genetic algorithm

This study proposes an efficient and novel method for recognizing pistachio varieties by leveraging Gabor filters for feature extraction and a genetic algorithm for feature selection, aiming to enhance classification accuracy and speed. Unlike conventional approaches that focus on individual processing of pistachio kernels—which, despite high accuracy, are time-consuming and computationally demanding—the proposed method employs holistic processing of images containing multiple pistachios, thereby significantly accelerating the recognition process. Key textural and shape-based features are initially extracted using Gabor filters. Subsequently, the genetic algorithm is applied to select optimal features and reduce data redundancy. The refined feature set is then classified using the K-Nearest Neighbor (KNN) algorithm. Experiments conducted on a dataset of 1,000 sub-images covering five common pistachio types (Akbari, Ahmad Aghaei, Kaleh Ghouchi, Fandoghi, and Badami) yielded an average classification accuracy of 99.5%. In comparison with deep learning models, the proposed method demonstrates competitive performance while requiring no extensive training phase or high computational resources. This results in a faster and more resource-efficient implementation, making it particularly suitable for industrial applications, especially in automated pistachio processing and packaging systems. The proposed method contributes to the automation of agricultural workflows, reducing both processing time and labor costs, and offers a practical solution for real-time classification in resource-constrained environments.

In arid and semi-arid countries such as Iran, the uneven spatial and temporal distribution of rainfall necessitates a reliance on irrigated agriculture for food production. Consequently, a substantial portion of water resources is allocated to agriculture. Identifying strategies reducing water consumption and improving its efficiency in agriculture are critical priorities. This study employs crop rotation as a key variable in an optimization framework to calculate a matrix of impact coefficients based on insights from expert farmers. The matrix quantifies the effects of sequential crop planting. These coefficients are incorporated into a water allocation optimization model aimed at maximizing economic profitability, utilizing a genetic algorithm and the AquaCrop plug-in program. For this purpose, C# coding within Visual Studio was used to optimize three-, four-, five-, six-, and seven-year rotations involving wheat, soybean, tomato, potato, corn, alfalfa, barley, and sugar beet. Moreover, the impact of crop rotation on crop yield, water allocation, and expected profitability per unit area was evaluated using a valuation formula. Rotation Optimization results indicated that the four-year rotation (sugar beet, corn, potato, tomato) achieved the highest economic profit, while the seven-year rotation was most effective in reducing water allocation (by 9.45%). Therefore, crop rotation optimization is a significant parameter for enhancing crop yield, boosting profitability, and achieving long-term water savings.

In this study, the country's water resources management system has been modeled using a system dynamics approach. After simulation, optimal water resources, social power of governance, government financial resources, and the rate of water migration have been determined based on the decision variables of household, agricultural, and industrial water tariffs. The optimal combined results suggest an 11%, 200%, and 200% increase in water tariffs for household, agricultural, and industrial sectors, respectively, over the next 5 years.

Initially, this study modeled and simulated the variables and feedback loops involved in water resources management using system dynamics tools. For optimization, two methods, genetic algorithm and the Simulation-optimization capability in the Vensim software, were employed. In the genetic algorithm, an initial population of 30 individuals and crossover and mutation probabilities of 83% and 17% were considered. The selection criterion for each chromosome is based on the roulette wheel method.

The results indicate that optimization using the genetic algorithm results in an 89% increase in water resources behind dams compared to the baseline conditions, whereas the Vensim software output shows an 84% improvement. Overall, the genetic algorithm improves the objective function by 2% compared to the Vensim software's optimization output. Additionally, after optimization, the best tariff policy for enhancing the objective function is a further increase in agricultural and industrial water tariffs compared to household tariffs.

The aim of the present study is to optimize the cultivation pattern in the form of a multi-objective model in order to ensure the quantitative and qualitative security of crop production in Babol city. The results of the optimal model showed that based on the approach of agricultural sustainability and ensuring the quantitative and qualitative security of crop production in the study area, the amount of profit of farmers in the optimal cultivation model compared to the common model of the region increased by about 0.5% and the amount of production of crops that in the current study Its maximization was proposed as the goal of quantitative security of food production (agricultural products), it has increased by 3.8 percent. Also, the consumption of chemical fertilizers, whose minimization was included as the goal of quality security of crop production in the region, has decreased by 1.9% compared to the current state of the region. The results of the increase in the production of crops and the significant reduction in the consumption of chemical inputs confirm that the proposed cultivation model can improve the quantitative and qualitative security of the production of crops (food) in order to achieve at least one of the indicators. Food security, which is the supply of more and healthy food, should play an effective role.

The specific detection of the type and severity of plant abiotic stresses to take timely measures helps prevent yield reduction. This study introduces a new method to detect the type and severity of stress in rice plants under salinity, drought, and heat conditions by investigating microRNAs. The concentration of eight microRNAs in the tissue of plants subjected to salinity, drought, and heat conditions was measured with the help of an optical biosensor based on gold nanoparticles. The biosensor worked based on probe-target hybridization, in which the mixture of probe/citrate-capped gold nanoparticles (compound 1) and microRNA/polyethyleneimine-capped nanoparticles (compound 2) resulted in the aggregation of nanoparticles and changes in their spectroscopic properties. In the following, machine learning methods were used to predict the type and severity of stress using such concentrations. The results showed that the support vector machine optimized by the genetic algorithm was able to detect the severity of salinity, drought, and heat stress applied to rice plants with appropriate performance and with coefficients of determination of 0.94, 0.91, and 0.86, respectively. Then, the results of feature selection based on the cooperative game theory showed that among the microRNAs studied, miRNA-156, miRNA-393, and miRNA-159 had the largest contribution in predicting drought, salinity, and heat stresses in the rice plants, respectively. The findings of the research show that the examination of plant microRNAs with the help of optical biosensors can lead to reliable features for determining plant growth conditions and plant stresses in the early stage.

Optimum operation of dam reservoirs is one of the most significant management factors in developing the annual resource and consumption plan of dam reservoirs during operation. The decisions regarding amount of water release are made by having the volume of  the reservoir, amount of demand, and the prediction of reservoir inflow in the actual operation of dam reservoirs. Since the volume of release is related to the storage volume of the reservoirs of the dams and should be optimized simultaneously, after introducing the genetic algorithm and the particle swarm algorithm, the performance of these algorithms alone and in combination with each other in the optimal operation of the Alavian dam reservoir are compared with the modeling results in the nonlinear programming and the rule curves of the operation are developed in this study. The performance indicators of the reservoir were been used including reliability, vulnerability and stability  to evaluate the performance of the examined algorithms in the optimal operation of the reservoir.

In this study, after introducing the genetic algorithm and the particle swarm algorithm, innovatively examines the accuracy and effectiveness of modeling by comparing the performance of these algorithms both individually and in combination. This comparison focuses on optimizing the operation of the Alavian dam reservoir over multi-step ahead, using modeling results from the software Lingo. To enhance decision-making for improved management of the Alavian dam reservoir, operation rule curves have been developed. The model utilizes a series of 25 years of data from the Alavian dam, which includes the volume of inflow, the volume of release from the reservoir, storage volume, and usage data encompassing drinking, agriculture, industry, and environmental needs. Additionally, information such as the volume of overflow from the dam reservoir and the volume of evaporation from the surface of the Alaviyan Dam reservoir has been collected on a monthly basis.

The results from these optimal solutions indicate that the combined algorithm outperforms other methods, demonstrating a better correlation with the reservoir management policy. Over the last 25 years, the combined algorithm met 85% of the water requirements for agriculture downstream of Alavian dam, compared to 82% for the Particle swarm optimization(PSO)  algorithm and 78% for the genetic algorithm (GA). In contrast, the nonlinear programming (NLP) method met 80%. The total shortages over the entire 25-year operational period for the GA, PSO, GA-PSO, and NLP algorithms were 38, 33.7, 27.1, and 35.2 million cubic meters, respectively. The GA-PSO algorithm has successfully addressed 10.87 million cubic meters more than the GA algorithm and 6.57 million cubic meters more than the PSO algorithm.

Investigating the results obtained from the optimal solutions revealed that the hybrid algorithm model provides a more favorable result and shows a better correlation regarding the reservoir operation policy. The results indicate the high performance of the hybrid algorithm compared to other studied methods in the optimal operation of the single reservoir system of Alavian dam. Accordingly, the optimal parameters of the Alavian dam reservoir were obtained using a hybrid algorithm. It was proposed to  release volume rule curves and reservoir volume for the  multi-step ahead.

In order to effectively manage soil and water resources, it is imperative to investigate wet aggregate stability (WAS) as a fundamental indicator for assessing soil structure and quality. In this study, machine learning techniques, specifically random forest (RF) and random forest optimized with genetic algorithm (GA-RF), were employed. The analysis focused on determining the texture, organic matter content, and lime characteristics of 55 soil samples collected from the Arsbaran forests. Utilizing various input combinations based on correlations with WAS, modeling was performed across seven distinct scenarios. Furthermore, three performance metrics including correlation coefficient (CC), normalized root mean square error (NRMSE), and Wilmot coefficient (WI) were utilized to evaluate the effectiveness of the models. The findings indicated that the RF5 model exhibited superior performance among the random forest models, achieving NRMSE = 0.038, CC = 0.736, and WI = 0.789. Similarly, the GA-RF5 model, optimized through a genetic algorithm approach, demonstrated exceptional performance with NRMSE = 0.031, CC = 0.800, and WI = 0.842 when considering input percentages of sand, silt, and clay. Moreover, results from RF1 (NRMSE = 0.047, CC = 0.589, WI = 0.721) and GA-RF1 (NRMSE = 0.036, CC = 0.662, WI = 0.797) emphasized that clay content exhibited the strongest correlation with stability. Additionally, the incorporation of calcium carbonate equivalent in scenario 7 significantly enhanced model performance and positively influenced the prediction of wet aggregate stability. In summary, the hybrid model combining random forest with a genetic algorithm is recommended for precise and reliable determination of wet aggregate stability in studies focusing on soil properties.

AbstractHydropower plants are one of the renewable energy sources with higher efficiency than other renewable sources. One of the appropriate methods to maximize efficiency in these power plants is metaheuristic methods. The purpose of this study is to calculate the maximum power generation from the Karoun Basin reservoirs, so that there is no disruption in the supply of downstream demands. Thus, the bacterial foraging optimization algorithm (BFO) and genetic algorithm (GA) have been used to optimize power generation. The results showed that it is possible to have maximum hydropower energy production with 75% reliability in downstream water supply. According to the results of GA and BFO, there is an annual hydropower energy production capacity of 18347 and 18431 GWh, respectively, in the study area, the majority of which is related to the Godarlandar dam on the Karoun river. The Dez river share in power generation, according to the GA results, is 2632.4 GWh and, according to the BFO results, is 2645.2 GWh. Comparing the performance of GA and BFO, as the objective function becomes more complex, BFO shows a higher ability in more accurate calculations.

Prediction of effluent quality parameters of wastewater treatment plant is essential in managing water resources, limitation of fresh water resources in the world, furthermore the ever-increasing population growth and the development of urbanization, have made the approach of urban wastewater reuse inevitable. In such a situation, the use of recycled water can be considered as one of the ways to overcome water shortage and prevent wastage of water resources. This research aimed to investigate the performance of Prediction of effluent quality parameters of wastewater treatment plant in using recycled water. On the other hand, due to the health hazards caused by the discharge of wastewater from wastewater treatment plants to water sources, achieving a precise design and correct management of wastewater treatment plants (WWTP: Wastewater Treatment Plant) is one of the important challenges of sustainable water resources management. 4 effective parameters including (BOD), (COD), (TSS) and (pH) of wastewater, were selected as input to the model, during a statistical period of 3 years (1397 to 1399). Also, 70% and 30% sizes were determined as the best sizes for training and testing stages in order to model BODeff and CODeff parameters. In this study, multi-Layer perceptron models (MLP), basic radial neural network models (RABF), as well as the integration of these models with several other algorithms, such as genetic algorithm (GA), particle swarm optimization algorithm (PSO) and sine cosine algorithm (SCA), were used in order to predict the quality parameters of wastewater treatment plant effluent.

Ensuring the health and sustainability of the environment is one of the secondary goals of hydraulic structures. Water pollution and the reduction of its quality are serious threats to the health of the earth and will turn rivers into channels for polluted industrial wastewater. Increasing the residence time of flow in rivers by constructing hydraulic structures such as gabion spur dikes can increase the self-purification capacity. In this research, a laboratory investigation of pollution transport using NaCl tracer material in a laboratory channel with a sediment bed with a medium diameter (D50) of 11.85 mm, thickness of 12 cm, and length of 12 meters in a different number of fine-grained or coarse-grained gabion spur dikes from 1 to 4 were performed. Analytical solutions of Advection-Dispersion equation (ADE), OTIS model, and solution of Transient Storage Model (TSM) were used for numerical simulation. Laboratory results showed that gabion spur dikes with fine-grained materials reduce the peak concentration of pollution (Cmax) compared to coarse-grained materials. The results showed that the gabion spur dikes in the flow path increase the residence time of the pollutant by increasing hyporheic exchanges. The advection-dispersion equation (ADE) has low accuracy in the simulations due to the lack of attention to the role of the storage zone exchanges, with a determination coefficient (R2) of 0.71 to 0.83. On the other hand, the OTIS model, which is based on the transient storage model (TSM), considering the role of the porous zones of spur dikes in the transient storage of solute, has high accuracy with a determination coefficient (R2) of 0.91 to 0.98. The estimated coefficients of longitudinal dispersion (Dx) and storage zone exchange (α) by the temporal moment analysis were evaluated lower than the estimates of OTIS model in most of the simulations.

Urban flooding is caused by the lack of capacity of the harvesting channel network and occurs when the amount of precipitation exceeds the network's capacity. One of the two main factors contributing to the aggravation of damage caused by urban floods is population growth and the expansion of urbanization, and the second factor is heavy rainfall caused by climate change, which plays an essential role in intensifying and accelerating the hydrological cycle and may change the amount and frequency of precipitation. This factor affects the probability of flooding, runoff volume, and peak flow. It is more visible in arid and semi-arid areas where rainfall usually occurs briefly but with high intensity. Urban flooding is a growing threat to urban infrastructure and public health, posing significant challenges to urban resilience and sustainability. One of the urban infrastructures that is of great importance is the runoff collection network. The increase of impervious surfaces wear and tear on the network. changes in the rainfall pattern due to climate change have increased the occurrence of urban floods and raised the importance of network redesign to minimize the system vulnerability.

In this research, the runoff harvesting network of ten districts of Tehran Municipality was redesigned and optimized. This area, with a population of 327,000 people, is located in the relatively dense fabric of the Tehran metropolis, and its area is 807 ha. Simulating the runoff collection network and checking the performance of the network by two indicators of vulnerability and reliability requires an accurate model with great details. For this purpose, in this research, SWMM version 5.1 software was used to simulate the runoff collection network. The study area was divided into 285 sub-basins to simulate the sub-channels in better detail. Then, information such as slope, area, and percentage of impervious space was introduced through ArcMap software version 10.3.1 as information under the watersheds. The sub-watershed width parameter was calculated by dividing the sub-watershed area by its most significant length using Q-GIS software and applied to the sub-basins. The LARS-WG model has also been used for the exponential micro-scale output of climate models. To simulate the network in the current or present situation, the historical precipitation information of the Mehrabad synoptic station was used, and to affect the network in future conditions, the precipitation information of the climate models of the sixth climate change report was used. Among the predictions of climate models, the most incremental changes in threshold precipitation were selected as a pessimistic scenario, and a system redesign was done to reduce vulnerability under this scenario.

This study was conducted to assess the performance of Tehran municipality's runoff collection network under current and future conditions. The SWMM hydraulic model was employed to simulate the network under various rainfall scenarios. Current conditions revealed a total runoff volume of 45.9, 51.14, and 59.7 thousand m3 for return periods of 2, 5, and 10 years, respectively. This runoff volume resulted in a vulnerability increase from 10.4 to 12.2% and a reliability reduction from 97.5 to 95.8%. To evaluate the network's performance under future climate change scenarios, the SWMM model was used with data from the IPCC sixth assessment report. Among the top five climate models, the one with the highest precipitation was selected as the pessimistic scenario. Simulation results under future conditions indicated a significant runoff volume increase, reaching 64.04 and 72.18 thousand m3 in 5- and 10-year return periods, respectively. This increase corresponded to vulnerability indices of 12.7 and 13.9% and reliability indices of 95.3 and 94.3% for the same return periods. To enhance the network's resilience, a genetic algorithm-based optimization approach was employed. Cost, reliability, and vulnerability index were considered optimization objectives with specific weighting functions. The algorithm converged to an optimal design solution in the 168th iteration, resulting in a 7.6% vulnerability reduction and a 98.1% reliability enhancement.

The vulnerability index in the return periods of 5 and 10 years is equal to 12.7 % and 13.9 %, respectively, and the reliability index is equal to 95.3 % and 94.3 %. After checking the network in its current state and future conditions, an optimal network redesign was done to improve system performance in both current and future conditions. For this purpose, the genetic algorithm was used for optimization, and the objective function consisting of cost, vulnerability index, and reliability index and the importance weights of each, were defined. Then, MATLAB software did the optimal network redesign by connecting the simulator and optimizer model. The results showed that in the 168th iteration, the algorithm reached its final answer of 0.3, which remained constant until the 300th iteration. Also, the optimal redesign has reduced network vulnerability by 7.6% and increased reliability by 98.1%. This research showed that with an optimal redesign and solving the current network problems, the system's ability to face future climate change threats could also be increased. Of course, spending the least money to achieve the best result was one of the main goals of this research. In future studies, it is recommended to use low-impact development tools along with optimal redesign to fix defects and improve the performance of the runoff collection network.

Weirs are a type of water structures that are used to pass floods, control water levels and measure flow rates. The accurate and appropriate design of the weir is of particular importance, and the existence of weirs with inappropriate discharge capacity is one of the most important factors of channel inefficiency. Circular crest weirs are reliable weirs for use in channels that are built perpendicular to the flow or at an angle (oblique) to the direction of the flow. Oblique weirs are used to increase the effective length of the weir and increase the water-passing capacity and hydraulic parameters such as the discharge coefficient. On the other hand, the study of the flow in the unsteady state, in which the flow variables in the channel vary with time, is of special importance in hydraulic science. In this research, the calibration of the discharge coefficient of the oblique circular crest weir under unsteady flow condition has been discussed. Also, the effect of changing the height of the weir and changing the flow pattern on the discharge coefficient of the unsteady flow in this type of weir has been investigated.

In this research, three oblique circular crest weirs with a height of 15, 10 and 20 cm and other identical geometric parameters under free and unsteady flow conditions in the flow range of 25 to 51 liters per second under the range of flow rate changes of 1, 3 and 5 liters per second and the range of time changes of 5, 10 and 15 seconds have been tested. Therefore, the total number of tests was equal to 27. Experiments were carried out in the research flume of Islamic Azad University, Isfahan (Khorasgan) branch with a rectangular cross-section of 10 meters in length and 0.6 meters in width, and weirs were installed at 2.5 meters from the entrance of the channel The flume has no slope of the floor and the height of the flume is the same without change and its walls are made of tempered glass and completely sealed. The mentioned flume is equipped with a closed water circulation system and can provide a maximum flow rate of up to 55 liters per second. The tank of this flume is made of fiberglass and has a cylindrical shape with a volume of 10 cubic meters and is placed underground at a height of about 2 meters. Flow can be regulated by PLC device. The depth gauge of the device without contacting the free surface of the flow, by sending and receiving ultrasonic waves, measures the distance with very high speed and accuracy, and in this way the depth of the flow is recorded in the PLC device. In fact, the most important part of this test set is the PLC device connected to the flume, which controls all flow settings, including the flow rate, maximum flow rate, relevant hydrographs, and records the flow depth data. In this study, the governing relations were first extracted and then the genetic algorithm was used for optimization. The optimization process in the genetic algorithm is based on a guided random process. This method is based on the theory of gradual evolution and Darwin's fundamental ideas. Genetic Algorithm is a non-algebraic optimization method that is suitable for functions whose optimization with algebraic methods is exhausting. This algorithm and other evolutionary algorithms examine the response space in parallel and cluster by cluster and not member by member and for this reason, the possibility of occurrence of local maxima or minima is eliminated. Also, these methods do not need information about the derivatives of the target function and only the main form of the function is required. In this research, the solver available in Excel software was used for optimization with evolutionary algorithm method. After specifying the target variable, which is the discharge coefficient in this research, the evolutionary algorithm option is selected, and the software performs its analysis to calculate the best discharge coefficient with the lowest value for total errors.

The results obtained in this research show that in all patterns of flow changes, increasing the ratio of water height relative to the weir crest to the weir height (H/P) causes a decrease in the discharge coefficient of unsteady flow. Also, in all patterns of flow rate change, increasing the height of the weir causes a decrease in the discharge coefficient of the unsteady flow, that is, the discharge coefficient of the unsteady flow in the oblique circular crest weir is a function of the upstream flow conditions and the height of the weir. Also, the unsteady flow rate coefficient in this type of weir is a function of the flow rate change pattern. As can be seen from the graphs obtained in this research, the flow rate change pattern does not have much effect on the slope of the flow coefficient changes compared to the H/P changes, but it is effective on the degree of influence of the weir height changes for a fixed H/P value. On the other hand, the graphs show that the discharge coefficient of unsteady flow for oblique circular crest weir varies between 0.5 and 1.5, which previous researchers had also concluded that the discharge coefficient of unsteady flow for other weirs is not constant and is a function of the geometry of the weir and the pattern of changes in flow rate.

In the realm of biotechnological enhancement of common beans, an imperative challenge lies in devising a reliable and effective in vitro regeneration strategy, given the inherent difficulty of regenerating this crop in laboratory settings. This research, aiming to address this challenge, leverages the power of Machine Learning (ML) models, specifically employing algorithms for Artificial Neural Networks (ANN). The primary objective is to establish an efficient and repeatable in vitro regeneration process while simultaneously optimizing and predicting future outcomes. The study incorporates various variables such as bean genotype, explants, and different doses of 6-benzylaminopurine (BAP) and CuSO4. A Recurrent Regression Neural Network (RRNN) is employed to model and anticipate the results of in vitro crop regeneration, specifically focusing on common beans. The experimental setup involves preconditioning common bean embryos with 10, 15, and 20 mg/L BAP for 25 days, followed by growth in a post-treatment environment comprising 0.3, 0.6, 0.9, and 1.2 mg/L BAP for 7 weeks. Subsequently, the plumular apice is isolated for in vitro regeneration. Notably, the RRNN model is also integrated with a Genetic Algorithm (GA) to optimize the regeneration process further. The results are compelling, with RRNN exhibiting the lowest Mean Squared Error (MSE) of 0.061, signifying superior predictive accuracy in total regeneration. In comparison, Support Vector Regression (SVR), Random Forest (RF), and Extreme Gradient Boosting (XGB) models exhibit higher MSE values of 0.081, 0.081, and 0.097, respectively. These findings underscore the efficacy of the RRNN algorithm, outperforming other models across all parameters. The superior performance of RRNN suggests its potential application in making precise predictions regarding common bean regeneration. In the context of a common bean breeding program, these outcomes can be harnessed to optimize and predict plant tissue culture methods, thereby enhancing biotechnological techniques employed in the cultivation of common beans. The integration of ML models, particularly RRNN, stands as a promising avenue for advancing crop regeneration strategies and contributing to the efficiency of biotechnological interventions in agriculture.

The purpose of this study is the effects of the formation of water markets on the improvement of water productivity in the Tajen catchment basin. In this research, a mathematical programming model modeling system and profit maximization objective function were used in MATLAB environment. After simulating the formation of the water market, its impact on physical and economic water productivity indicators was evaluated in two groups including: farms without water restrictions group (A) and farms with water restrictions group (B). Based on the results, forming a water market leads to a 13 percent increase in profit in group (A) and 30 percent in group (B). According to the results, the formation of the water market reduces and increases the amount of water consumption in representative farms (A) and (B), respectively. The results of the evaluation of water productivity indicators indicate that in group (A), the availability of water and consequently the increase of the cultivated area, and in group (B), the compensation of the lack of water and the increase of the cultivated area have led to an increase in physical productivity. In the farms of group (A), the sale of water and in the farms of group (B), the allocation of water to products with higher economic value has led to an increase in the economic productivity of water. In general, it can be said that forming a water market leads to an increase in productivity, but alone it does not lead to achieving sustainable agriculture and reducing water consumption at the watershed level. Therefore, the implementation of other policies such as the control of extraction from surface and underground water resources, volume delivery of water based on the pattern of optimal cultivation and allocation of water to products with higher economic value along with the water market approach can improve water productivity in addition to reducing water consumption.

In order to determine the potential habitat of plant species, it is essential to know the ecological needs of the species as well as climatic and edaphic characteristics to apply management in accordance with the ecological conditions of the studied area. In this research, in order to develop model for the distribution of Astragalus Sp., using different statistical methods in part of the pastures of the Savar-Abad Basin, at first by producing using topographic, slop, aspect maps, types of vegetation in study area were determined. In the specified types, a number of sampling sites with dimensions of 2 to 10 square meters were selected. Information related to the presence and absence of Astragalus sp as dependent variable and other environmental information as independent variables was measured. In each homogenous unit, three transects of 750 meters, two transects along the most gradients (height, direction and slope), And another transect established perpendicular to those two transects. Along each transect, 15 plots were placed at a distance of 50 meters, thus 47 plots were established in each homogeneous unit. (Total 2 units, 94 plots). The size of sampling plots was determined according to the type and distribution of plant species using the Minimum Surface Method. In each plot, the type and number of plant species and their coverage percentage were recorded. For soil sampling, At the beginning and end of each transect, the soil profile was dug and soil sampling was done according to existing standards, and soil variables including gravel, clay, sand, silt, lime, organic matter, acidity and electrical conductivity were measured in the laboratory. Also, in each sampling unit, latitude, longitude, slope, direction and height from the sea level were also determined. In this study, the dependent variables are the data of the presence and absence of vegetation types, and the independent variables include soil and topography characteristics. The best distribution model was determined using statistical analysis. The results showed that the MaxEnt model has a better performance than the logistic regression and genetic algorithm models. However, the findings of the research show that altitude, acidity and salinity have a greater effect on the distribution of different species in the study area.

The aim of this research is to optimize the design parameters of underground drainage systems with an economic approach. The study of the relationship between the depth and distance of drain installation has been the subject of many researchers, each of whom has tried to reduce the costs of drain implementation. In this research, genetic and multi-world algorithm optimization model was used to optimize the main design parameters of the underground drainage system of regional agricultural lands around Gorgan city. The area of the construction area of the drainage system was around 200 hectares. In this research, by using genetic and multi-world algorithm, the design parameters were selected in such a way that they lead to the lowest implementation cost of the underground drainage system. In this regard, the design parameters have been selected by combining Hohhot's permanent equation and optimization algorithms.

The area under study is Aliabad district, one of the functions of Gorgan city. The lands of Ali Abad region are also located in the upper part of the plains. These lands are located in eastern longitude and northern latitude. The study area covers about 200 hectares.
Genetic Algorithm:Genetic algorithm is an optimization method inspired by living nature, which can be referred to as a numerical method, direct and random search in classifications. This algorithm is based on repetition and its basic principles are adapted from genetic science.
Multi verse Algorithm:The big bang theory considers the occurrence of a big explosion as the beginning of the origin of our universe. According to this theory, the big bang is the origin of everything in this universe and nothing existed before it. A population-based algorithm performs the search process in two stages: exploration and exploitation. In this algorithm, the concepts of white hole and black hole are used to explore the search space. In contrast, wormholes help exploit search spaces.

Genetic Algorithm:By applying the genetic algorithm optimization model to the data of the studied lands, the optimal parameters were calculated. Table (4) shows the design parameters obtained from the genetic algorithm optimization model in different drainage coefficients for the allowed depth of drain installation. Considering the entire search area (permissible depth of drainage installation from 1.5 to 3.5 meters from the ground surface), the results obtained from the land input data of the studied area showed that taking into account the drainage coefficient of 2.5 mm per day, the minimum cost the equivalent of 51.3 million Tomans has happened in 8 hectares at a depth of 2.62 meters from the ground surface with an installation distance of 79.9 meters and a diameter of 125 mm.
Multiverse algorithm
The optimal parameters were calculated by applying the multi-world algorithm optimization model. Table (7) shows the design parameters obtained from the optimization model in different drainage coefficients for the allowed depth of drain installation. Considering the entire search area (permissible depth of drain installation from 1.5 to 3.5 meters from the ground surface), the results obtained from the input data of Aliabad lands showed that taking into account the drainage coefficient (discharge intensity) 2.5 mm per the minimum cost equivalent to 51.5 million Tomans has happened in an 8-hectare unit at a depth of 2.61 meters from the ground with an installation distance of 79.5 meters and a diameter of 125 mm.
Comparing the results of genetic and multiverse algorithms
Comparing the performance of genetic and multi-world algorithms shows the high efficiency of both algorithms in solving the problem of optimizing the diameter of drainage pipes and their installation depth. Both algorithms have almost the same performance in solving this optimization problem; So that both algorithms in the distance of the impervious layer to the depth of the drain installation (D) is equal to 2.25 meters, the stabilization depth of the water table (in the middle of the two drains) from the ground level (H) is equal to 1.5 meters and intensity Drainage or drainage from the surface unit (q) is equal to 4 mm per day, and they have calculated the optimal depth of drainage installation to be 13.3 meters

The design of drainage systems consists of choosing three parameters: depth, diameter and distance of drains. Various approaches can be used to choose the best combination of three parameters. One of the approaches can be to reduce the costs of implementing the drainage system. In this research, using the genetic algorithm, these parameters were selected in such a way that they lead to the lowest implementation cost of the drainage system. In this regard, the design parameters have been selected by combining Hohhot's permanent equation and genetic algorithm.

Given the application of hydrological response in a watershed, various methods have been used to determine this response and the results have shown a high degree of accuracy and accuracy variability depending on the data used. By reviewing and summarizing the results of research carried out in the modeling of rainfall-runoff, particularly the time-area method, it was found that in most of these studies, the concept of watershed time concentration was used, which in most of the formulas used, the physical properties of the watershed were used and the dependence of time concentration on rainfall conditions was not studied. Therefore, this study was conducted to evaluate these methods using the kinematic wave method in the GIS environment, the HEC-1 method, and optimization methods using genetic algorithms in a V-shaped experimental watershed.

Observational data available in the V-shaped experimental watershed of the University of Illinois was used for rainfall-runoff modeling. The studied watershed had an impermeable aluminum surface and two uniform side sheets with a one-sided slope towards the channel with a constant value of 1%. In addition, a central channel with a one-sided slope towards the outlet of the watershed with a constant value of 1% was present. The roughness coefficient in this watershed was determined based on trial and error at 0.014.

After preparing the time-area histogram of the watershed using each of the mentioned methods, the corresponding outflow hydrographs of the watershed were determined. Then, the results were compared with observational data, and various components of the computational hydrographs were also examined. The results showed that the performance of the genetic algorithm in determining the peak time of the hydrograph with a 15% relative error was better than the performance of the kinematic wave and HEC-1 models. Additionally, the genetic algorithm model had the highest correlation coefficient with observational hydrographs with an average Nash-Sutcliffe Index of 0.968 and an average correlation coefficient of 0.983. Furthermore, by fitting the curve to the modeling results, an equation was obtained to determine the equilibrium time of the watershed relative to rainfall intensity, with a determination coefficient of 0.999. This equation expresses the inverse relationship between equilibrium time and rainfall intensity (with a power of 0.33), i.e., doubling the rainfall intensity reduces the equilibrium time by 20%. Finally, the coefficient of the equation determining the equilibrium time for this watershed was found to be 495.2, and for each rainfall intensity, its corresponding equilibrium time can be calculated with high accuracy.

In this study, under experimental watershed conditions, rainfall-runoff modeling was performed with three categories of events and three categories of different rainfall durations, each event category having four different rainfall intensity sizes. Corresponding hydrographs were obtained for each event by examining the computational hydrographs and comparing them with observational hydrographs, and it was found that the three models had one to two percent relative error in determining the maximum runoff, but in determining the time to reach the hydrograph peak, the kinematic wave and HEC-1 models had an average error of 44%. Finally, using the correlation and Nash-Sutcliffe coefficients, it was determined that the computational hydrographs produced by the genetic algorithm method were closer to the observational hydrographs and had a higher degree of correlation. It is worth mentioning that in this experimental watershed, the dependence of equilibrium time on rainfall intensity in impermeable conditions was confirmed. It is recommended that the effect of infiltration or changes in surface roughness and the determination of the dependence size be investigated.

Water resources management, especially irrigation practices, is heavily reliant on reference evapotranspiration (ET0). ET0 is the rate of evaporation and transpiration from a standard reference surface with a presumed surface resistance of 70 s.m-1, the height of 0.12 m and an albedo of 0.23. Penman-Monteith FAO-56 (P-M FAO-56) approach is the most commonly used method for calculating ET0. In spite of the fact that FAO-PM is achievable, its implementation remains inconvenient because it requires a large amount of meteorological data, which is derived from standard meteorological observation stations. In the absence of complete climate data, it is highly desirable to have a model with fewer input climatic dates. Therefore, remote sensing methods have been used and improved over time to estimate ET0 at various spatial scales. Alternatively, it has been observed that the research community has become increasingly interested in obtaining data from metaheuristic algorithms that are based on artificial intelligence (AI).

In this research, it has been attempted to estimate the amount of daily reference evapotranspiration (ET0) using two data-driven models, using a combination of inputs from meteorological station data and satellite imagery data from MODIS sensor, by considering different inputs from these sources. The models include the random forest (RF) and hybridized RF with genetic algorithm optimization (GA-RF). Moreover, the correlation of input variables with ET0 is evaluated and the possibility of training a simple and accurate machine learning model in the conditions of lack or absence of meteorological data using satellite image data is investigated. So, this study aimed to determine ET0 in the time period of 2003-2021 using land surface temperature (LST) data and leaf area index (LAI) acquired from MODIS sensor and Tabriz meteorological station data including maximum and minimum air temperatures (Tmax, Tmin), average temperatures (T), wind speeds (U2), average relative humidity (RH), maximum and minimum relative humidity (RHmax, RHmin), and sunny hours (n). For the study area, daily LST were extracted from the Terra (MOD11A1) and Aqua (MYD11A1) satellites. Moreover, the LST of Terra and Aqua satellites were combined, since the LST values had missing data due to the presence of clouds. Furthermore, MODIS MCD15A3H version 6.1 using four-day data from Terra and Aqua satellites was used to determine the leaf area index (LAI). The standard P-M FAO-56 method for calculating daily reference evapotranspiration was considered as the base method. The set of input parameters was considered based on the cross-correlation of the parameters with reference evapotranspiration obtained from the FAO-Penman-Monteith equation.

The results of two data-driven models including standalone random forest (RF) and hybridized RF model with genetic algorithm (GA) to estimate ET0 values were compared with calculated ET0 by P-M FAO-56 equation. The results indicated that all of the studied input variables are highly correlated with the target variable. Based on the P-M FAO-56 method, the average air temperature with the highest value (R2=0.903) and the wind speed with the lowest value (R2=0.282) has a high and low correlation with reference evapotranspiration. Also, by comparing LAI and LST MODIS parameters, LST has the highest correlation coefficient with ET0 with R2=0.865. A total of twelve scenarios for estimating ET0 are evaluated, each with a different set of input parameters. Based on the correlation between the parameters and ET0, the first ten scenarios are categorized. Additionally, the eleventh scenario is based only on satellite images, and the twelfth scenario is based solely on weather station data. Based on the results, the GA-RF-10 (R2=0.976, RMSE=0.200, MAPE=11.373, and MBE=0.028), which includes all input parameters, outperforms the other models. There was a greater degree of accuracy with the RF-10 (R2=0.949, RMSE=0.293, MAPE=16.442, and MBE=0.017) when compared with the other random forest models. Based on the comparison of scenario 11 (satellite image data) and scenario 12 (meteorological station data), it appears that scenario 12 is more accurate for both RF (R2=0.922, RMSE=0.357, MAPE=20.712, and MBE=0.009) and GA-RF (R2=0.944, RMSE=0.306, MAPE=17.037, and MBE=0.013) models. Despite the fact that only satellite image parameters did not provide accurate estimation of ET0 compared to independent meteorological parameters, the inclusion of these parameters in the ET0 estimation resulted in more acceptable results, demonstrating the importance of satellite image parameters. Thus, satellite data may be useful and recommended for estimating ET0, particularly in areas without meteorological stations.