of all personnel due to its negative social effects. It also reduces the risk of COVID-19 by minimizing the number of workers. So far, a mathematical model for selecting optimal LoA in the chemical industry considering sustainability has not been presented. [ABSTRACT FROM AUTHOR]

In this paper, the optimization algorithm based on the population as improved global particle swarm optimization is described and used for inverse modelling of two-dimensional magnetic field data. This algorithm is able to estimate the parameters of depth, shape factor, amplitude coefficient, magnetic inclination angle and origin point coordinates. To evaluate the efficiency of this method, the magnetic field of an artificial model was analysed, with and without added random noise. The results suggest that the proposed algorithm is capable of model parameter estimation with high accuracy. Accordingly, the improved global particle swarm optimization algorithm was used to analyse the magnetic field of the study area in the Ileh region in Iran located in Taybad city. The study area is very rich in terms of iron resources. The estimate for the study area is that the depth of the buried mass centre is about 114.9 m and its approximate shape is similar to a horizontal cylinder based on the calculated shape factor value which is 1.76. The calculated depth is an acceptable match with the average depth of drillings. [ABSTRACT FROM AUTHOR]

This paper develops and applies algorithms for optimally merging satellite precipitation products with rain-gauge precipitation for accurate rainfall estimation. The satellite-based precipitation products (SBPs) PERSIANN-CDR, TMPA-3B42, GPM-IMERG, and GSMaP MKV are combined and evaluated to generate accurate rainfall estimates. Daily satellite precipitation data are compared with corresponding station data to calculate the bias for the period 2014–2019. Three different algorithms are proposed whose adjustable parameters are optimally determined by solving constrained optimization algorithms to produce combinations of satellite-based precipitation products. The optimal combination is named optimally merged satellite-based precipitation (OMSBP). The root mean square error (RMSE), coefficient correlation (CC), and the Nash–Sutcliffe error (NSE) are employed to test the proposed method with precipitation data for the Tehran urban region, Iran. The spatially resolved results over the studied urban area establish that TMPA-3B42, with an average value MAE, MBE, and RMSE equal to 0.68 mm, − 0.31 mm, and 2.94 mm, leads to better estimates of precipitation than those of PERSIANN-CDR, IMERG, and GSMaP MKV. Moreover, algorithms alg7 and alg8 yielded better results with respect to the MAE and MBE, respectively. Lastly, algorithm alg3 produced better results than alg7 and alg8 based on the RMSE, NSE, and CC corresponding to precipitation predictions. [ABSTRACT FROM AUTHOR]

In this paper, exergy analysis of a steam power plant located in southern Iran named Zarand power plant has been studied. In order to optimize the performance of the Rankine cycle and achieve higher exergy efficiency, several parameters have been considered as decision variables. Knowing that there is the ability to change some of the parameters in the specific range in the process of electricity production in power plant, temperature and output pressure of the boiler and output pressure of four steps of extraction turbine have been selected as six decision variables. Also, exergy efficiency has been considered as the objective function. For this purpose, the exergy efficiency of the system is optimized using intelligent algorithms including bees, fireflies, and algorithm based on teaching and learning and they are compared with each other. The results show that in the case of suitable changes of decision variables and applying appropriate algorithms, exergy efficiency of the studied thermal power plant can be increased from 30.1% to 30.68047%, 30.70368%, and 30.70369%, respectively. It means using optimization algorithms of bees, fireflies, training-learning, exergy efficiency of the Rankine cycle of the studied power plant can be increased by 0.58047%, 0.60368%, and 0.60369%, respectively. [ABSTRACT FROM AUTHOR]

In this paper, a new thermodynamic cycle for power and fresh water production is presented, which includes MED-TVC desalinations and Allam cycles due to the important influence they have on the electric power industry in controlling and limiting greenhouse emissions. First, the Allam cycle analyzed and the appropriate location for heat-extraction identified to produce the required water vapor for the desalination system. It was determined that the heat site suitable for use in the desalination cycle is the heat from the outlet of the Compressor, which is estimated as 100 MW. The MED-TVC Desalination, one of the most suitable and most economical desalination, is used to combine the Allam cycle and desalination in the Kish district, located in the south of Iran. The proposed cycle is analyzed from the perspective of energy and exergy. The results show, the highest amount of exergy used to generate power in turbine and the amount of produced freshwater increase with increasing the capacity of Turbine. For this purpose genetic algorithm is used in two different scenarios to minimize and maximize the exergy destruction and produced fresh water respectively. The optimization of the system with genetic algorithm led to 18% decrease in total exergy destruction of the cycle in the first scenario and 7% decrease in the second optimization scenario. Furthermore, the efficiency of the cycle in first scenario and second scenario increased by 30% and 13% respectively. In the scenario optimization scheme, the amount of fresh water increased by 22%. [ABSTRACT FROM AUTHOR]

Copyright of Irrigation & Drainage is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In this paper, a wind/photovoltaic/battery/diesel hybrid system with hourly analysis during a year is modeled and optimized for different cities of Iran with various ranges of wind, solar and ambient temperature. A number of solar panels, wind turbines, batteries as well as nominal capacity of diesel engine are considered as design parameters. Fuel ratio and total annual cost (TAC) are selected as two simultaneous objective functions, and particle swarm optimization algorithm is used to find the optimum value of design parameter. The optimum results reveal that Zahedan has the significant lower TAC compared with other studied cases. Optimum cost increases 4.63%, 5.85%, 8.24%, 15.45% and 17.60%, respectively, in the Bushehr, Kerman, Tabriz, Tehran and Mashhad as compared with Zahedan. Optimum results reveal that annual cost extremely increases for the system with the absence of diesel engine (highest fuel ratio). For example, TAC increases at least 100% for the improvement of fuel ratio from 0.8 to 1 for all studied cities. The results also reveal a regular fluctuation in the battery charging and discharging is observed in the high available radiation cities such as Zahedan and Kerman. Furthermore, TAC increases in a linear manner, while fuel ratio increases in an exponentially manner with the increase in the number of PV panels in the optimum situation for all studied cases. [ABSTRACT FROM AUTHOR]

The special features of some old residential complexes make reconstructing a better option than rebuilding. The complexity of redesign issues, the ability of computers to solve problems, and the capability of evolutionary optimization techniques in architecture make the use of these methods a priority over traditional processes. This paper, while introducing Particle Swarm Optimization (PSO) as one of the swarm intelligence based algorithms, answers the question of how this algorithm can be used to redesign residential complexes. To achieve this, after reviewing the application of PSO algorithms in architectural space planning, the redesign criteria and constraints was divided into four categories; including primary design specifications, contact-related criteria, designer-related criteria and redesign-related constraints. After the quantification process of these criteria, how to implement the algorithm to achieve optimal plans for each of the five plan types available in high-rise apartment complex in Mashhad, Iran, was shown as a case study. [ABSTRACT FROM AUTHOR]

Frequent land-use changes in urban areas require an efficient and dynamic approach to reform and update detailed plans by re-arrangement of surrounding land-uses in case of change in one or several urban land-uses. However, re-arrangement of land-uses is problematic, since a variety of conflicting criteria must be considered and satisfied. This paper proposes and examines a two-step approach to resolve the issue. The first step adopts a multi-objective optimization technique to obtain an optimal arrangement of surrounding land-uses in case of change in one or several urban land-uses, whereas the second step uses clustering analysis to produce appropriate solutions for decision makers from the outputs of the first step. To present and assess the approach, a case study was conducted in Tehran, the capital of Iran. To satisfy the first step, four conflicting objective functions including maximization of consistency, maximization of dependency, maximization of suitability and maximization of compactness were defined and optimized using non-dominated sorting genetic algorithm. Per-capita demand was also employed as a constraint in the optimization process. Clustering analysis based on ant colony optimization was used to satisfy the second step. The results of the optimization were satisfactory both from a convergence and from a repeatability point of view. Furthermore, the objective functions of optimized arrangements were better than existing land-use arrangement in the area, with the per-capita demand deficiency significantly compensated. The approach was also communicated to urban planners in order to assess its usefulness. In conclusion, the proposed approach can extensively support and facilitate decision making of urban planners and policy makers in reforming and updating existing detailed plans after land-use changes. [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]

This paper provides an integrated framework based on statistical tests, time series neural network and improved multi-layer perceptron neural network (MLP) with novel meta-heuristic algorithms in order to obtain best prediction of dairy product demand (DPD) in Iran. At first, a series of economic and social indicators that seemed to be effective in the demand for dairy products is identified. Then, the ineffective indices are eliminated by using Pearson correlation coefficient, and statistically significant variables are determined. Then, MLP is improved with the help of novel meta-heuristic algorithms such as gray wolf optimization and cultural algorithm. The designed hybrid method is used to predict the DPD in Iran by using data from 2013 to 2017. The results show that the MLP offers 71.9% of the coefficient of determination, which is better compared to the other two methods if no improvement is achieved. [ABSTRACT FROM AUTHOR]

Credit allocation through the usage of Portfolio optimization mainly seeks to maximize return and minimize the risk of the portfolio; but there are other important issues including sustainable development which is important for government/public sectors. This paper presents a novel credit allocation approach based on portfolio optimization and investigates the effects of selected indicators of sustainable development on credit allocation. In order to evaluate this case study, constraint mean-variance was used as the extension of Markowitz portfolio theory. Selected indicators were modeled as the mathematical model's objectives and constraints. In order to show the applicability of the model, experimental results were given based on credit allocation data for National Development Fund of Iran (NDFI). The results show that sustainable development selected indicators exacerbate the return of NDFI portfolio from one side and from the other side, its effect on NDFI risk is somewhat similar but lighter. [ABSTRACT FROM AUTHOR]

Purpose – The purpose of this paper is to develop a new suit sizing system based on up-dated data, using data mining techniques, to improve the final quality and reduce the waste of fabric. This paper aims to investigate the effect of data reduction on the final fitness of the sizing chart. Design/methodology/approach – Principal component analysis is applied to reduce the sizing variables, non-hierarchical clustering approach is used to segment the heterogeneous population to more homogeneous one, and the aggregate loss of fitness is used to evaluate the resulted sizing chart. Findings – The results show that, when principal component analysis reduces the ten sizing variables to two main components, the final fitness for the resulted sizing chart is the best. These two main components are height and circumference. The hierarchical clustering approach could effectively group all body type to seven clusters. The resulted sizing chart could be used as a reference for suit manufacturers. Practical implications – Due to wide differences in race, nutrition and climate, people who live in different countries have their own body size; also, most of current sizing systems are out-dated, so there is an urgent need to develop a new sizing system. Due to the growing rate of globalization, the final results will be useful for those companies wanting to connect to global business chains. Originality/value – This work introduces the first suit sizing systems, based on data mining, for Iranian males, that has more fitness in comparison to the current sizing chart. The effect of the number of principal components on the final fitness of a sizing system is introduced as an innovative way, to avoid losing useful data during data reduction process with principal component analysis. [ABSTRACT FROM AUTHOR]

Stochastic dual dynamic programming (SDDP) is a widely used technique for operation optimization of large-scale hydropower systems in which reservoir inflow uncertainty is modeled with discrete scenarios produced by statistical time series models, such as the family of periodic auto-regressive (PAR) models. It is a common practice in statistical modeling of hydrologic time series to fit a well-known probability distribution (usually normal distribution) to the data by applying proper transformation. Box-Cox transformation is a commonly used transformation in the case of normal distribution fitting. The convexity requirement of SDDP means that nonlinearly transformed time series cannot be used for statistical inflow model calibration. In this paper, a linear approximation is proposed to estimate the expected value of the next stage inflow. In the proposed approach, next-stage inflows are estimated by a model that uses transformed time series. Furthermore, using the proposed linear approximation, it is shown that it is possible to utilize the time series transformed by Box-Cox transformation for scenario generation in SDDP. The Karoon multireservoir system in Iran has been used as a case study in order to show the effectiveness of the proposed method. Some concluding remarks have also been provided by comparing the results of the two SDDP models, with and without the proposed linear approximation. [ABSTRACT FROM AUTHOR]

The distillation tower's reboiler is one of the largest energy consumers in petrochemical facilities, and reducing its energy consumption is a crucial issue. This study proposes two optimal methods, namely Direct Vapor Recompression (DVR) and External Vapor Recompression (EVR), to reduce the consumption of cold and hot utilities in a petrochemical deethanizer tower. The Pars petrochemical in Iran is taken as a case study, and the proposed methods are compared with the base case using energy, exergy, and economic approaches, simulated through Aspen HYSYS software in the steady-state design conditions. Exergy analysis reveals that the EVR and DVR methods reduce the exergy destruction of the deethanizer tower by about 70.06 % and 67.29 %, respectively, compared to the base case. Moreover, the EVR method allows for complete recycling of low-pressure vapor, reducing the total exergy destruction rate from 0.871 to 0.261 GJ/tethane. The feed separation cost for the base case, DVR, and EVR are estimated to be around 28 $/kgfeed, 21.57 $/kgfeed, and 21.14 $/kgfeed, respectively. The EVR method results in reduced utility and ethane separation cost rates from 5.153 to 3.274 $/tethane and 17.64 to 15.78 $/year. Overall, the findings suggest that both DVR and EVR methods are effective in reducing the energy consumption and costs associated with deethanizer tower operations. Moreover, real-time optimization techniques can be developed to monitor and adjust the deethanizer tower's operating parameters, such as feed flow rate, reboiler duty, and reflux ratio. [ABSTRACT FROM AUTHOR]

Flight network optimization, one of the airspace planning challenges, effectively manages airspace resources toward increasing airspace capacity and reducing air traffic congestion. In this paper, the structure of the air transport network is analyzed with a multi-objective genetic algorithm to reduce the number of airways and to aggregate the passengers and also to reduce route changes and the travel time fortravelers. The proposed topology model of this study is based on the combination of two topologies – point-to-point and hub-and-spoke – with multiple goals for decreasing in airways and travel length per passenger and also to reach the minimum number of air stops per passenger. Four state-of-the-art Multi-objective Genetic Algorithms (MOGAs) are considered for comparison studies and are tested and assessed in data of the Iran airline industry in 2018, as an experiment to real-world applications. Using the combination of point-to-point and hub-and-spoke topologies can improve the performance of the MOGA to solve a network-wide flight trajectory planning. Based on Iran airline traffic patterns in 2018, the proposed model successfully decreased 50.8% of air routes (184 air routes) compared to the current situations while the average travel length and the average changes in routes were increased up to 13.8% (about 100 km) and up to 18%, respectively. The proposed model also suggests that the current air routes of Iran can be decreased to 24.7% (89 airways) if the travel length and the number of changes increase up to 4.5% (32 km) and 5%, respectively. The simulation results show the potential benefits of the proposed model and the advantages of it. Optimizing the structure of the flight network can significantly reduce operational cost while ensuring the operation safety. According to the results, the multi-objective optimization model is successfully able to precisely design the efficiently optimized airline topologies. [ABSTRACT FROM AUTHOR]

This paper addresses a possible decrease in flood damages by using structural methods and determines proper locations (layout) to construct protective levees and height of levees (design of levees) in high-risk areas. Because of discontinuity of the objective function and a large number of decision variables, the optimization uses the genetic algorithm (GA). The simulation of the region is carried out with the Hydrologic Engineering Center's River Analysis System (HEC-RAS) model. The GA is employed to maximize the benefit of flood control and also to minimize the cost of protective levees' construction. Thus, the fitness function of the algorithm maximizes the net benefit of the project. After a sensitivity analysis, mutation and crossover probability are assumed to be 0.03 and 0.7, respectively. Thus, 1,000 generations and 98 chromosomes for each run are considered. The optimization model is run 5 times for floods with return periods of 50 and 100 years. Furthermore, the algorithm is used to evaluate flood damages in the Sarm and Khoor Abad River, located in the Qom province of Iran. Project net benefits resulting from the optimization model for rivers using 100-year flood exceed those for a 50-year flood. Results indicate that construction of protective levees reduces the rate of damages up to 99% in comparison with a nonconstruction of levees scenario. By taking into account the construction cost of levees, net benefits decrease by 0.97% and 1.1% for floods with 50-year and 100-year return periods, respectively. [ABSTRACT FROM AUTHOR]

This paper combines optimization (LINGO) and simulation (HEC-ResSim) models to determine monthly operating rules for the Zayandeh Rud Reservoir system in Iran. Based on the optimized flow determined in the single-objective framework, system behaviour was simulated over 47 years. The results show that optimizing the operation of Zayandeh Rud Reservoir could increase its storage by 88.9% and increase the reliability index of regulated water for all downstream demands by over 10%. [ABSTRACT FROM AUTHOR]

Meta-heuristic algorithms, such as the genetic algorithm and ant colony optimization, have received considerable attention in recent years due to their higher ability for solving difficult engineering optimization problems. This paper employs these techniques for estimating parameters of commonly used flood frequency distributions, and compares them with some conventional methods such as maximum likelihood, moments and probability weighted moments using annual maximum discharge data of 14 rivers from East-Azarbaijan, Iran. The results indicate that both the genetic algorithm and ant colony optimization are suitable parameter estimation alternatives. Also, the results of Monte Carlo simulation for various sample sizes, ranging from 20 to 100, demonstrate that the meta-heuristic algorithms yield accurate quantile estimates. [ABSTRACT FROM AUTHOR]

A common method for assessing the energy potential of hydropower systems in Iran is the sequential streamflow routing with control on the energy-yield reliability. The method results in developing a reliability-based simulation (RBS) model that is used to analyze single-reservoir hydropower systems. In most of the cascade hydropower systems in the country, a single-reservoir RBS model is usually employed in the design and operation of each of the systems reservoirs. This paper presents a multireservoir RBS model considering the integrated operation of the systems. The model employs the general algorithm of the single-reservoir RBS model; however, with a single-period optimization submodel in determining releases from reservoirs during the system simulation. The objective function of the submodels minimizes the sum of reservoir releases and/or maximizes the sum of reservoir storages in each of the time periods, subject to a reliability constraint on the system’s energy yield. The single and multireservoir RBS models are applied in the Khersan hydropower system located in Iran as a case study. The multireservoir RBS, compared to the single-reservoir model, results in 7.9% excess firm-energy yield in reliability of 90%. [ABSTRACT FROM AUTHOR]

Identifying railway capacity is an important task that can identify ‘in principal’ whether the network can handle an intended traffic flow, and whether there is any free capacity left for additional train services. Capacity determination techniques can also be used to identify how best to improve an existing network, and at least cost. In this article, an optimization approach has been applied to a case study of the Iran national railway, in order to identify its current capacity and to optimally expand it given a variety of technical conditions. This railway is very important in Iran and will be upgraded extensively in the coming years. Hence, the conclusions in this article may help in that endeavor. A sensitivity analysis is recommended to evaluate a wider range of possible scenarios. Hence, more useful lower and upper bounds can be provided for the performance of the system. [ABSTRACT FROM AUTHOR]

This paper is an effort to analyse Iran's oil production policy during the last 15 years of the Shah's regime. The particular question the paper attempts to answer is whether oil resources were overextracted during that period.
Analysis is performed in a welfare maximization framework utilizing dynamic programming and classical optimization techniques. The following two alternatives regarding the economic decision making process are examined in this analysis: first, as the official documents of the previous regime indicate, economic decisions were made through a national planning exercise; and second, as the authorities of the new regime argue, the main economic decisions were made by the Shah himself. However, the methodology of the paper remains rather unconventional in the sense that it does not follow the usual procedure of choosing an objective function and computing the optimal policy on this ground, but, it studies the historical behaviour of the decision maker to derive implications regarding the possible objectives which he has pursued. [ABSTRACT FROM AUTHOR]

Inherent hazards such as landslides pose a threat to human life and may inflict significant harm on the surrounding ecosystem. For planning, controlling, and avoiding landslide situations to minimize damages, a landslide susceptibility map is necessary. As a consequence of this, the current research makes use of a methodical approach and upgraded algorithms to identify and forecast locations that are susceptible to landslides. When it comes to problems associated with landslides, standard optimization techniques have been used quite a bit. This study presents a novel approach to the development of an artificial neural network (ANN) in the Iranian region of Kurdistan by using the cuckoo optimization algorithm (COA) and the SailFish optimizer (SFO) as metaheuristic approaches. In order to maximize the computational properties of these algorithms and depict a new kind of swarm intelligence, a multi-layer perceptron (MLP) neural network is used in the synthesis process. The findings of the landslide hazard maps were checked and compared using actual landslide sites. There were 1072 landslides shown on the inventory map. There was a 70:30 split between training and testing locations at random. Model input was narrowed down to 16 different landslide qualifying variables, namely elevation, slope aspect, slope angle, NDVI, distance to fault, plan curvature, profile curvature, rainfall, distance from river, distance to road, SPI, STI, TRI, TWI, land use, and geology. All of these parameters were considered to be important in determining the likelihood of a landslide occurring. The area under the curve (AUC) criterion was used to evaluate the accuracy of the probabilistic models that were put into use. Incidentally, the calculated comparable AUCs were as follows: 0.797, 0.789, 0.784, 0.779, 0.763, 0.758, 0.749, 0.740, 0.725, and 0.716 for COA-MLP, and 0.719, 0.695, 0.682, 0.675, 0.671, 0.670, 0.662, and 0.650 for SFO-MLP. The greatest hybrid model for forecasting landslide detection corresponds to the COA-MLP model, and it has a swarm size of four hundred people. As a consequence, the findings demonstrated that these two models had an effective performance for ANN-MLP optimization. Taking into consideration this evaluation, the hybrid models that were provided are trustworthy for the modeling of landslide susceptibility. As a result, the map of vulnerability that was developed can be utilized for hazardous design and increased planners' knowledge of dangerous locations. [ABSTRACT FROM AUTHOR]

One of the attractive issues in Data Envelopment Analysis (DEA) literature is to find the anchor points of the production possibility set (PPS). Each extreme efficient unit which is located on the intersection of the strong and weak efficient frontiers of the PPS, is called an anchor point. In the other word, a decision making unit (DMU) is an anchor point, if there is at least one supporting hyperplane at the unit under consideration, in the situation that some components of its gradient vector are equal to zero, and so some input or output factors do not play any role in the performance of that unit. This study presents a new method to identify the anchor points of the PPS under the variable returns to scale (VRS) assumption and in the presence of the uncertain data. The proposed method is based on the robust optimization technique and finding the weak and strong defining supporting hyperplanes passing through the unit under evaluation. The potentially of the proposed method is illustrated by a data set, includes 20 banks in Iran. [ABSTRACT FROM AUTHOR]

The successful application of hydrological models relies on careful calibration and uncertainty analysis. However, there are many different calibration/uncertainty analysis algorithms, and each could be run with different objective functions. In this paper, we highlight the fact that each combination of optimization algorithm-objective functions may lead to a different set of optimum parameters, while having the same performance; this makes the interpretation of dominant hydrological processes in a watershed highly uncertain. We used three different optimization algorithms (SUFI-2, GLUE, and PSO), and eight different objective functions (R², bR², NSE, MNS, RSR, SSQR, KGE, and PBIAS) in a SWAT model to calibrate the monthly discharges in two watersheds in Iran. The results show that all three algorithms, using the same objective function, produced acceptable calibration results; however, with significantly different parameter ranges. Similarly, an algorithm using different objective functions also produced acceptable calibration results, but with different parameter ranges. The different calibrated parameter ranges consequently resulted in significantly different water resource estimates. Hence, the parameters and the outputs that they produce in a calibrated model are "conditioned" on the choices of the optimization algorithm and objective function. This adds another level of non-negligible uncertainty to watershed models, calling for more attention and investigation in this area. [ABSTRACT FROM AUTHOR]

Regarding evaluating disaster risks in Iran's West Kurdistan area, the multi-layer perceptron (MLP) neural network was upgraded with two novel techniques: backtracking search algorithm (BSA) and biogeography-based optimization (BBO). Utilizing 16 landslide conditioning elements such as elevation (aspect), plan (curve), profile (curvature), geology, NDVI (land use), slope (degree), stream power index (SPI), topographic wetness index (TWI), rainfall, and sediment transport index (STI), and 504 landslides as target variables, a large geographic database is constructed. Applying the techniques mentioned above to the synthesis of the MLP results in the suggested BBO-MLP and BSA-MLP ensembles. As accuracy standards, we benefit from mean absolute error, mean square error, and area under the receiving operating characteristic curve to assess the utilized models, we have also designed a scoring system. The MLP's accuracy increases thanks to the application of the BBO and BSA algorithms. Comparing the BBO with the BSA, we find that the former achieves higher average MLP optimization ranks (20, 15, and 14). A further finding showed that the BBO is superior to the BSA at maximizing the MLP. [ABSTRACT FROM AUTHOR]

One of the serious challenges in financial and credit institutions is the reform of the financial portfolio of branches with negative returns. The financial portfolio of banks has a combined structure of deposit attraction and investment, the main purpose of this study is to modify the deposit portfolio and facilities of branches so that the outcome of income and expenses tends towards positive returns. Inspired by the basic model proposed by Markowitz [1], this study provides a model for financial and credit institutions tailored to their needs. model parameters are: The current portfolio status of a branch, along with other factors that affect portfolio performance. model variables are: Changes that will be made to the numerical values of the initial portfolio to modify the model from negative to positive returns. In order to be able to modify the portfolio in multi-period, the one-period to multi-period model has been developed. Countries like Iran, where government decisions affect interest rates on deposits and loans, and they have different types of deposits and loans with different rates, it is necessary to establish a logical correspondence between different types of deposits and facilities. The main finding of this research is to provide a model that can improve the branches that have a portfolio with negative returns, with an achievable program, while observing the government and upstream constraints. The proposed models used for the Agricultural Bank of Iran, and the results have been analyzed. The results show that despite the restrictions that banks have to follow the orders of the government and the upstream, they have to create a domestic market and inject some kind of virtual deposit and loans, Reform the portfolio of branches with negative returns. [ABSTRACT FROM AUTHOR]

Regular optimization techniques have been widely used in landslide-related problems. This paper outlines two novel optimizations of artificial neural network (ANN) using grey wolf optimization (GWO) and biogeography-based optimization (BBO) metaheuristic algorithms in the Ardabil province, Iran. To this end, these algorithms are synthesized with a multi-layer perceptron (MLP) neural network for optimizing its computational parameters. The used spatial database consists of fourteen landslide conditioning factors, namely elevation, slope aspect, land use, plan curvature, profile curvature, soil type, distance to river, distance to road, distance to fault, rainfall, slope degree, stream power index (SPI), topographic wetness index (TWI) and lithology. 70% of the identified landslides are randomly selected to train the proposed models and the remaining 30% is used to evaluate the accuracy of them. Also, the frequency ratio theory is used to analyze the spatial interaction between the landslide and conditioning factors. Obtained values of area under the receiver operating characteristic curve, as well as mean square error and mean absolute error showed that both GWO and BBO hybrid algorithms could efficiently improve the learning capability of the MLP. Besides, the BBO-based ensemble surpasses other implemented models. [ABSTRACT FROM AUTHOR]

Predicting crop yield is an important issue for farmers. Food security is important for decision-makers. The agriculture industry can more accurately supply human demand for food if the crop yield is predicted accurately. Tomato is one of the most important crops so that 160 million tonnes of tomatoes are produced annually around the world. In this study, tomato yield based on data of 40 cities of Iran country including annual average temperature (T), relative humidity (RH), effective rainfall (R), wind speed (WS), and Evapotranspiration (EV) for the period of 1968–2018 was predicted using a new Bayesian model averaging (BMA). The paper's main innovation is the use of the new BMA so that it allows the modellers to quantify the uncertainty of model parameters and inputs simultaneously. For this aim, first, the multiple Adaptive neuro-fuzzy interface system (ANFIS) and multi-layer perceptron (MLP) were used for predicting crop yield. To train the ANFIS and MLP model, a new algorithm, namely, multi verse optimization algorithm (MOA) was used. Also, the ability of MOA was benchmarked against the particle swarm optimization (PSO), and firefly algorithm (FFA). In the next level, the new BMA used the outputs of the ANFIS-MOA, MLP-MOA, ANFIS, FFA, MLP-FFA, ANFIS-PSO, MLP-PSO, ANFIS, and MLP for predicting tomato yield in an ensemble framework. The five- input combination of RH, T, and R, WS, and EV gave the best result. The mean absolute error (MAE) of the BMA in the testing level was 20.12 (Ton/ha) while it was 24.12, 24.45, 24.67, 25.12, 29.12, 30.12, 31.12, and 33.45 for the ANFIS-MOA, MLP-MOA, ANFIS-FFA, MLP-FFA, ANFIS-PSO, MLP-PSO, ANFIS, and MLP models. Regarding the results of uncertainty analysis, the uncertainty of BMA was lower than those of the ANFIS-MOA, MLP-MOA, ANFIS-FFA, MLP-FFA, ANFIS-PSO, MLP-PSO, ANFIS, and MLP models while the MLP model provided the highest uncertainty. The results of this study indicated that BMA using multiple MLP and ANFIS model was useful for predicting tomato yield. [ABSTRACT FROM AUTHOR]

A fuzzy multi-objective optimisation model was investigated for water quality management in a river under uncertain conditions. In this study, to deal with multiple pollutants simultaneously, the National Sanitation Foundation's water quality index was considered as one of the model's objective functions based on fuzzy set theory. This made it possible to investigate the overall effect of uncertainties on simultaneous changes. Another objective function was the total treatment costs for wastewater discharged into the river. A water quality simulation model and a non-dominated-archiving ant colony optimisation algorithm were used to determine the values of water quality parameters and the model's optimal solutions, respectively. Furthermore, a simulation–optimisation approach was adopted for facilitating the problem-solving process and applied to a hypothetical case study resembling a river system in Iran. The results show that the proposed model significantly reduced the total wastewater treatment costs compared with a similar single-objective model with a more cautious and a cost-effective approach. Although the treatment costs were increased compared with the similar deterministic model, more feasible approach was taken by considering the uncertainties associated with the objectives. With suitable modifications, the model could be easily adapted for other river systems. [ABSTRACT FROM AUTHOR]

The Angstrom–Prescott (A–P) model is widely suggested for estimating solar radiation (Rs) in areas without measured or deficiency of data. The aim of this research was calibration and validation of the coefficients of the A–P model at six meteorological stations across arid and semi-arid regions of Iran. This model has improved by adding the air temperature and relative humidity terms. Besides, the coefficients of the A–P model and improved models have calibrated using some optimization algorithms including Harmony Search (HS) and Shuffled Complex Evolution (SCE). Performance indices, i.e., Root Mean Square Error (RMSE), Mean Bias Error, and coefficient of determination (R2) have used to analyze the models ability in estimating Rs. The results indicated that the performance of the A–P model had more precision and less error than improved models in all the stations. In addition, the best results have obtained for the A–P model with the SCE algorithm. The RMSE varies between 0.82 and 2.67 MJ m−2 day−1 for the A–P model with the SCE algorithm in the calibration phase. In the SCE algorithm, the values of RMSE had decreased about 4% and 7% for Mashhad and Kerman stations in the calibration phase compared to the HS algorithm, respectively. [ABSTRACT FROM AUTHOR]

Monitoring and assessment of groundwater quality (GWQ) as an important freshwater source for drinking purposes in urban and rural regions of developing countries due to rapidly increasing contamination is one of the concerns of water managers. Therefore, developing an efficient intelligent model for analyzing GWQ could help hydro-environmental engineers for sustainable water supply. The current research investigated the applicability of a novel nature-inspired optimization algorithm hybridized with multi-layer perceptron artificial neural network based on gray wolf optimization (GWO) for estimating dissolved oxygen (DO) total dissolved solid (TDS) and turbidity parameters at Asadabad Plain, Iran, and results are compared with the stand-alone multi-layer perceptron artificial neural network (MLPANN), generalized regression neural network (GRNN), and multiple linear regression (MLR) approaches. Evaluation of performance of models is carried out using various statistical indices like relative root mean square error, Nash-Sutcliffe efficiency, and correlation coefficient. Based on the results obtained, it is found that the hybrid GWO-MLPANN is a beneficial GWQ forecasting tool in accordance to high performance accuracy. Also, the study found that the superiority of the applied meta-heuristic algorithm (GWO) in improving the performance accuracy of the stand-alone artificial intelligence techniques in modeling the GWQ parameters. [ABSTRACT FROM AUTHOR]

Due to the threat and increasing trend to diabetes, different approaches to diagnose it have been proposed, so that classification is one of the main techniques. In this article ultimate aim is designing a novel system to diagnose diabetes. To this end, we use an ensemble classifier to apply support vector machine (SVM), k-nearest neighbor (KNN), and whale optimization algorithm (WOA). WOA is responsible for generating weights for each classifier to improve the accuracy of the diabetes classification. For our empirical study, we gathered a dataset of diabetes from medical centers in Iran. The implementation results showed that the designed ensemble classifier achieved the accuracy rate of 83%, which means it improved the accuracy of the best preceding classifier about 5%. Moreover, the designed ensemble classifier based on WOA improved the accuracy about 1% in comparison with PSO that is preceding the WOA in terms of accuracy level. [ABSTRACT FROM AUTHOR]

Absorption chillers are one of the most used equipment in industrial, commercial, and domestic applications. For the places where high cooling is required, they are utilized in a network to perform the cooling demand. The main objective of the current study was to find the optimum operating conditions of a network of steam absorption chillers according to energy and economic viewpoints. Firstly, energy and economic analysis and modelling of the absorption chiller network were carried out to have a deep understanding of the network and investigate the effects of operating conditions. Finally, the particle swarm optimization search algorithm was employed to find an optimum levelized total costs of the plant. The absorption chiller network plant of the Marun Petrochemical Complex in Iran was selected as a case study. To verify the simulation results, the outputs of energy modelling were compared with the measured values. The comparison with experimental results indicated that the developed model could predict the working condition of the absorption chiller network with high accuracy. The economic analysis results revealed that the levelized total costs of the plant is 1730 $/kW and the pay-back period is three years. The optimization findings indicated that working at optimal conditions reduces the levelized total costs of the plant by 8.5%, compared to the design condition. [ABSTRACT FROM AUTHOR]

Abstract: In this paper, we solve the well-known conditional and unconditional -center problem using a modified harmony search algorithm. This music inspired algorithm is a simple meta-heuristic that was proposed recently for solving combinatorial and large-scale engineering and optimization problems. This algorithm is applicable to both discrete and continuous search spaces. We have tested the present algorithm on ORLIB and TSP test problems and compared the results of the classic harmony search approach to those of the modified harmony search method. We also present some results for other meta-heuristic algorithms including the variable neighborhood search, the Tabu search, and the scatter search. Finally, we utilize this location model to locate bicycle stations in the historic city of Isfahan in Iran. [Copyright &y& Elsevier]

Abstract: Although water and soil conservation activities reduce reservoir sedimentation, it is inevitable that reservoirs fed by rivers transporting high amounts of sediment will experience sedimentation. The Ghezel-Ozan and Shah-Roud rivers, which flow to the Sefid-Roud reservoir dam, are both highly sediment-laden and transport significant amounts of sediment in both bed load and suspended load forms to the reservoir. Hence, it seems that the only practical way to remove the sediment from the reservoir is to flush it out using the Chasse method. In the present paper, field measurements of Chasse operation characteristics taken in previous years are presented, and a numerical model that simulates this process is introduced. After calibrating the model using field measured data, the calculated results (for reservoir pressure flushing and released sediment volume) of the numerical model were compared with other measured data for the same Chasse operation and the results agree well. Finally, using the numerical simulation results, the best approaches to ensure highly effective flushing while conserving reservoir water are presented (at least for the Sefid-Roud dam). The operation of the bottom outlet gates, the shape of the output hydrograph, and the reservoir water level variation during flushing were optimized. In addition, the numerical model and related parameters, which need to be calibrated, are discussed. [Copyright &y& Elsevier]

Abstract: In the absence of either satellite ephemeris information or camera model, rational functions are introduced by many investigators as mathematical model for image to ground coordinate system transformation. The dependency of this method on many ground control points (GCPs), numerical complexity, particularly terms selection, can be regarded as the most known disadvantages of rational functions. This paper presents a mathematical solution to overcome these problems. Genetic algorithms are used as an intelligent method for optimum rational function terms selection. The results from an experimental test carried out over a test field in Iran are presented as utilizing an IKONOS Geo image. Different numbers of GCPs are fed through a variety of genetic algorithms (GAs) with different control parameter settings. Some initial constraints are introduced to make the process stable and fast. The residual errors at independent check points proved that sub-pixel accuracies can be achieved even when only seven and five GCPs are used. GAs could select rational function terms in such a way that numerical problems are avoided without the need to normalize image and ground coordinates. [Copyright &y& Elsevier]

Palmer Drought Severity Index (PDSI) is known as a robust agricultural drought index since it considers the water balance conditions in the soil. It has been widely used as a reference index for monitoring agricultural drought. In this study, the PDSI time series were calculated for nine synoptic stations to monitor agricultural drought in semi-arid region located at Zagros mountains of Iran. Autoregressive Moving Average (ARMA) was used as the stochastic model while Radial Basis Function Neural Network (RBFNN) and Support Vector Machine (SVM) were applied as Machine Learning (ML)-based techniques. According to the time series analysis of PDSI, for the driest months the most PDSI drought events are normal drought and mild drought conditions. As an innovation, Dragonfly Algorithm (DA) was used in this study to optimize the SVM's parameters, called as the hybrid SVM-DA model. It is worthy to mention that the hybrid SVM-DA is developed as a meta-innovative model for the first time in hydrological studies. The novel hybrid SVM-DA paradigm could improve the SVM's accuracy up to 29% in predicting PDSI and therefore was found as the superior model. The best statistics for this model were obtained as Root Mean Squared Error (RMSE) = 0.817, Normalized RMSE (NRMSE) = 0.097, Wilmott Index (WI) = 0.940, and R = 0.889. The Mean Absolute Error values of the PDSI predictions via the novel SVM-DA model were under 0.6 for incipient drought, under 0.7 for mild and moderate droughts. In general, the error values in severe and extreme droughts were more than the other classes; however, the hybrid SVM-DA was the best-performing model in most of the cases. [ABSTRACT FROM AUTHOR]

Stand-alone hybrid energy systems based on solar and energy storage are an effective option for rural areas to meet the load demand. The objective of the current work is to the optimal configuration of a stand-alone hybrid photovoltaic/battery energy storage system with the help of an efficient metaheuristic algorithm, improved harmony search, to supply electrical of a residential load in Iran. The objective function is a minimization of total life cycle cost (TLCC) subject to the reliability index (loss of load probability). The optimal configurations of hybrid systems are compared in respect of different losses of load probability (0 to 20%). Sensitivity analysis and effects of economic parameters based on photovoltaic and battery prices are carried out to study the possibility of the suggested scheme. The results show that, by increasing the reliability index from 0 to 20%, the optimal number of panels and batteries decreases by 52 and 1202. Also, it is found that the TLCC of the system and cost of system components are increased by decreasing of the reliability index value. [ABSTRACT FROM AUTHOR]

This study proposes a new stochastic approach for optimizing diversion system design and its construction schedule by considering different hydrological and hydraulic uncertainties sources. For this purpose, a multi-objective optimization-simulation model was developed to evaluate the failure of a diversion system to flood. Two objective functions, the expected flood damage (EFD) and cost-benefit (CB) index of a diversion system, are optimized in this study using a non-dominated sorting genetic algorithm II (NSGA-II). The approach is tested for four different compositions of uncertainties (Base Case, Case1, Case2, and Case3) to estimate their impacts based on distance index (D) and the boxplot. Finally, finance constraints are evaluated based on the construction period of the project. The Karun-4 dam, located in Iran, is considered as the case study. The obtained results demonstrate that the hydrological uncertainty with D c a s e 2 basecase = 21.335 and IQR basecase = 2.1 M has the highest effect on the Pareto optimal front and the hydraulic uncertainty of downstream cofferdam with D c a s e 3 basecase = 5.789 and IQR c a s e 2 = 1.8 M has the lowest effect on the Pareto optimal front. The best value of the CB index is related to the base case (66.42%) using the pseudo weight factor. The study indicates that the total investment of the water diversion system is lower than the consultant's plan by 20.23%, 18.33%, 17.28%, and 18.81% when the different components of uncertainty are considered. An implementation period of 6-year and 11-year is the best option for no financial constraints and financial constraints, respectively. The stochastic simulation-optimization approach proposed in the present study provides decision-makers reliable insight into planning dam construction. [ABSTRACT FROM AUTHOR]

Renewable energy technologies have been developed in recent years due to the limited sources of fossil fuels, the possibility of depletion of fossil fuels and the related environmental issues. In these types of systems, it is crucial to reach optimum sizing in order to have an affordable system based on solar and wind energy and energy storage. In this study, a powerful optimization scheme based on tabu search, called discrete tabu search, has been proposed for sizing three stand-alone solar/wind/energy storage (battery) hybrid systems. For validating the applied algorithm effectiveness, the results are compared with the results found by the discrete harmony search. The obtained outcomes are compared on the basis of total annual cost. The components of the scheme are analyzed in different operating conditions by applying meteorological data in addition to real time information from three typical regions of Iran. According to the obtained data, applying 'discrete tabu search' leads to better outputs on the basis of mean, standard deviation and worst indexes. [ABSTRACT FROM AUTHOR]

Optimizing purposes of the drilling process include reduction in time, saving costs, and increasing efficiency, which requires optimization of controllable variables and variables affecting the drilling process. Drilling optimization is directly related to maximizing the rate of penetration (ROP). However, estimation of ROP is difficult due to the complexity of the relationship between the variables affecting the drilling process. The main goal of this study is to develop three computational intelligence (CI)-based models including multilayer perceptron neural network optimized by backpropagation algorithm (BP-MLPNN), cascade-forward neural network optimized by backpropagation algorithm, and radial basis function neural network optimized by biogeography-based optimization algorithm (BBO-RBFNN) to estimate ROP. Also, in order to broaden the comparisons, some conventional ROP models from the literature were employed. The required data were collected from the well log unit and the final drilling reports of four drilled wells in two different oil fields in southwestern Iran. Firstly, all data were preprocessed to remove outliers; then the overall noises of the data were reduced by implementing Savitzky–Golay smoothing filter. In the next stage, nine input variables were selected during a feature selection step by combining the BP-MLPNN and NSGA-II algorithm. The results of this study showed that developed CI-based models more accurate than conventional ROP models. Also, a survey of statistical indices and graphical error tools proved that BBO-RBFNN model has the highest performance to predict ROP with values of APRE, AAPRE, RMSE and R2 equal to − 0.603, 5.531, 0.490 and 0.948, respectively. [ABSTRACT FROM AUTHOR]

Suspended sediment load (SSL) estimation is a required exercise in water resource management. This article proposes the use of hybrid artificial neural network (ANN) models, for the prediction of SSL, based on previous SSL values. Different input scenarios of daily SSL were used to evaluate the capacity of the ANN-ant lion optimization (ALO), ANN-bat algorithm (BA) and ANN-particle swarm optimization (PSO). The Goorganrood basin in Iran was selected for this study. First, the lagged SSL data were used as the inputs to the models. Next, the rainfall and temperature data were used. Optimization algorithms were used to fine-tune the parameters of the ANN model. Three statistical indexes were used to evaluate the accuracy of the models: the root-mean-square error (RMSE), mean absolute error (MAE) and Nash-Sutcliffe efficiency (NSE). An uncertainty analysis of the predicting models was performed to evaluate the capability of the hybrid ANN models. A comparison of models indicated that the ANN-ALO improved the RMSE accuracy of the ANN-BA and ANN-PSO models by 18% and 26%, respectively. Based on the uncertainty analysis, it can be surmised that the ANN-ALO has an acceptable degree of uncertainty in predicting daily SSL. Generally, the results indicate that the ANN-ALO is applicable for a variety of water resource management operations. [ABSTRACT FROM AUTHOR]

The modelling of drought is of utmost importance for the efficient management of water resources. This article used the adaptive neuro-fuzzy interface system (ANFIS), multilayer perceptron (MLP), radial basis function neural network (RBFNN), and support vector machine (SVM) models to forecast meteorological droughts in Iran. The spatial–temporal pattern of droughts in Iran was also found using recorded observation data from 1980 to 2014. A nomadic people algorithm (NPA) was utilized to train the ANFIS, MLP, RBFNN, and SVM models. Additionally, the NPA was benchmarked against the bat algorithm, salp swarm algorithm, and krill algorithm (KA). The hybrid ANFIS, MLP, RBFNN, and SVM models were used to forecast the 3-month standardized precipitation index. New evolutionary algorithms were utilized to improve the convergence speed of the soft computing models and their accuracy. First, random stations, namely, in Azarbayjan (northwest Iran), Khouzestan (southwest Iran), Khorasan (northeast Iran), and Sistan and Balouchestan (southeast Iran) were selected for the testing of the models. According to the results obtained from the Azarbayjan station, the Nash–Sutcliffe efficiency (NSE) was 0.93, 0.86, 0.85, and 0.83 for the ANFIS–NPA, MLP–NPA, RBFNN–NPA, and SVM–NPA models, respectively. For Sistan and Baloucehstan, the results indicated the superiority of the ANFIS–NPA model, followed by the MLP–NPA model, compared to the RBFNN–NPA and SVM–NPA models, and suggested that the hybrid models performed better than the standalone MLP, RBFNN, ANFIS, and SVM models. The second aim of the study was to capture the relationship between large-scale climate signals and drought indices by using a wavelet coherence analysis. The general results indicated that the NPA and wavelet coherence analysis are useful tools for modelling drought indices. [ABSTRACT FROM AUTHOR]