فهرست مطالب علی باریکلو

Heavy metals such as lead, aluminum, mercury, copper, cadmium, nickel, and arsenic are now commonly found worldwide. Among these, cadmium and lead are the most hazardous, posing significant risks to both the environment and human health. Cleaning soils contaminated with organic and inorganic contaminants is one of the most significant and fundamental challenges facing society today. One effective method for soil purification is to extract or immobilize the contaminant within the soil.

It is unclear how water-soluble polymers contribute to the immobilization of heavy metals. The purpose of this study is to examine how various polymers affect the immobilization of lead, zinc, and cadmium in the soil near a lead and zinc mine in the province of Zanjan. A factorial experiment with three replications was conducted using a randomized complete block design. The experimental treatments included one type of soil and three different kinds of acrylic polymers (cationic, nonionic, and anionic) applied at four different levels (0, 0.05, 0.1, and 0.2). The absorbable amounts of lead, zinc, and cadmium were tested at various intervals after the polymers were applied to the soil samples. After that, SAS statistical software was used to examine the data. To do this, the Duncan multiple range test was used to compare the means. The necessary tables and graphs were then created using Excel.

The findings demonstrated that, at 1% probability level, the kind of polymer had a considerable impact on the amount of lead, zinc, and cadmium that may be absorbed in the soil. The average concentration of soil-absorbable lead for the different types of polymers employed was 239.8, 260.15, and 267.65 mg/kg; anionic polymer had the lowest concentration. Stated differently, anionic polymer decreases the capacity to absorb lead and stabilizes more lead in the soil than the other two forms of polymer. Anionic polymers most likely have a stronger impact on soil granulation. Additionally, at 1% probability level, the impact of acrylic polymer intake on the amount of lead, zinc, and cadmium absorbable in the soil was considerable. With an increase in the amount of polymer utilized in the soil, the greatest absorbable lead concentration (301.58 mg/kg) in the control treatment dropped to the lowest absorbable lead concentration (0.2). It was possible to determine the polymer percentage and the lead concentration, which came out to be 205.9 mg/kg of soil. Zinc concentration dropped as acrylic polymer consumption increased; in the control treatment, absorbable zinc concentrations ranged from 0.2 to 83.5 mg/kg of soil, with 0.2 being the highest concentration. At 1% probability level, the impact of the polymer's contact time with the soil on the amount of lead, zinc, and cadmium that the soil may absorb was significant. As a result, the tested soil had 414.52 mg of these elements at the initial stage of polymer treatment. The quantity of absorbable lead in the soil became 66% immobilized after a month, and after 720 hours, the amount of absorbable lead dropped to 141.83 mg/kg. As the polymer's contact time with the soil increased, so did the concentration of absorbable zinc in the soil. At 1% probability level, there was a strong correlation between the kind and amount of acrylic polymers and the amount of lead, zinc, and cadmium that may be absorbed in the soil. The ingestion of 0.2% anionic polymer resulted in the largest amount of lead immobilization, lowering the soil's absorbable lead concentration from 300 to 192 mg/kg of soil. A higher amount of anionic polymer immobilized the lead, and both cationic and non-ionic polymers were positioned after it. Additionally, anionic polymer was more prevalent than cationic polymer. It caused the non-ionic polymer's absorbable zinc to become immobile. Following 720 hours of polymer treatment, the soil's absorbable zinc element was immobilized to a greater extent by the anionic polymer (20%) than by the cationic and non-ionic polymers (26%), respectively. In comparison to the original concentration, the largest amount of immobilization by anionic polymer after one month was 78%, and the lowest amount of immobilization by nonionic polymer was 61%. Anionic polymer was 27% more effective than non-ionic polymer, 18% more effective than cationic polymer, and stabilized more cadmium.

 The results of this study showed that with increasing the duration of contact of polymers used with the soil, the amount of mobility of heavy metals in the soil decreased and also with increasing the amount of polymer consumption, the rate of metal stabilization in the soil increased. Anionic polymers immobilize more lead, zinc and cadmium in soil. To reduce the mobility of lead, zinc and cadmium and improve the stability and increase aggregation in soil, the use of acrylic polymer in contaminated soil is recommended.

Soil quality is one of the most crucial factors determining crop productivity and production stability. The soil's physical, chemical, biological, and ecological characteristics affect its quality. Numerous researchers have concentrated the evaluation on a small number of soil quality indicators because measuring all soil quality indicators would be time-consuming and expensive. This study looked at the spatial autocorrelation of soil quality in the southwest areas of the Urmia Plain to establish the minimal data set for quantitative assessment. To accomplish this, 120 composite soil samples were collected from a depth of 0 to 60 cm, and the soil quality index was then calculated using the IQI method in 4 modes: Total-Linear (IQIwL-TDS), Total-Nonlinear (IQIwNL-TDS), Minimum-Linear (IQIwL-MDS), and Minimum nonlinearity (IQIwNL-MDS). 22 physical and chemical characteristics were used to choose the data set. The characteristics of sand percentage, sodium absorption ratio, cation exchange capacity, Available phosphorus, active calcium carbonate, and nickel concentration were chosen as the minimum data set (MDS) using the decomposition method into principal components. The linear IQIMDS mode produced the greatest soil quality index result, whereas the non-linear IQIMDS mode produced the lowest. The non-linear mode of the IQI index has a greater correlation coefficient (R2=0.85) than the linear mode of the IQI index (R2=0.73), according to an analysis of the linear and non-linear correlation coefficient between the soil quality index with the total category and minimum data. The findings of computing the global Moran's index for study sets of IQI soil quality index data revealed that the soil quality data are not independent of each other and are spatially autocorrelated, distributed in clusters, and have spatial autocorrelation. Getis-ord GI statistics indicated that the eastern and southeastern parts of the research region comprise clusters with poor soil quality, salt marshes produced by Lake Urmia's drying up, and surrounding arid plains.

One of the important issues in the sustainable management of soils in order to optimize the agricultural production and preserve natural resources is the assessment of soil quality.  Soil quality is the capacity of a specific kind of soil to function to sustain plant and animal productivity, maintain or enhance water and air quality, and support human health and habitation. It is also considered one of the most important factors investigated in the assessment of soil management. Knowledge of quality changes is necessary for sustainable soil management. Since soil quality cannot be measured directly, it must be obtained from the relevant characteristics. Soil quality characteristics are sets of measurable soil characteristics that are sensitive to land use change, management, or conservation operations. Using soil quality indicators is a useful tool to determine and compare soil quality. The purpose of this research is to quantify the soil quality index using multivariate analysis in different soil types in Urmia Plain.

In this research, according to the semi-detailed soil studies of Urmia plain, 24 soil profiles from different soil units of this area, which are mostly under garden and agricultural use, were excavated, described, sampled, and classified, and 96 samples were also collected from soil solum. 2 profiles in Typic Haploxerepts (TH1) soil type, 4 profiles in Fluvaquentic Endoaquepts (FE) soil type, 6 profiles in Typic Calcixerepts (TC) soil type, 2 profiles in Typic Endoaquepts (TE) soil type, 5 profiles in Fluventic soil type Haploxerepts (FH) and 2 profiles were located in Typic Halaquept (TH2) soil type. At a certain distance from the excavation site of the profiles, four soil samples were taken from four directions of the profile. Using principal component analysis (PCA), among 22 characteristics affecting soil quality (TDS), the minimum characteristics affecting soil quality (MDS) were determined. Then the soil quality in different soil types of region was evaluated using two cumulative soil quality indices (IQI) and Nemuro Quality Index (NQI) and each of them was evaluated in two sets of TDS and MDS in different soil types.

Among the measured parameters, pH had the lowest (2.5%) and salinity (EC) had the highest coefficient of variation (154.6%) in the region. Among the 22 measured soil properties, sodium absorption ratio (SAR) in the first component, nickel element (Ni) in the second component, cation exchange capacity (CEC) in the third component, sand percentage in the fourth component, active lime (ACCE) in the fifth component and absorbable phosphorus (PAW) in the sixth component were selected as MDS. The examination of the soil quality index showed that the soils of this region mainly have quality grade II (57%). The highest average value of selected soil quality index related to MDS mode in IQI model was calculated with a value of 0.79 in Fluventic Haploxerepts soil type and the lowest average value related to TDS mode in NQI model was calculated with 0.28 value in Typic Halaquepts soil type. The correlation coefficient between the soil quality index with the total category and minimum data in both IQI and NQI models was equal (R2=0.48).

The sequence order of both soil quality indices (IQIa, NQI) in both TDS and MDS conditions in the types of the studied area was as FE>TE>TH1>TC>FH>TH2. Therefore, the highest soil quality was observed in the Fluventic Endoaquepts type and the lowest soil quality was observed in the Typic Halaquepts type. Based on the results, both indicators were classified in three classes (good, medium and poor) in TDS and MDS sets. In the case of TDS, 57.83% of land (equivalent to 19731 hectares) had good class (II), 30.48% of land (equivalent to 10400 hectares) had medium class (III) and 11.69% of land (equivalent to 3990 hectares) they had poor class (IV); (very good (I) and very poor (V) class were not observed). In MDS mode, 18.56% of lands (equivalent to 6333 hectares) had very good class (I), 27.15% of lands (equivalent to 9264 hectares) had good class (II) and 54.29% of lands (equivalent to 18524 hectares) They had medium class (III); (weak class (IV) and very weak (V) were not observed). The degrees of IQIa and NQI indices were similar and were divided into three classes (good, medium and poor). As a result, 39.3% of land (equivalent to 13412 hectares) was in good class (II), 24.59% of land (equivalent to 8392 hectares) was in medium class (III) and 1.36% of land (equivalent to 12317 hectares) was placed in poor class (IV); (very good (I) and very poor (V) classes were not observed). In general, the soils of the region were limited in terms of the studied indicators in the parts leading to the lake, and there was a significant correlation between IQITDS and IQIMDS, and between NQITDS and NQIMDS. This shows that the determined MDS set can be a good representative of TDS in soil quality assessment in Urmia Plain.

A variety of precise farming practices in arid and semi-arid regions such as Iran require periodic information on soil salinity and sodium content. Sodic soils have unfavorable physical and chemical properties due to the high percentage of exchangeable sodium (ESP). This problem reduces the capacity of available water and growth of plants. To measure the percentage of exchangeable sodium, it is necessary to measure the amount of cation exchange capacity (CEC). Because determining CEC are time consuming, it is appropriate and economical to develop a method that determines ESP indirectly from easy-measured properties. One of the methods to study the relationships and correlations between different soil properties and their quantitative expression is the use of some statistical models. These models, called transfer functions, include data mining, regression models, artificial neural networks, and the coherent neural-fuzzy integrated system (CANFIS).

The aim of this study was to develop an intelligent model (CANFIS) for predicting soil ESP from soil easy-measured properties in approximately 1450 ha of salt affected soils, South East of Urmia Lake, Bonab region, East Azarbaijan Province. For this purpose, 209 soil samples were taken by grid survey method from surface (0-25 cm) and then carried out laboratory for measure necessary soil properties. Soil acidity and electrical conductivity of samples were measured in a ratio of 1: 5 soils to water, soil tissue by hydrometric method, sodium cation by flame photometer and calcium and magnesium by returned titration method.

Pearson correlation method showed that the accuracy of estimating intelligent models depends on the correct choice of first layer input information. Therefore, using the correlation matrix, the relationship between soil parameters (independent variable) and the percentage of exchangeable sodium (dependent variable) was determined. Sodium absorption ratio (0.961), electrical conductivity (0.808), pH (0.638), clay content (0.524), sand (0.482) and silt (0.389) have the greatest effect on estimation Percentage of exchangeable sodium in soil. Also, the positive relationship between soil reaction and the percentage of exchangeable sodium on the one hand and the high correlation between the percentage of exchangeable sodium and electrical conductivity indicate the importance of the fine soil. In this study, the relationship of linear regression between the percentage of exchangeable sodium and the ratio of sodium uptake with an explanation coefficient of 0.91 was calculated, which is significant at the level of 5% probability. Two important targets were designed in this paper. First target is determining performance of Fuzzy Neural Networks (CANFIS) in predicting ESP by sand, clay, pH, SAR, EC as input variable. The second target is evaluation of performance of CANFIS model by selected variable of PCA model. Results showed that the performance of second model was acceptable Model 1 justifies 88% of the changes in the percentage of exchangeable sodium by entering all inputs. But CANFIS model with higher inputs selected by PCA model (principal component analysis) including sodium adsorption ratio, electrical conductivity, soil reaction has higher accuracy. So that the values of root mean square error and correlation coefficient in the test stage for the first model were 0.88 and 3.25 and the second model was 0.96 and 1.0, respectively.

These results demonstrated the superiority of intelligent models in explanation of the relationship between ESP and other soil easily-measured properties. In order to model the soil retrieval properties such as cation exchange capacity and to achieve the most suitable model, it is necessary to pay attention to the number and most effective input variables. Because the main goal is to provide a model with a minimum number of inputs as well as inputs that are easy to measure and in a short time. The results of quantification of the importance of variables in the CANFIS model confirm the use of three characteristics of sodium adsorption ratio, electrical conductivity of soil saturated extract and soil acidity in modeling the percentage of exchangeable sodium. The results of this study can be generalized to soils of similar arid and semi-arid regions. Also, due to the ambiguity of soil-related phenomena or the approximate values of the measured values of different soil properties and the uncertainty in the data, the use of hybrid models such as CANFIS that use fuzzy sets, It can be useful in fitting soil transfer functions.Keywords: Easly-measured Properties, Hard-measured Properties, PCA All right reserved.

Land suitability evaluation Based on FAO's Framework is the most widely used assessment method. One of the failures of this method is a lack of crop requirements attribute for fruit trees. The Automated Land Evaluation System (ALES), is a microcomputer program that allows to the users to build their own knowledge-based systems which they can evaluate the physical suitability of land units, based on the FAO's Framework. The main destination of this research was to apply ALES program for land use suitability determination of grape, apple and peach in Malekan region (East Azerbaijan province). For this purpose, soil morphological and analytical data were carried out for 13 lands unites based on geopedological methods. The control section data between 0 and 150 cm were calculated by “soil layer generator” to apply and run the ALES program. Climate evaluation showed that the study area is completely suitable for each three land uses. The main recognized soil limitation factors were calcium carbonate and texture in the total of study area for selected land uses. Application of ALES program revealed that 100% of study region is suitable (S1 and S2) for grape, 70% for apple and 28% for peach. Also, land use could be arranged according to their land suitability classes as follows: peach < apple < grape. This arrangement reflects the priority for agricultural uses. Finally, ALES program appears to be useful in semi-arid regions, such as East Azarbaijan, for fruits trees land suitability evaluation, and formulate sustaining agro-ecological systems.

Soil cation exchange capacity (CEC) is defined as the amount of positive charge that can be exchanged per mass of soil. Modeling and estimating of CEC is a useful index of soil fertility. Assessing and designing various management scenarios requires having accurate information regarding the soil data bank. In order to estimate the soil CEC, 32 profiles were dug in Tabriz plain, and 131 different samples were collected from different depths and physiochemical experiments such as particle size distribution, organic carbon, pH and CEC of soil samples were performed. Then using seven regression models that were selected based on previous studies, were calibrated and evaluated for the study area. Also seven different architectures of artificial neural networks were designed to predict the CEC of soil and the results of artificial neural networks and multivariate regression models were evaluated using correlation coefficient (R2), root mean square error (RMSE). Results revealed that artificial neural network with R2 = 0.86 and RMSE= 2.14 is better than regression based functions due to the existence of nonlinear relations between the easily available soil properties (independent variables) and the CEC (dependent variable).

Soil properties at the lands lot scale is a process that effects on infiltration rates, which can lead to an increased stormwater runoff. Sustainable land management for runoff controls requires reliable information on the spatial distribution of soil infiltration rate. The traditional method of soil analysis and interpretation are laborious, time-consuming, hence becoming expensive. Therefore spatial analysis of infiltration rate is necessary for the determination of susceptible areas for surface runoff. The purpose of this study was to propose alternative approaches in searching for infiltration rate and surface runoff hotspots. The study was conducted on an agricultural field at Khodafarin, East Azarbaijan province, Iran. It is with 675500 to 692500 longitudinal coordinates and 4332500 to 4349000 latitude coordinates. To arrive at the goal of this research, 88 sample points were selected with using a geographic information system and considering the Soil distribution pattern and land utilization. Infiltration rate data was collected from double rings method with 3 replicated at each point. Soil samples were obtained from each point and then sent to soil analyzed laboratory to determine physical and chemical properties. Kriging method was used for the interpolation of the study area. Finally, soil properties distribution layer expended in Arc GIS software that analyzing hot spot surface runoff hazard. The significant correlation of infiltration rate with soil parameter including porosity, sand, silt, and organic content. Overall, at wide distances of case study lands organic material and porosity were assessed effectively to water permeability into the soil and other measured parameters due to statistics were without specified spatial distribution. The results showed that Simulation generates equally likely sets of values for a variable, which are consistent with available in-situ measurements. The information on spatial sampling density and hotspot pattern could be useful for long-term monitoring and assessment.

Infiltration plays a pivotal role in the hydrologic cycle by effectively acting to partition water into surface and subsurface components. Direct measurement of infiltration rate is expensive and work and time consuming. Artificial Neural Networks (ANNs), Gene Expression Programing (GEP) and hybrid of ANN and Genetic Algorithm (ANN-GA) can be used for estimation of soil infiltration rate as an indirect methods. The main objective of this research was to develope an infiltration rate model in Khoda afarin region based on the collected data (88 double ring infiltration) and some soil properties. The Pierson correlation revealed among the soil properties, sand and silt contents, porosity and organic matter have the most correlation with the infiltration rate. Determination Coefficient (R2) and Normalized Root Mean Square Error (NRMSE) were calculated to be 0.88 and 7.9%, respectively for the ANN method and 0.75 and 11.3% for the GEP method. Both ANN and GEP methods perform poorly, in extrapolating the minimum and maximum amount of infiltration rate. The hybrid model of ANN-GA was the best model in terms of statistical indices including R2 (0.93) and RMSE (6.1%). This model comprised of 4 neurons (sand, silt, porosity percentage and OM) in input layer and 5 neurons using sigmoidal tangent functions in the hidden layer and linear activation functions in the output layer. The results indicated that the neural-genetics algorithm can be used to optimize weight parameter of artificial neural network. Overall the hybrid ANN-GA model showed better performance than the other models, so that the R2 and NRMSE for the hybrid model were 0.93 and 6.1% respectively. Therefore it is suggested as a powerful tool for estimating infiltration rate.

Two different criteria are exist in the soil science as indices of Alkality. These are the Sodium Adsorption Ratio (SAR) and the Exchangeable Sodium Percentage (ESP). As shown for measured of ESP, it is essential to have soil Cation Exchange Capacity (CEC). But, For CEC determined using laborious and time consuming tests, it be more appropriate and economical to develop a model that predict ESP indirectly from a easily-measured properties. Researches showed a relationship between ESP and SAR. So, SAR can be allocated to predict of ESP. For this reason, many attempts have been made to predict ESP from soil. The specific goal of the research develop model to determining ESP based on SAR by OLS and BN models for Bonab soils in East Azarbaijan province, Iran. For arrived presented research, 209 soil samples were taken by grid survey (250˟250) of Bonab, Iran. The site is located at mean 1300 m above mean sea level, in semiarid climate in the Northwest of Iran. Then, some soil chemical properties such as Na+, Ca2+, Mg2+, SAR and ESP of the soil samples were measured using laboratory experiments. Then, two model was developed by OLS and BN. OLS estimators are linear functions of the values of the dependent variable which are linearly combined using weights that are a non-linear function of the values of the explanatory variables. So the OLS estimator is respect to how it uses the values of the dependent variable only, and irrespective of how it uses the values of the explanatory. So A Bayesian network is a probabilistic graphical model that represents a set of variables and their conditional dependencies via a directed acyclic graph (DAG). Given symptoms, the network can be used to compute the probabilities of the presence of various diseases. Efficient algorithms can perform inference and learning in Bayesian networks. Generalizations of Bayesian networks that can represent and solve decision problems under uncertainty. The Coefficient of Determination (R2) and Root Mean Square error (RMSE) of the soil ESP-SAR model is reported 0.99, 0.71 and 0.98, 1.63 by OLS and BN respectively. Based on the statistical result, both of soil ESP-SAR model was judged acceptable. T-test were used to compare the soil ESP values predicted using the soil ESP-SAR model with the soil ESP values measured by laboratory tests. The paired samples t-test results indicated that the difference between the soil ESP values predicted by the model and measured by laboratory tests were not statistically significant (P>0.05). Therefore, the soil ESP-SAR model can provide an easy, economic and brief methodology to estimate soil ESP. The GMER index also indicated low estimation of two selected land evaluation method. The results of present study illustrated that OLS and BN models can predict ESP with acceptable limits. OLS and BN are mathematical models between input and output variables and has the ability of modeling between ESP and SAR.

Increasing demand for agricultural products and lack of appropriate soil and water resources with problems of field research reveals the application of efficient models to predict crop yield. This research aimed to examines the efficiency of artificial neural networks, comparative fuzzy neural network, adaptive nero fuzzy inference system and particle swarm optimization algorithm models for estimating the wheat yield through soil and land properties. For this purpose, 80 soil profiles were drilled in wheat fields’area in East Azerbaijan province with temperature and moisture regimes of mesic and aridic border to xeric, respectively. Soil samples were collected from each genetic horizon. The results of sensitivity analysis showed that total nitrogen, absorbable phosphorus, slope, gravel, soil reaction and organic matter are effective soil properties in wheat yields. The hybrid model of PSO-ANFIS was the best model from the viewpoint of statistical indices including R2 (0.89) and RMSE (213.5). Also, neuro-fuzzy method has a R2 (0.84) and RMSD (243.2) and artificial neural networks have a R2 (0.81) and RMSD (274.5), respectively. The GMER index also indicated overestimation of artificial neural network (0.24) and nero fuzzy (0.53) and underestimation of PSO-ANFIS model (1.13). The results indicated that the hybrid neuro-fuzzy-swarm particles model performed better than other models that can be used a powerful tool for estimating wheat yield.

Refer to the growing pollution of water resources and importance of their constant monitoring, in this section comprehensive review of rare elements and heavy metals in underground water in some parts of Mahneshan city and Dandi region was done to check the effects of mineral actions, related industries and agricultural activities in this region. During the research 12 samples from 6 deep rural drinking water provider wells were selected in 3 times and analyzed with ICP-OES for heavy metals such as (Lead,Arsenic,Cadmium, chrom).The highest level of contamination was compared with the guides of America's environmental protection agent and Iran's national standard. Results showed that measured elements were below the allowed level. Also human health risk was assessed, using EPA factor. Average of heavy metals's density in spring for Lead, Arsenic, Chrome and Cadmium was 0.00083, 0.0024 and 0.00079 and in summer 0.00090, 0.0029 and 0.00080 mg/l. Results showed that there is not any significant statistical difference between results of heavy metals's density that was measured with world and national standards. Assessment results for relation between risk of heavy metals and health of region residents was calculated 19*5-10 for cancer related diseases and 4*6-10 for nonrelated ones. Results of measured density of heavy metal and its comparison with standards (Iran’s national standard, world hygiene organization's standards, America's environmental protection agent) illustrated that the region of study is not threatened with any hygienic risk.

In recent decades, the most important issue for agricultural activities is maximizing the productions. Today, wheat is grown on more lands than any other commercial crops and continues to be the most important food grain source for humans. Sustainable agriculture is a scientific activity based on ecological principles with focus on achieving sustainable production. It requires a full understanding of the relationships between crop production with soil and land characteristics. Furthermore, one of the objectives of sustainable agriculture is enhancing the agricultural production efficiency through applying proper management, which requires a deep understanding of relationships between production rate, soil and environment characteristics. Hence, the first step in this process is finding appropriate methods which are able to determine the correct relationships between measured characteristics of soil and environment with performance rate. The aim of this study was evaluating the performance of neuro-genetic hybrid model in predicting wheat yield by using land characteristics in the west of Herris City.
The study area was located in the northwest of east Azarbaijan province, Heris region. In this study, 80 soil profiles were surveyed in irrigated wheat farms and soil samples were taken from each genetic horizon for physical and chemical analyses. In this region, soil moisture and temperature regimes are Aridic border to Xeric and Mesic, respectively. The soils were classified as Entisols and Aridisols. We used 1×1 m woody square plots in each profile to determine the amounts of yield. Because of nonlinear trend of yield, a nonlinear algorithm hybrid technique (neural-genetics) was used for modeling. At first step, the average weight of soil characteristics (from depth of 100 cm) and landscape parameters of selected profiles were measured for modeling according to the annual growing season of wheat. Then, land components and wheat yield were considered as inputs and output of model, respectively. For this reason, genetic algorithm was investigated to train neural network. Finally, estimated wheat yield was obtained using input data. Root mean square error (RMSE) and Coefficient of determination (r2), Nash-Sutcliffe Coefficient (NES) indices were used for assessing the method performance.
The sensitivity analysis of model showed that soil and land parameters such as total nitrogen, available phosphorus, slope percentage, content of gravel, soil reaction and organic matter percentage played an important role in determining wheat yield in the studied area. The soil organic matter and total nitrogen had the highest and lowest correlation with wheat yield quantity and quality, respectively, indicating the total nitrogen was the most important soil property for determination of wheat yield in our studied area. We found that network learning process based on genetic algorithms in the learning process had lower error. The findings showed that beside of confirming the desired results in the case of using sigmoid activation function in the hidden layer and linear activation function in the output layer of all neural networks, it is demonstrated that the proposed hybrid technique had much better results. These findings also confirm better prediction ability of neural network based on error back propagation algorithm or Levenberg-Marquardt training algorithm compared to other types of neural network confirms.
Using nonlinear techniques in modeling and forecasting wheat yield due to its nonlinear trend and influencing variables is inevitable. Recently, genetic algorithms and neural network techniques is considered as the most important tools to model nonlinear and complex processes. Despite the advantages of these techniques there are a lot of weaknesses. Imposing specific conditioned form by researchers in the techniques of genetic algorithms and stopping neural network learning at the optimal points are the main weaknesses of these techniques, while searching for global optimal point and not imposing a specific functional forms are the robustness of genetic algorithm techniques and neural networks, respectively. Results of this study indicated that the proposed hybrid technique had much better results. Correlation coefficient (0.87) and average deviation square error (473.5) were high and low, respectively. It can be concluded that the surveyed soil properties have very strong relationship with the yield. Implementation of appropriate land management practices is thus necessary for improving soil and land characteristics to maintain high yield, preventing land degradation and preserving it for future generations required for sustainable development.