فهرست مطالب mahmoud omid

Land suitability is a crucial factor in land use planning and sustainable agricultural production. Evaluating land suitability helps optimize land use, promote sustainable land use, protect the environment, and ensure optimal use of natural resources. This study was conducted in the Abiek region of Qazvin province in northwest Iran, covering an area of 60,000 hectares. After collecting data from 300 soil profiles and determining land suitability classes for wheat cultivation with surface irrigation using the FAO classification system, digital elevation models, Landsat-8 and Sentinel-2 satellite images, and environmental variables extracted from the digital elevation model were used to create digital maps using both traditional and machine learning methods. The results showed that the machine learning method had a higher accuracy rate of 74% and a Kappa index of 68 compared to the traditional method with an accuracy rate of 62% and a Kappa index of 53. The most important environmental variables used in the machine learning model were those extracted from the digital elevation model and Landsat-8 satellite images. The largest area for wheat cultivation with surface irrigation was found in the relatively suitable class (S2), with 30,753 hectares in the random forest method and 21,028 hectares in the traditional method. In contrast, the smallest area belongs to the unsuitable class (N), with 3,052 hectares in the forest method. Additionally, random fields and 7185 hectares were identified in the traditional method. Also, 15,000 hectares of the study area are suitable for wheat cultivation without restrictions.

Estimating the surface area of defects of diseased potatoes is a key factor in the automatic grading of this product. In this article, an algorithm has been developed using fuzzy clustering method and image processing functions to estimate the defective areas of potato tubers infected with black scab disease. Fuzzy clustering, which is an unsupervised method, was used to segment color images and extract defective areas of potatoes, and image processing functions have been used to extract the total area of potatoes. In the segmentation method based on fuzzy clustering, the data matrix related to potato images were divided into separate clusters in a fuzzy way, in which the boundaries of the clusters are defined in a fuzzy way instead of being definite and specific. The results showed that this algorithm is very efficient for extracting black scab disease and can be used to extract the amount of diseases that can be used for automatic grading of this product based on the American standards.

In some orchards in the harvest season, the pomegranates are suspected to carob moth infestation. Visible infested fruits are removed but there is a possibility of hidden infestation. The effect of microwave heating on this hidden infestation was investigated in this study.

 Research Method:

The mature pomegranate fruits were artificially infested with the eggs or larvae (1st, 2nd and 3rd) of the carob moth inside the crown. Microwave radiation was focused on the crown zone of infested pomegranate with a novel setup and its effect on pest mortality was studied. The experiments were carried out at three microwave powers (540, 720 and 900 W) and three heating times (4, 6 and 8 minutes). In order to study the effect of microwave heating treatments on pomegranate, quality parameters including appearance, weight loss, total soluble solids (TSS), pH, titratable acidity (TA) and taste index (TSS/TA) of the samples were investigated after 60 days’ storage.

The egg and larval mortality rose with microwave power and heating time. The mortality was reduced with increasing the age of pest. There were no significant differences among values of quality factors except for titratable acidity. Because of 100% mortality with no significant differences on quality parameters, 6 min treatment time with 720 microwave power was selected as the optimum treatment.

Research limitations:

 Energy consumption in microwave heating limits the application of this method in practice.

Originality/Value: 

Microwave local heating of the pomegranate crown is an effective novel method to remove carob moth in hidden infestation.

Investigation of soil organic carbon stock (SOCS) in agricultural lands and the role of factors affecting its variability and digital modeling are important for predicting possible scenarios of future carbon stock. The purpose of this study was to investigate the spatial variability and to estimate SOCS at 0 to 100 cm depth based on two generation of machine learning approaches in a part of Qazvin plain. SOCS of about 211 legacy soil data were prepared. The environmental variables including 11 geomorphometric variables and 25 spectral indices with 10-meter spatial resolution were used. Further, the dataset was divided into two parts: 70% of data were chosen as training and 30% of data for model validation. Two algorithm were used for SOCS modeling in the study area. Validation results indicated that the QRF had a higher coefficient of determination than the RF. According to the results of the relative importance of environmental variables, DEM and Valley depth parameters are more important in the spatial modeling of SOCS than other variables. Generally, it is suggested to investigate hybrid models in the process of modeling secondary soil characteristics.

Modeling and mapping of plants nutrient elements in soil has importance in increasing the productivity of agriculture and achieving sustainable development. The aim of this research was to prepare digital maps of two nutrients, namely, available phosphorus (Pav) and exchangeable potassium (Kex) using machine learning models (MLM) i.e., random forest (RF), cubist (CB), support vector regression (SVR) and k-nearest neighborhood (k-NN) at two depths of 15-30 and 0-15 cm in a part of Abyek Plain. In this regard, 278 soil profiles were dug, sampled from the desired horizons, and samples were analyzed. MLM performance was implemented by 10-fold cross-valuation. The modeling results demonstrated that the RF model had the highest accuracy and minimum error compared to the other three models in spatial estimation of available Pav and Kex at the two studied depths. According to the results, for Pav at a depth of 0-15 cm, CCC statistics values of 0.84, 0.74, 0.48 and 0.35 and NRMSE values of 0.38, 0.54, 0.70, and 0.80 belonged to RF, CB, k-NN, and SVR, respectively. For Kex at the same depth, CCC values were 0.82, 0.72, 0. 70, 0.47 and NRMSE 0.25, 0.34, 0.36 and 0.45, by RF, CB, SVR, and k-NN models, respectively. Similar results were obtained for 15-30 cm layer. The relative importance of environmental variables showed that soil covariates had a more effective role in the spatial estimation of Pav and Kex than other environmental variables. According to the estimated maps of the two elements and the predominance of agricultural land uses, major parts of the area are Pav deficient based on standard amounts. Therefore, to increase productivity and improve management of soil fertility, use of phosphate fertilizers is recommended under the supervision of soil experts.

“AppTree” is an intelligent platform to bring researchers, visitors, and all interested people closer to the oldest and most attractive botanical garden at the University of Tehran. AppTree can scan the QR-Barcode of each plant in person by smartphone or search various plants on the website and get all the useful knowledge about them. Also, the ability of AppTree is the recognition of different plants which don’t have labels. The plant recognition part is a machine learning module that can identify more than 100 different species of plants and give the user details about them. This novel platform is based on Android and Web-app and the identification of new plants type is done by machine learning approach. We utilized VGG19, a deep CNN, to classify images and to identify unlabeled plants. The classification accuracy, F1-score, recall, and precision were 98.25, 93.16%, 88.21%, and 94.85%, respectively, on the plant dataset of the University of Tehran. The proposed method was compared with other deep learning architectures such as AlexNet, AlexNetOWTBn, and GoogLeNet on the same dataset and obtained higher performance. Our AppTree platform has achieved considerable success and easily can be extended to use in other botanical gardens.

Soil salinity, as one of the most important indicators of soil quality, has crucial roles in land use planning and land management in arid and semi-arid regions. The aim of this study was to model soil salinity at five standard depth (0-5, 5-15, 15-30, 30-60, and 60-100 cm) of global digital soil mapping project in 60,000 hectares of Qazvin plain with spatial resolution of 15m. Field studies included a sampling of 278 soil profiles and then the EC was measured in the laboratory. The recursive feature elimination (RFE) method was employed to select environmental covariates including parameters extracted from Landsat 8 image (OLI/TIRS) data, topography, and climatic parameters. Four machine learning algorithms as random forest (RF), cubist (CB), decision tree regression (DTr), and k-nearest neighbors (k-NN) were applied for predicting and mapping soil salinity. According to RFE, 10 covariates were chosen for each standardized depth. The results of modeling showed that the CB model at the depth of 0-5 and 15-30 cm with R2 values of 0.92 and 0.85 and RMSE 4.77 and 7.90 dS/m and the RF model at depths of 5-15, 30-60, and 60-100 cm with R2 values of 0.93, 0.94, 0.96 and RMSE 6.65, 5.10 and 3.20 dS/m, respectively, had the highest accuracy compared to two other models i.e., DTr and k-NN. Furthermore, the covariates extracted from RS data had more impact on topsoil salinity prediction while the climate and topographic attributes influence subsurface soil salinity. Generally, The RF and CB models along with appropriate environmental covariates were able to present salinity variation of study standard depths.

Recreational use of the area must be performed conforms to its ecological capability. Therefore, this study was carried out with the aim of providing a method for modelling and ranking the areas with ecotourism capability. For this purpose, Makhdoum systemic method, regarding to the region specifications, and multi-layer perceptron artificial neural network (MLP) were used to evaluate the ecological capability of Arasbaran protected area. At first, ecological and socio-economic resources were identified and maps of them were provided. Then, ecotourism capability map was prepared by analyzing and overlaying of data in ArcGIS. In the next step, using the results of the systemic method, neural network was trained and its various structures were evaluated. Finally, map of the suitable tourism areas was modeled based on neural network output. In the end, using the socio-economic criteria and recreational attractions, prioritize and final evaluation was performed. Regarding to the systemic analysis, the area has the capability for intensive recreation class-2 (0.06%), and extensive recreation class-2 (10.33%). Topology 7-9-3 was selected as the best classifier with an overall accuracy of 98% for recreational regions classification. The best and the lowest of neural network application were shown to belong to intensive recreation class, and extensive recreation class, respectively. Based on modeled map, 0.17%, 10.09%, and 89.74% of the area were shown to belong to intensive recreation-class 2, extensive recreation-class 2, and unsuitable for recreation, respectively. This study showed artificial neural network has potential for classification of the suitable tourism areas with high accuracy.

Climate change studies and simulations conducted by GCM models show that patterns of temperature and rainfall will change over the next 50 to 100 years can affect patterns of forest stands increment. Growth and yield models do not have the ability to simulation forest stands under the effect of climate change. Due to lack of efficient models, JABOWA-4 as a hybrid model that can evaluate the population dynamic under climate change scenarios, and can explore the long-term aspects of forest composition, was applied in this study. In order to uncertainty of climate change trend in future, three greenhouse emission scenarios were formulated to explore future global developments with special emphasis on greenhouse gases. After comparison of modeled and real values of diameter growth, R2 and RMSE were calculated to be 0.98 and 1.734 (cm2), respectively, indicating a good correlation between two mentioned values. The response of species to climate change were assessed separately for Beech and Maple with 31 and 25 percent reduction in DBH increment, respectively, wich showed a negative response to climate change. Oak projected to increase slightly and after that decreased by17 percent under climate change and Hornbeam showed positive response to climate change but less than real values. The results of this study indicated that gap models are good at providing forest yield prediction affected by climate change.

The road network is an important element for sustainable forest ecosystem management. On the other hand, efficiency and quality of road design can be improved by considering of environmental and technical principles. Therefore, this study was performed to determine the capability of Arasbaran protected area for road passing and communication routes in order to use in the area management. For this purpose, criteria of the slope, aspect, height, soil texture, lithology, erosion susceptibility, vegetation density, distance to stream, and distance to existing road as the effective criteria for road design were identified by literature review, and their prepared maps were standardized with the fuzzy logic method. Then, the criteria were weighted using of analytical hierarchy process (AHP) and finally were combined to prepare suitability map for road planning by weighted linear combination (WLC) method. According to results, the highest weight (0.289) and the lowest weight (0.033) were belonged to slope and height criterion, respectively. Finally, the area was classified into four classes with the capability of low, medium, high and very high for road network passing, that region with medium passing capability has the highest percent (49.83%). The study proved GIS and AHP capabilities considering to economic and environmental problems for developing the road capability map in order to use for road locating in Arasbaran area.

The selection of cropping patterns is one of the main factors in increasing agricultural productivity. Optimal allocation of land and determination of suitable crop production in each region to prevent unwarranted consumption of inputs and reduce the disaster of lack of food supply after scientific study of factors affecting cropping pattern and taking into account different indices. Therefore, the present study determines the factors affecting the cropping pattern and their prioritization. This research was conducted in Silakhor agricultural area in Dorud Lorestan. The research method used in this study was a library, skillful interviews, and inspection (collecting questionnaires from farmers). The variables affecting the cropping pattern were extracted using exploratory factor analysis and then Shannon entropy-based TOPSIS method was used to prioritize crop cultivation. Factor analysis results indicated that the variables affecting sustainable crop pattern selection in the region can be classified into six factors, mechanization-farming, soil and climate, macro-government management, production support, social and production margin. These factors explained 61.41% of the variance of the effective variables in selecting the cropping pattern. Also, in the four-criterion entropy method, Access to cash capital of cultivation needed (0.236), Crop water requirement (0.233), crop profit (0.098), and cultivation area more than 1 ha (0.039). They had the highest priority in choosing the pattern of cultivation. Finally, the results of TOPSIS Multi-Criteria Decision Making showed that autumn sugar beet (0.598), Wheat (0.589), Barley (0.558), Canola (0.556), autumn peas (0.515). ), Rice (0.499), Quinoa (0.471), and saffron (0.390), respectively, have the highest priority for being included in the region's cultivation pattern.

It is necessary to use methods to monitor the pH of the rumen and maintain it between 5.5 and 7. In this research, a pH Nano-sensor based on EIS technique was developed and assessed in order to be used in wireless monitoring system of rumen pH. Single-Wall Carbone Nanotubes were functionalized with carboxylic groups (COOH), also with Amin groups (NHRNH2). Then interdigitated chrome-gold electrodes were coated by a drop of the solution obtained from dispersing with a known ratio of COOH-SWNT and Amin-SWNT in PECH/THF solution. Finally, the developed electrode was used as working electrode in EIS experiments over the laboratorial and real (rumen liquid) samples in the form of buffer solutions, adjusted at various pH values. Each experiment was done by applying AC voltages of 20 mV with frequencies ranging from 0.1Hz to 1MHz. Results showed that the developed electrode was pH sensitive and for real samples, impedance modulus, |Z|, linearly increased with pH (Freq.=0.4kHz, R2 =0.99).

The aim of the study was to provide an intelligent artificial neural networks-based method for modeling the capability of Arasbaran protected area for road crossing, in order to design, modify, and appropriate development of existing road network and communication routs in the region. First, using Analytical Hierarchy Process (AHP) and Weighted Linear Combination (WLC) method, and utilization the effective informative layers on routing, the suitability map of road construction was prepared to provide training samples in ArcGIS. In the following, Multilayer Perceptron (MLP) network was used to estimate the suitability value of road crossing. In order to evaluate the neural network’s model performance, the results were compared with the results of multivariate linear regression. According to the results, artificial neural network and statistical method of regression were shown to be useful in determining the suitability value of road crossing with coefficient of determination (R2) 0.908 and 0.901, root mean squared error (RMSE) 0.0385 and 0.04, respectively. Neural network results were relatively better than regression. Also, according to the results of sensitivity analysis of input variables, four criteria of slope, bedrock, erosion susceptibility, and soil texture showed the highest influence in estimating the model, respectively.

The aim of this study is to determine the growth pattern and to investigate the vegetation indices power for sugarcane yield modelling at field scale in Imam Khomeini Agro-industry. For this purpose, the vegetation indices extracted from Landsat7 satellite images were investigated using time series analysis. Overall, 306 Landsat7 satellite images from March 2004 to February 2017 were used. All of the images were converted to surface reflectance via FLAASH algorithm. The average values of 13 vegetation indices related to the study region extracted from satellite images and converted to seven days' time-series via interpolation. In order to eliminate the noise, all series were reconstructed using the Savitzky-Golay algorithm. Thus, 13 different time series of vegetation indices were made for 523 sugarcane fields. Then the growth pattern was drawn via averaging NDVI time series and it was divided into three growth periods. Then the accumulative values of vegetation indices related to the first and second periods of growth stage were extracted since 2004 to 2017. Therefore, 3286 samples were prepared overall, of which 2628 samples were used for modelling and 658 samples for evaluation. The samples extracted from time series were evaluated by simple linear regression model against the average observed yields. The result showed that the accumulative vegetation index of GNDVI for the first growth period with R2=0.47, RMSE=11.70 ton/ha and the accumulative vegetation index of NDI for the second growth period with R2=0.56, RMSE=10.62 ton/ha are a better indeces for sugarcane yield estimation as compared to the other vegetation indices. Also, the sum of GNDVI and NDI indeces for summation of first and second growth periods had a better result (R2=0.65, RMSE=9.47 ton/ha) than that's where one index at one period was used. Finally, the sugarcane yield of 658 samples was estimated for evaluation and the R2 and RMSE of the best model was obtained to be 0.58 and 10.99 ton/ha, respectively. The results of this study confirm the suitability of the GNDVI and NDI indeces for monitoring sugarcane growth during the first and second growth stages.

Rough rice is one of the most important agricultural products and it plays an important role in ensuring food security. The objective of this study was to investigate the effect of high power ultrasound in tempering duration on the drying kinetics of rough rice in a combined far-infrared radiation (FIR) dryer. Tests were conducted in a factorial design at four levels of ultrasound power density (Zero, 0.5, 0.75 and 1 kW/kg), four levels of frequency (20, 25, 28, and 30kHz) and three levels of drying air temperature (30, 40, and 50oC). Results showed that mechanical characteristics of rough rice were affected significantly at all ultrasound power and frequency levels at different inlet air temperatures at tempering duration and led to reduction of both drying time and specific energy consumption. So that at power of 0.5 kW / kg, low ultrasonic frequencies of 20 and 25 kHz and input temperature of 30 ° C while reducing the percentage of cracks in rough rice kernels, they also increase the energy required for healthy seed breakage on average.

Nowadays, one of the main challenges in the maritime is the control and monitoring of ports in different weather conditions. To achieve this, Autonomous Surface Vehicles (ASV) are used. In this research, as part of the Morvarid research project, a stereo vision system was implemented on an ASV to detect, localize, and track static and dynamic objects. In order to examine the proposed obstacle detection algorithm, two sets of experiments have been designed; first, the ASV moves toward stationary objects to localize all static and dynamic objects. Second, the ASV tracks a target boat, which equipped with an RTK-GPS and estimates relative and absolute positions and movement vector. The results showed that the proposed algorithm successfully estimated 3D size and position of the surrounding objects. The accuracy of the tracking algorithm was evaluated in the digital elevation map, with the lowest RMSE of 1.575 (m), and 0.6621 (m) using raw and EKF data, respectively.

Prediction of sugarcane yield is very important for a wide range of applications like, sugarcane production management, preparation of sugarcane refineries and pre-sales and warehouse industrial products. In this study, a model based on time-series processing of vegetation indices, Normalized Difference Vegetation Index (NDVI), Green Normalized Differnce Vegetation Index (GNDVI) and Enhanced Vegetation Index (EVI) extracted from satellite images, were used to estimate sugarcane yield. Overall 474 Landsat 7 satellite images from January 2001 to December 2017 obtained from USGS (U.S. Geological Survey) were processed. At first the DN (Digital Number) of pixels were converted to TOA (Top of Atmosphere) reflectance and then the distorted pixels due to not clear sky such as cloud, shadow, snow and ice were eliminated. Consequently, the average of the vegetation indices values of study region for every images were computed. Then the weekly time-series of vegetation indices were calculated via interpolation. The accumulated vegetation indices values from 15th to 44 th week of year and average observed yields efficiency were evaluated by regression model. The result showed the NDVI and GNDVI vegetation indices with R2=0.63, RMSE=4.71 ton/ha and R2=0.60, RMSE 4.93 ton/ha, respectively, have good relations with sugarcane stem yield efficiency. The 2017 sugarcane yield of MianAB Sugarcane Agro-Industry Company efficiency was predicted as 86.35 ton/ha using the NDVI model which was 4.16 ton/ha less than observed value.

Among all kinds of renewable energies, the solar energy has the greatest application compared to the other types. However, the biggest shortage of solar collectors is their low effectiveness at night or in the cloudy weather. The latent heat storage of phase change materials (PCMs) can be utilized as a solution for the above-mentioned problem. However most PCMs have low thermal conductivities. In this research aluminum oxide (Al2O3) and copper (Cu) nanoparticles were used to enhance the thermal properties of Paraffin wax as a PCM. The morphology of the nanocomposites was studied by Field Emission Scanning Electron Microscopy. The experiments were performed in a factorial arrangement in a completely randomized design with three main factors including weight percentage (three levels), type (two levels), and size of the nanoparticles (three levels) and pure Paraffin wax used as a control sample. Thermal conductivity of nanocomposites was measured at a temperature range for each sample and in the solid phase. The highest and lowest values of thermal conductivity coefficients compared to control sample have increased 442% and 122%, respectively. Analysis of variance results showed that the size, type and concentration of nanoparticles affected thermal conductivity of nanocomposites significantly (p<0.01). In different size of nanoparticles, thermal conductivity coefficient of nanocomposites has increased with increasing of the nanoparticle concentration. Also, the highest thermal conductivity coefficient of nanocomposites was obtained at the smallest size of the nanoparticles. The highest thermal conductivity coefficients of nanocomposites were achieved by addition of Cu nanoparticles at the weight percentage of 6% and sizes of 30 and 70 nm to Paraffin wax.

Managing the production of greenhouse products requires knowledge of controlling many environmental factors and plant nutrition and fight against pests and plant diseases. Recognition pests and fight against them is one of the most important activities in the process of production of greenhouse products. Pre-knowledge of the demographic density of insect pests is one of the effective methods of pesticides and reduce their levels of use, especially for insect pest control toxins. Wireless Sensor Networking Technologies (WSN) is one of the new technologies used to sense the environment and collect and transmit information to the user or the central station to view and respond appropriately to an occurrence or phenomenon. In this study, the use of WSN in monitoring, timely diagnosis of greenhouse white flies, design and mapping of greenhouse contamination was investigated. For this goal, 3750 images of 15 sticky traps with white flies that attached to Melon greenhouse in Isfahan Agricultural Jihad Research Center were provide and transmitted online using a WSN to a computer located at a distance of 900 meters from the greenhouse. The color images of the sticky traps are acquired by using 15 digital cameras were converted to gray colored images using MATLAB software, then after image classification with Support Vector Machine (SVM) classifier based on their features, are divided into two categories of images: whiteflies affected image and whiteflies unaffected image. After identification of the white flies, number of pests was counted and infection maps of Greenhouse with ArcMap10.2 software was drawn up. Assessment of the system showed that accuracy of SVM algorithm for categorizing images of sticky traps was 97.73%, and the average values of statistic parameters of the Confusion matrix for 15 traps including sensitivity, accuracy, specificity and classification accuracy were 98.46%, 83.31%, 99.08% and 97.72% respectively. The overall accuracy of the system for detection and counting Greenhouse whitefly pests is 97.71%. The average root mean square error (RMSE) in estimating of the number of white flight by image processing and direct counting was between 1 and 5.03. Therefore, the system is suitable for detecting and tracing and counting the number of trapped white flies, and it is possible to design appropriate greenhouse poisoning plans to fight this pest.

It is essential to have integrated information on the energy exchange of forage crops in order to allow comparisons of their energy consumption patterns. Thus the aims of this study are examination of the energy consumption pattern, estimation of the amount of produced CO2eq. and modeling between the yield and energy inputs in three forage crops. These forage crops that are fed to dairy cows were wheat straw, maize silage and alfalfa. The total amount of energy inputs in fields of wheat (and its straw), silage corn and alfalfa were calculated as: 32077.85, 93049.87 and 30208.04 MJ ha-1 respectively. The amount of produced CO2eq. in these three crops were estimated to be 2704.67, 5861.79 and 5538 respectively. The value of energy ratio in two crops of wheat and alfalfa were computed as 2.69 and 2.18 while in the silage crop due to higher amount of output energy rather than input energy was calculated less than one. Also, the adaptive neuro-fuzzy inference system was used for modeling the relation of the yield of these forage crops and the amount of energy inputs. For estimation of the model for wheat straw, the model with three 'gaussmf' memberships function for each input variables was the best among the other models. Also, the best model for maize silage and alfalfa were 'pimf' for tow memberships function and 'trapmf' for three memberships function, respectively.

Access routes are the basic requirements to access recreational areas and tourism planning. The purpose of this study is designing and evaluating of forest road network in order to select the optimal road network for tourism development in Arasbaran protected area. For this purpose, recreational suitable areas were evaluated and identified using Makhdoum systemic methods and Multilayer perceptron (MLP) neural network. In order to prepare the road passing suitability map, effective criteria for road designing have been standardized with the fuzzy logic method and combined according to the relative importance obtained from the analytical hierarchy process. Then, the road network options were designed for access to recreational areas in the GIS environment and evaluated in terms of technical, environmental and socioeconomic. The results of the tourism suitable area assessment showed sections of the region have a capability for intensive recreation class 2 (0.17%), and extensive recreation class 2 (10.09%). According to the weighting results by criteria, slope criterion with a value 0.289 and height criterion with a value 0.033 have the highest and the lowest weight, respectively. Overall, 14 road network variants were designed and based on the final evaluation, variant 7 was selected as the optimal option with density 3.34 m/ha, accessibility (hard) 64.68% and minimum cost and environmental impacts. Therefore, taking into account the cost and environmental impacts and using GIS capabilities, it is possible principle design of the road network, and as a result the development of existing access roads in order to develop tourism in the area.

Growth of industrial activities and increasing emissions are giving greater attention to environmental problems in the world. Unpleasant (malodorous) smells can be classified as pollutants that have a negative impact on the quality of life. About one-third to half of animal products unusable for humans are used as raw materials in the processing and recycling industry. One of the most important features of slaughterhouse rendering plants is the release of volatile compounds and unpleasant odours, which disturb workers and people living adjacent of this industry. The purpose of this study was to evaluate an electronic nose system as a tool for displaying vapours from a slaughterhouse rendering plant, selecting an array of appropriate sensors and determining the fingerprint for this pollutant unit. Material and methods: Batch cooking was carried out at a temperature of 140 ° C under 3 bar pressure for four hours and uniformly stirred at a speed of 20 rpm (ISIRI 2389, 1995). A total of 30 liquid samples, each one with volume of 10 ml, were obtained from condensed vapours of batch cooker. Samples were transferred to the laboratory located at the Agricultural Machinery Department of the University of Tehran, and an electronic nose system was used for analysis and investigation. The electronic nose system was based on metal oxide semiconductor (MOS) sensors and included an array of six gas sensors. The principal component analysis (PCA) method was used to evaluate the sensors and select appropriate array of sensors. Observation of the sensor’s response up until steady state with the aim of reducing consumption of time and oxygen, showed that 30 seconds to reach sensors to their baseline (baseline time), 100 seconds to contact the vapours with sensors (injection and response time) and 40 seconds to clear the sensors (purging time) were suitable. Correlation analysis of the sensors showed that some of the sensors had a correlation higher than 0. 85. The analysis of variance distribution of the two primary principal components showed that these two components comprised more than 99% of the total variance, and the primary component (PC-1) comprised over 98% of the total variance. The highest effect on the first component was related to the MQ135 sensor, after that the MQ136, MQ9, MQ131, MQ5 and, finally, MQ3 sensors were effective. The analysis of the principal components showed that MQ135 and MQ136 sensors, having a high sensitivity to ammonia, hydrogen sulphide and benzene, were the most suitable sensors for detecting the unpleasant smell released from the poultry slaughterhouse waste batch cooking (rendering plant). Selection of the MQ135 and MQ136 sensors as an array can be used to distinguish between pollutants from poultry rendering plants and pollutants released from other industries, and these sensors can be used to determine the fingerprint of the odour emitted from poultry rendering plants. According to the results of this research, the electronic nose system with arrays of MQ135 and MQ136 can be used to monitor and control the quality of pollutants from poultry rendering plants. Also, with referring to this fact that unpleasant odours as part of air quality control have no standard definition in Iran, an electronic nose system could be used to control the air quality in terms of the presence of unpleasant odours in the environment.

Decision-making in natural resources often leads to complexities beyond the statistical empirical methods,therefore we need new solutions than algorithmic methods. Artificial neural networks (ANN) technology mimics the human brain in the process of problem solving.The aim ofthis studywas to predict the commercial volume and cordwood volume using this technique (Artificial Neural Network). For this purpose, 367 marked trees in the experimental and educational forest of Kheyrood were selected. Some factors including diameter at breast height, diameter at stump, stump height, total height, topographic factors (slope, aspect and elevation), species, tree situation and minimum median diameter of last log were measured. The factors were considered as input network. Multi-layer Perceptron network (MLP) was used for modeling. The result showed that Multi-layer Perceptron network (with the 0/94 and 0/71 R2, and 0/233 RMSE) has acceptable accuracy to predict the commercial and cordwood volume.

Solid waste management in addition to its role on the economic cycle, is considered as one of the most important indicators of development in developing countries. Recycling is one of the sustainable solutions in solid waste management. However, recycling has environmental and economic benefits, unfortunately, no coherent and integrated work has been done in our country. Finding the best location for waste recycling is very important for the proper implementation of operations. The aim of this study is to provide a framework for decision making techniques of Delphi, Delphi fuzzy and Analytic Hierarchy Process (AHP) using geographic information systems (GIS), to identify potential sites for establishing waste recycling station in Karaj, Iran. Thus, after identifying criteria using classical Delphi technique, the standard boundaries of each criterion was calculated using fuzzy Delphi technique. This study led to identification of 13 effective criteria in locating recycling station and also determining the allowable boundaries. Seven areas were identified as prone recycling stations using GIS and AHP. Finally, three of the seven regions having the highest scores were selected as the optimal locations of recycling stations.

In this study, an intelligent diagnosis systems have been developed and applied for classifying six types of cooling radiator conditions by means of infrared thermal images; namely, radiator tube blockage, radiator fin blockage, loose connections between fins and tubes, radiator door failure, coolant leakage and normal. The proposed system is consisted of several subsequent procedures including thermal image acquisition, preprocessing, of images via two dimensional discrete wavelet transform (2D-DWT), feature extraction, feature selection, and classification. The 2D-DWT was implemented to decompose the thermal images. Subsequently, statistical texture features were extracted from the original and decomposed thermal images. Consequently, statistical texture features are extracted from the original and decomposed thermal images to develop ANFIS classifiers. In this paper, the significant and relevant features are selected based on genetic algorithm (GA) in order to enhance the performance of ANFIS classifier. For evaluating ANFIS classifier performance, the values of the confusion matrix, such as specificity, sensitivity, precision and accuracy were computed. The overall accuracy of the classifier was 94.11 %. The results demonstrated that this system can be employed satisfactorily as an intelligent condition monitoring and fault diagnosis for a class of cooling radiator.