نشریه مهندسی زراعی
سال چهل و هفتم شماره 3 (پاییز 1403)

The recovery of phosphorus as struvite from treatment plants has attracted researchers' attention due to its potential as a phosphorus fertilizer. Struvite is a white crystalline substance consisting of magnesium, ammonium and phosphorus in equal molar concentrations (MgNH4P04.6H2O). The low water solubility of struvite is thought to limit its agronomic utility as a phosphorus (P) fertilizer compared with highly soluble P fertilizers (triple superphosphate). Because limited studies have been done regarding the effect of struvite on the availability of phosphorus in calcareous soils. Therefore, this study examines the effect of struvite replacement with triple superphosphate fertilizer on phosphorus availability in wheat plants in calcareous soils deficient in phosphorus.Methods and Materials: Soil with phosphorus deficiency was collected from 0-30 cm depth under arable lands of Hajjiabad-e Seyyedeh located in Ghorveh township, Kurdistan Province, Iran. The soil was air-dried and ground to pass through a 2-mm sieve, followed by laboratory analysis to determine its physico-chemical properties. Struvite used in the research was obtained by optimizing the three main factors of sulfuric acid concentration, solid-to-liquid ratio, and time for the leaching process, and the three key factors of Mg/P ratio, N/P ratio and pH for the precipitation process by Response Surface Methodology. To achieve the aim of this study The factorial experiment was carried out in the form of a completely randomized design in 3 replications. The factors include the application of different proportions of struvite replaced with triple superphosphate in 6 levels (S0:P0, S0:P100, S25:P75, S50:P50, S75:P25 and S100:P0) and 3 levels of phosphorus (50, 100 and 150 kg/ha) and a total of 54 pots. The application rate for struvite was calculated based on total phosphorus (P2O5) of triple superphosphate. Then 10 wheat seeds were planted in each pot at 2-cm depth which after plant emerging and greening declined to 4 plants in each pot. The pots were randomly moved twice a week during the growth period to eliminate environmental effects. Irrigation and weeding operations were done by hand. Plants (shoots and roots) were harvested 60 days after planting (beginning of flowering), washed with distilled water and dry with tissue paper. The samples were air-dried and then oven dried at 70˚C to a constant weight in a forced air-driven oven. Phosphorus concentrations in plant extracts by the molybdenum vanadate or yellow method and Nitrogen concentration in plant was measured by the Kjeldahl method. After harvesting the plants, the soil was immediately air-dried and passed through a 2mm sieve. Then, the amount of phosphorus was determined by Olsen method. The statistical results of the data were analyzed using SAS software and LSD test (at 5% level) was used for comparing the mean values.

Based on the obtained results, all of the investigated treatments and their interactions were significant at the probability level of one percent (P < 0.01). The comparison of the average effects of different struvite treatments showed that by replacing struvite instead of triple super phosphate fertilizer in all three levels of fertilizer, the highest shoot fresh weight (with an average of 7.79 gr/pot), shoot dry weight (with an average of 1.13 gr/pot) shoot Nitrogen concentration (with an average of 4.82%) and its uptake (with an average of 5.44 gr/pot) was obtained from the application of S75:P25 150 kg/h superphosphate fertilizer. Also, the results showed that the highest amount of phosphorus concentration and uptake, respectively, with an average of 0.174% and 0.197 gr/pot, was obtained from the application of the S75:P25 treatment with 150 kg TSP/ha, which is compared to the application of the S75:P25 treatment of 50 and 100 kg TSP/ha had an increase equivalent to 26.43, 59.89, 11.49 and 43.14% respectively. The results also showed that the highest amount of soil phosphorus after harvesting the plant with an average of 18.95 mg/kg was obtained from the S100:P0 treatment with 150 kg TSP/ha, which compared to the S100:P0 treatment with 100 and 50 kg TSP/ha with an average of 13.29 and 12.56 mg/kg had an increase equivalent to 29.86 and 33.72%, respectively.

In spite of its low solubility, struvite is as effective as highly soluble phosphorus fertilizers for plants. There is still a lack of clarity regarding the mechanisms of struvite dissolution as well as the reasons behind this apparent dichotomy. Therefore, more accurate measurements of pH and EC in substrates, analysis of soil properties and fractionation of phosphorus in soil will enhance our understanding of the use of struvite. Therefore, it is recommended to optimize the timing and application rate of struvite in relation to the demand for different agricultural and garden crops

Anthurium (Anthurium scherzerianum schott) is one of the most important ornamental plants with beautiful leaves and flowers. The quantitative and qualitative characteristics of this flower can be affected by many factors, including the cultivation and feeding system. Biochar is a carbon-rich solid material that is produced during the process of pyrolysis (decomposition of organic materials by heat in the absence of oxygen or a small amount of oxygen). It includes elements such as (Si, P, S, N, H, O, K, alkali cations and heavy metals) with different proportions. In addition, humic acid is used as a biological polymer in the agricultural field to increase the efficiency of cultivation of various plant products, improve the efficiency of fertilizer consumption, the possibility of using it in soilless and greenhouse cultivation environments and increasing the efficiency of water consumption.

This study was conducted to investigate the effect of biochar and humic acid on the quantitative, qualitative and nutritional characteristics of anthurium flowers as a factorial experiment based on randomized complete block design in three replications in the greenhouse of the Faculty of Agriculture of Shahid Chamran University of Ahvaz during 2017-2018. In order to perform this experiment, first, Anthurium seedlings were prepared from the Anthurium flower production greenhouse located in Pakdasht Varamin and transferred to the greenhouse of Shahid Chamran University of Ahvaz. Then they were cultivated in 15 liter pots containing cocopeat and perlite in a ratio of 1:1. The treatments included biochar at 3 levels (0%, 5%, and 10% by weight), which was provided to the substrate at the same time as cultivation, and humic acid at 3 concentrations of 0, 500, and 1000 mg/liter. The end of experiment, indicators such as fresh and dry weight of roots, root surface, chlorophyll a and chlorophyll b and carotenoids, total soluble carbohydrates, nitrogen and potassium were measured.

The results showed that the use of biochar and humic acid significantly increased the morphological characteristics such as fresh and dry weight of roots, number of leaves, root surface and leaf surface. The highest fresh weight (50.62 grams) and dry weight (5.12 grams) of the root was obtained by using 10% biochar along with 1000 mg/liter of humic acid. There was a significant difference between plants treated with 1000 mg/liter of humic acid and 500 mg/liter of humic acid in all different levels of biochar on leaf number. The highest number of leaves (82.66) in the highest concentration of humic acid and biochar were obtained. The highest number of flowers was obtained at the highest level of humic acid and biochar. Also, biochemical properties such as chlorophyll and carotenoid and nutritional properties such as nitrogen and potassium increased significantly under the influence of treatments. The increase in growth parameters can be due to the effect of these two compounds in increasing the photosynthetic pigments, improving the absorption of water and nutrients, including nitrogen and potassium. Biochar, as a compound resulting from the anaerobic pyrolysis of different biomasses, changes the physical and chemical characteristics of the cultivation environment and increases the capacity to hold water and nutrients, increase total porosity and ventilation porosity, living and non-living biological compounds. On the other hand, humic acid, as a biopolymer, has a high ability to stimulate chemical reactions in the plant environment, especially in the rhizosphere of the plant. It is worth mentioning that the behavior of humic acid as a biopolymer in the plant environment can also affect the secondary metabolites of the plant, which has been reported in various studies for plants.

In general, Mechanisms such as increasing root activity due to increasing cationic capacity, increasing water retention capacity in the culture medium, increasing biological activities in the culture medium during the application of biochar are important and key factors that they can affect the absorption of different nutrients and the biochemical reactions of the rhizosphere environment of the plant. Therefore, the results showed that the consumption of biochar and humic acid significantly increased in vegetative characteristics, reproductive characteristics, photosynthetic pigments and nutritional elements such as nitrogen and potassium. The use of 10% biochar and 1000 mg/liter of humic acid was the most effective treatment in improving the mentioned factors.

The use of remote sensing, due to the provision of timely data and the high capability of image analysis, as well as the possibility of studying in a wide range with acceptable accuracy, is of great help to the planners and implementers of the agricultural sector. Remote sensing is one of the effective tools for monitoring, studying and determining the level of cultivation of agricultural and horticultural products, especially in large areas. Therefore, Annual Landsat images are valuable resources that enable crop monitoring in issues related to diagnosis, crop yield prediction, and crop-cultivation pattern studies.

Landsat 8 and OLI satellite images related to 2018 were used to estimate the overall level of crops in the area and to separate the agricultural area from other areas. These images were downloaded from the site http://earthexplorer.usgs.gov, which is related to row 37 and path 166. In order to collect additional information used in this research, Google Earth images and ground control points taken with a GPS device, Garmin model 64s, were used. Finally, the area under cultivation of the products was calculated. The statistics of the Ministry of Agricultural Jihad in the crop year 2016-2017 were used to evaluate the results. The classification steps are done to classify different classes.

For this purpose, in this research, to estimate the monitoring of main crops in the area and to classification agricultural crops, satellite images of Landsat 8 sensors with OLI sensor and NDVI index related to the time series of one-year images were used. The area of wheat and barley cultivated land in the region was estimated to be 10639 hectares, which shows an error of about 6.8% compared to the results of Jihad Keshavarzi statistics, which is 9956.56 hectares. After classifying the satellite images, using teaching samples that were not involved in the classification process, the accuracy of the classified image was evaluated. In this research, after calculating the cultivated area in GIS, the results were validated by comparing with the available statistics of Jihad-Agriculture and regional service centers and time control points by GPS, kappa coefficient and general accuracy coefficient. Supervised classification method with support vector machine algorithm and artificial neural network was used to separate farms. The crop classification maps were divided into 5 categories, wheat and barley, summer crops, rice crops, irrigated crops and non-agricultural lands. The lowest amount of commission error in both classification methods, 8.1 %, is related to summer cultivation, and the emission error in non-agricultural lands was 0.5 % in support vector machine method and 2.5% in artificial neural network method. Sentinel-2 images with a spatial resolution of 10 meters were used to prepare the classification map.

Conclusion :

After classification, the maps produced by satellite images were compared with reference data and ground facts, as well as with the help of satellite images available in Google Earth software. Then the error matrix was formed. Kappa coefficient and overall accuracy were obtained in the vector machine method as 0.74 and 68%, respectively, and in the neural network method as 0.70 and 76% respectively.

Coffee is a common drink which is obtained from the roasted and ground beans of the coffee plant. Coffee beverages are widely consumed as a stimulant, a property largely attributed to the presence of caffeine, which is the most active pharmaceutical ingredient consumed worldwide. When the fruit of the coffee plant ripens, the coffee beans are harvested, processed, and finally dried. Dried coffee beans are roasted to different degrees and graded depending on the desired aroma and taste. It is very important to detect natural and unnatural impurities and adulteration in coffee.

An odor machine system based on eight MOS sensors was used to investigate the effect of bread storage time based on odor characteristics. The designed system includes a data acquisition system, sensors, sensor shield, sample container, power supply, connections, electric valves, air pump, and air filter. The sensor array consisted of 8 MOS sensors, including MQ136, TGS822, MQ9, MQ3, TGS813, TG2620, TG2602, and MQ135, each reacting to specific volatile compounds. These sensors are widely used in olfactory machines because of their high chemical stability, high durability, low response to moisture, and affordable prices. They are the most commonly used sensors in electronic nose systems. Sensors are the main components of an electronic nose system; therefore, it is necessary to select sensors able to detect differences among samples. In this research, the use of electronic nose technology and artificial intelligence was evaluated to detect common adulteration in Arabica coffee (Medium Dark). Robusta coffee samples with weight percentages of 10, 40, 30, 20, and 50% were used for experiments and adulteration. An electronic nose equipped with eight metal oxide sensors was used to carry out experiments related to odor. The data received from 8 sensors was first recorded and stored as raw data. In this research, the fractional method was used to normalize the data. Preprocessed data were used as the input matrix for multivariate analytical methods. The unsupervised multivariate principal component analysis (PCA) method was used to analyze the data. The LDA method was used to reduce classification differences and expand the differences between different groups. The artificial neural networks (ANN) method was used for classification. All calculations and analyses were done using Excel 2016, Unscrambler x10.4, and MATLAB software. Model evaluation criteria are used to evaluate algorithm performance in supervised learning. To analyze the system's performance, common criteria including Specificity, Recall, Precision, Accuracy, Area Under the Curve (AUC), and F-score were used.

The results of PCA showed that 87% of the total variance of the data was explained by PC1, and 8% by PC2, and the two main components constituted 95% of the total variance of the normalized data. Based on the results, pure Robusta coffee (B) was located on the right side of the PCA diagram and completely separate from other levels of adulteration. Also, pure Arabica coffee (A) was placed in the vicinity of counterfeit samples, and all counterfeit samples showed the same behavior as Arabica coffee, which is very difficult to distinguish. The loading diagram was examined to determine the role of sensors in separating the groups. Based on the loading diagram for coffee adulteration detection, the sensors that had the highest value on the principal component were MQ9, TGS822, and MQ136. Other sensors also showed a high correlation with the smell of the samples. In other words, other sensors could be neglected. The models of artificial neural networks analysis were evaluated by the correct classification rate (CCR), root mean square error (RMSE), and coefficient of determination (R2). According to the results obtained for 7 different coffee groups, the 7-8-8 structure had the best results. This structure has 8 neurons in the input layer (number of sensors), a hidden layer with 8 neurons, and 7 neurons in the output layer (7 groups). The average values of the class obtained from the ANN model for the parameters of accuracy, precision, recall, specificity, area under the curve (AUC), and F-score were equal to 0.984, 0.952, 0.943, 0.990, 0.971, and 0.942, respectively. Also, the ANN method showed higher accuracy than the LDA method.

The electronic nose showed that it is a fast and effective tool for detecting adulteration substances in coffee.

Compressed air is a versatile energy source used in various applications. However, pumping water with compressed air requires specific designs. Various designs have been proposed for pumping water using compressed air. Some of these designs include Air jet pumps, air-lift pumps, diaphragm pumps, and hydro-pneumatic pumps (discrete flow). The hydro-pneumatic pump is composed of a chamber with two unidirectional valves for intake and discharge, separated by a well. Additionally, it includes an internal tube connected from the top to the outlet unidirectional valve. As compressed air enters the chamber, it applies pressure on the water surface within the chamber, resulting in the closure of the intake valve and the opening of the outlet valve, facilitating the upward pumping of water through the internal tube. Studies have been carried out in the field of jet pumps and air-lift pumps. However, the notion of enhancing flow rate and efficiency by integrating the pumping mechanisms of these pumps gave rise to the original idea of developing a hybrid water pump with a compressed air driver. The primary goal was to approach the efficiency of a hydro-pneumatic pump and simplify the design, allowing water pumping without the need for sensors or control systems.

To assess the compressed air water pump and compare its performance with a hydro-pneumatic pump, a prototype with similar dimensions was constructed. By turning on or off and combining three compressed air nozzles within the pump structure, it was possible to operate the Combinatorial compressed air pump in four different modes. During field experiments, the performance, which included measuring input air pressure, flow rate, and water pumping height, was measured. Additionally, the efficiency of the Combinatorial compressed air pump was calculated under experimental conditions. Field experiments was conducted using a factorial design in randomized blocks. Treated variables included immersion depth (4 levels), inlet air pressure (6 levels), pump types and their working modes (5 levels). Discharge flow rates and water pumping height were measured across four replicates. at post processing, pumping efficiency calculated. Analysis of variance and post-hoc tests were conducted to analyze the significant effects of treatment variables and their interactions. to identify the best level for each treatment across different levels of other treatments, interaction slicing was employed. result was presented in charts and tables.

The variance analysis revealed a significant difference at the 1% confidence level among pump types, Immersion depth, input air pressure, and their interactions on water pump flow rate. Increasing submergence depth led to higher flow rates in the hydro-pneumatic pump, Combinatorial pneumatic pump, Bubble pump, Bubble & Airlift combined pump, and air-lift pump. Additionally, raising input air flow resulted in increased water pumping rates for all types of pumps.The hydro-pneumatic pump exhibited higher flow rates compared to other pumps, attributed to its positive displacement structure. The flow rate in all pumps increased with higher input air pressure due to the increase in air flow.The variance analysis on pump efficiency showed significant differences at the 1% confidence level in input air pressure levels, Immersion depth, pump type, and their interactions. With increased Immersion depth, pump efficiency rose in the following order: Combinatorial pneumatic pump, hydro-pneumatic pump, Bubble pump, Bubble & Airlift combined pump and air-lift pump, and air-lift pump. The Combinatorial pneumatic pump showed the most positive impact of Immersion depth on efficiency.Immersion depth, inlet air pressure, and pump type significantly impacted discharge rate and pump efficiency. With increased immersion depth and air pressure, discharge and efficiency rose for all pump models and operating modes. The hydro-Pneumatic pump achieved higher efficiency and discharge due to its different structure. At 2m immersion depth, the best performance among all pump models and modes was observed: Airlift pump (10.3% efficiency), Bubble pump (20.8%), Bubble & Airlift Combined pump (19.3%), Pneumatic Combined Pump (27.1%), and Hydro-Pneumatic pump (25.2%).

While the hydro-Pneumatic pump offered superior performance, the compressed air pump's simpler structure and lack of electronic control circuitry present advantages. Future research could explore optimizing the compressed air pump design for improved efficiency while maintaining its structural simplicity. Due to structural differences, the hydro-pneumatic pump exhibits significantly higher efficiency (approximately 54%). It was expected that this efficiency would be maintained with increasing pressure, but due to the limited immersion depth in the experiments and dimensional mismatch of the pump with high input air pressure, we observed a decrease in efficiency at higher pressures. This indicates that for each submergence depth and pump head, there is an optimal pressure that the pump dimensions should be designed to suit.

Drying is one of the most economical ways to preserve food and is used to increase its shelf- life. Microencapsulation protects sensitive foods from adverse environmental conditions (such as the effect of moisture and oxygen) and reduces food quality fluctuations. The principle of microencapsulation via spray drying is to prepare an emulsion or suspension and spray it in the hot air of the drying chamber. Plant pigments, such as anthocyanins, have been considered, but they are unstable under processing conditions. Hibiscus sabdariffa (sour tea) is a resistant herbaceous shrub and annual or perennial plant that contains anthocyanins. More than 300 types of sour tea are found in tropical and subtropical regions worldwide. Gum Arabic and maltodextrin are used as carrier materials to maintain the stability and functional characteristics of the powder prepared by spraying. Owing to its high solubility, low viscosity, and suitable emulsifying properties, gum Arabic is a carrier of interest in the spray drying process. Maltodextrin is a partial hydrolysis product of starch and oligosaccharides and has become one of the most important and widely used carrier compounds in spray drying because of its high solubility and low viscosity. Because anthocyanins are soluble in water, they are compatible with formulations containing maltodextrin, gum arabic, and starch. The main goal of this research was to investigate the microencapsulation of sour tea extract using a spray drying method for the development of stable anthocyanin formulations because this method is scalable.

Sour tea was prepared from the gardens of Khuzestan province, Karun city, in 2023. To prepare the sour tea plant, the sepals were first washed with distilled water and dried in an oven for 15 h at a temperature of 40º C. The sepals were then powdered using a hand mill. After passing through a sieve with a mesh size of 150 micrometers, the prepared powder was extracted using 50% ethanol. The extract was passed through a paper filter and centrifuged in a refrigerated centrifuge (10 minutes, 3780 g). Extraction was performed from sour tea, and after the concentration stage, it was combined with gum arabic and maltodextrin as carriers. The carrier material including the binary solution of gum arabic and maltodextrin in a specific ratio dissolved in 1000 ml of warm distilled water (at a temperature of about 70 º C) and stirred overnight on a magnetic stirrer at 4º C were kept. The ratio of the extract to the wall material was varied (1, 2, and 3% by weight). In this study, the inlet air temperature, inlet air flow, and inlet feed temperature to the dryer were considered constant, and the inlet air was sent to the dryer at a constant temperature of 160º C. The feed and air flow rate were 70% (respectively equivalent to 3 L/min and 25 m3 /h), and the nozzle opening and closing time intervals were 3 and 1 s, respectively. In order to optimize the preparation of the powder, the response surface methodology (RMS) with a central composite design (CCD) was used to obtain a mathematical model to predict the process behavior. The effects of independent variables, including the amount of wall material (4, 7 and 10%) and sour tea extract (1, 2 and 3%), on dependent variables, such as total anthocyanin (TAC), surface anthocyanin (SAC), and encapsulation efficiency (EE), were investigated. Moisture content, solubility index, bulk density, tapped and particle density, flowability, porosity, and morphology were also investigated in the powder samples.

The obtained data were modeled using the Design Expert software11. The data analysis showed that the best model for estimating the surface anthocyanin and anthocyanin encapsulation rate was the third-order model with coefficients of explanation of 0.8853 and 9205. After final optimization, the SAC value was 0.49, TAC was 4.371 mg/liter, EE was 42.27%, moisture content was 3.92, solubility index was 45.47%, bulk density was 0.98, tapped density was 1.03, and particle density was 2.28 g/cm3. Hausner and carr index confirmed the excellent flowability of the powders. The optimal wall and core materials were 66.6% and 1.63%, respectively. Scanning electron microscopy images showed that the powder particles were micrometer in size and almost spherical. Powders containing a high percentage of gum Arabic showed relatively greater shrinkage and indentation than powders containing high maltodextrin content.

Machine learning algorithms usually do not consider spatial autocorrelation in soil data, unless it is perspicuity specified. Machine learning algorithms that compute autocorrelated observations have been recently formulated, such as geographic random forest (Georganos et al., 2019), or spatial ensemble techniques (Jiang et al., 2017). In theory, if we include all relevant environmental variables to model a soil property or class, there should be no spatial autocorrelation in the residuals of the fitted models. If this happens, some important predictors are likely to be missed. Despite the availability of the data set and the care taken during modeling, residual autocorrelation is still likely to occur. Several researchers have suggested the use of spatial alternative covariates as an indicator of spatial location in the SCORPAN model. The most common alternative is to use geographic coordinates (east and north) as covariates in the model, which leads to synthetic maps, especially when used in combination with tree-based algorithms. On the other hand, distance maps from observation locations are proposed by Hengl et al. (2018). Distance maps to observation locations usually do not have a clear meaning in terms of soil processes in an area (e.g., distance from a river). In the field of digital soil mapping, the current use of distance maps is not satisfactory for several reasons. The presence of pseudo-covariates with a set of covariates related to pedology is not very useful because it prevents the analysis of residuals and the creation of new hypotheses from these residuals. It also hinders the interpretation of the most important key predictors. Finally, pseudo-distance covariates may be well integrated into multiple pedology-related covariates, making them better predictors or masking the effect of pedology-related covariates. In spatial ecology, spatial eigen-vector maps, spatial filters or trend level regression replace distance maps in reducing or eliminating spatial autocorrelation (Kuhn et al., 2009). The purpose of this study is first to detect and calculate the spatial autocorrelation in the soil data. In the second step, it is going to develop a non-spatial model without considering the spatial autocorrelation, then to extract the spatial eigenvectors as an index of the spatial autocorrelation, and finally to use them as independent variables in spatial modeling.

Methods and Materials:

 In this study, the soil salinity data utilized of 297 soil samples from a section of the Qazvin plain. The first and second derivatives of a digital elevation model as topography factors, remote sensing indices, parent material map, geoform map, and annual average temperature and rainfall maps were used to select the most important auxiliary variables. Finally, in order to select the best and most relevant environmental variables for modeling, the correlation between these variables and the dependent variable i.e. soil salinity in 297 study points was used using FSelector package of R software. Moran's I and Jerry's C indices were used to evaluate the spatial autocorrelation of soil data. First, the non-spatial ordinary least square (OLS) model was fitted to predict the spatial distribution of soil salinity. At this stage, spatial autocorrelation was not considered. Then spatial regression was fitted by calculating spatial filters through spatial eigenvectors as independent variables. Finally, the comparison of the outputs of the non-spatial OLS model and the spatial regression model was done with criteria such as R2, Akaike information criteria (AIC), autocorrelation of residuals and root mean of square error (RMSE).

Statistical analysis indicated the high variability of soil salinity in the study area (coefficient of variation or CV more than 35%). Also, soil salinity shows high skewness and kurtosis, indicating its abnormal distribution. The high variability of this soil characteristic emphasizes the interaction of complex and numerous factors, including soil forming processes and different management strategies. The most important variables selected based on the correlation analysis include elevation, Multi-resolution Valley Bottom Flatness (MrVBF), wetness index, drainage basin, greenness index, normalized differential vegetation index (NDVI) and the corrected and transformed vegetation index (CTVI). A total of 7 variables were selected, which include four topography variables and three remote sensing variables. Among the topographical variables, the MrVBF had the most importance (correlation: 0.70). The spatial distribution map of soil salinity shows that the soil salinity is low in the northern, northeastern and northwestern parts towards the center of the studied area. The highest amount of salinity is found in the southern and southeastern regions. Moran's I and Jerry's C indices were 0.57 and 0.4, respectively. Based on both indices, soil salinity in the study area exhibits spatial autocorrelation. In the spatial regression model, by considering spatial autocorrelation, compared to the non-spatial model, the results are improved. By considering the spatial autocorrelation, the value of R2 increased, while the values of AIC, spatial autocorrelation of the residuals and RMSE decreased. The distribution maps of residuals from the non-spatial OLS model and the spatial regression model differ in terms of the spatial sign of the residuals and the spatial autocorrelation distribution that can be recognized in the form of clusters. Clusters (red or blue) indicate the presence of spatial autocorrelation in the residuals. In the distribution map of the residuals of the non-spatial model, more and larger clusters (marked with green ovals) are identified, indicating the existence of spatial autocorrelation in the residuals of the model. The presence of spatial autocorrelation in the residuals of a model shows that the model is not able to remove the spatial dependence, which may be due to not considering an important auxiliary variable in the modeling.

This study was conducted in order to investigate the effect of spatial autocorrelation on the results of soil salinity modeling. Soil salinity prediction was done by non-spatial OLS model (without considering spatial autocorrelation) and spatial regression model (with spatial autocorrelation considered). The results indicated the improvement of the performance of the spatial regression model compared to the non-spatial ordinary least squares model. In the spatial model, considering the spatial autocorrelation as a covariate, the value of R2 increased, while the values of AIC, spatial autocorrelation of the residuals, and RMSE decreased.

Rapid global industrial development has led to a significant increase in the risk of environmental contamination with heavy metals. Soil contamination with heavy metals is a challenge due to the risks associated with human health and the environment, as well as soil-related food security. It is considered universal. Soil moisture, as one of the influencing parameters on soil spectral reflectance and its high spatio-temporal variability, is considered the most important confounding factor in using Visible and Near Infrared Reflectance Spectroscopy (VNIRS) techniques to estimate soil heavy metals. . In this study, the ability of the external parameter orthogonal (EPO) algorithm to reduce the effect of moisture on soil spectral reflectance was evaluated to improve the performance of machine learning methods for heavy metal estimation.

In the present study, a modeling approach based on spectral information obtained from VNIRS technique is used to investigate the effect of soil moisture on the estimation of heavy metal concentration (nickel and lead). Soil samples were obtained from areas suspected of heavy metal contamination. For this purpose, 129 soil samples were collected from fields contaminated with heavy metals in Tehran, Gilan and East Azerbaijan provinces. Nickel and lead concentrations in air-dried and sieved soil samples were measured in the laboratory using the ISO 11466 method. Then the soil samples were coded and transferred to the dark room for spectroscopy. Spectral reflectance of soil samples at 7 moisture levels (air-dried, 6, 12, 18, 24, 30 and 36%) using a FieldSpec-3 spectrometer and a contact probe in the spectral range of 350-2500 nm in a room Darkness was measured. After applying the necessary pre-processing, the soft and de-noised spectra related to the soil samples were randomly separated into two sets of data sets for modeling and validation. EPO using a set of calibration samples was developed. To estimate heavy metals, machine learning algorithms including PLSR and SVR were used.

The results indicate that with the increase in soil moisture, the spectral reflectance in the entire range of 2450-400 nm decreases non-linearly. This means that the amount of reduction in different wavelengths is not the same. The greatest reduction occurs in the range of absorption peaks located in the range of wavelengths of 1600-1400 nm and 1850-2000 nm. VNIR spectroscopy has a high ability to estimate nickel and lead heavy metals in dry soil. The presence of moisture in the soil, even at the level of 6%, leads to a significant decrease in the ability of this technology to accurately estimate heavy metals in the soil. At humidity greater than 24%, both machine learning models evaluated for both heavy metals are in the medium class.

In a general conclusion, it can be stated that the use of EPO algorithm significantly improves the ability of machine learning methods in the estimation of heavy metals in soil in the presence of moisture in soil samples. In general, SVR algorithm has the best performance compared to PLSR methods for modeling soil heavy metals. On the other hand, VNIR reflectance spectrum information provides more capability in estimating nickel than lead.In this study, the ability of the EPO method was evaluated in order to minimize the effect of soil moisture disturbing parameters on the ability of VNIR spectroscopy to improve the accuracy of soil heavy metal concentration modeling including nickel and lead based on PLSR and SVR machine learning methods. The results indicate that with the increase in soil moisture, the spectral reflectance in the entire range of 2450-400 nm decreases non-linearly. This means that the amount of reduction in different wavelengths is not the same. The greatest decrease occurs in the range of absorption peaks located in the wavelength range of 1600-1400 nm and 1850-2000 nm. VNIR spectroscopy has a high ability to estimate nickel and lead heavy metals in dry soil. The presence of moisture in the soil, even at the level of 6%, leads to a significant decrease in the ability of this technology to accurately estimate heavy metals in the soil. At humidity greater than 24%, both machine learning models are evaluated for both heavy metals in the medium class. Using the EPO algorithm significantly improves the ability of machine learning methods to estimate heavy metals in soil in the presence of moisture in soil samples. In general, SVR algorithm has the best performance compared to PLSR methods for modeling soil heavy metals. On the other hand, the information of VNIR reflectance spectrum offers more capability in estimating nickel than lead.