Precision Agriculture
Adel Taherihajivand; kimia shirini; sina samadi Gharehveran
Abstract
Introduction In many countries, on average, more than 50% of people's food comes from grains, and nearly 70% of the cultivated area of one billion hectares of the world is dedicated to grains. A variety of weeds grow along with cereals in the fields, which can reduce crop yield due to competition for ...
Read More
Introduction In many countries, on average, more than 50% of people's food comes from grains, and nearly 70% of the cultivated area of one billion hectares of the world is dedicated to grains. A variety of weeds grow along with cereals in the fields, which can reduce crop yield due to competition for light, water and nutrients. To eliminate weeds accurately and with minimal problems, timely detection with high accuracy and speed is required. be done. In the field of agriculture, it is controlling and eliminating weeds in grain fields. Weeds are one of the most important factors affecting the production of agricultural products, which are their most important competitors in conventional agriculture, they spray the entire field to eliminate weeds, while weeds appear scattered and patchy in the field. which shows the necessity of using precise agriculture to solve this type of heterogeneity. In addition to causing economic damage, the conventional method of fighting can cause pollution of the environment and even the human food chain. Research shows that the losses caused by pests, diseases and weeds can reach 40% of the global crop every year and it is predicted that this percentage will increase significantly in the coming years. Besides, according to the research of Goktoan et al., the annual cost of weeds for The Australian economy is estimated to be around $4 billion as a loss in agricultural income.Materials and Methods Among the new methods in this field is the use of machine vision technology and related methods such as deep learning object detection algorithms and convolutional neural networks (CNN). The steps related to the implementation of the project include preparing data for training and evaluating networks, using new object detection algorithms, using different convolutional neural networks with different characteristics to extract image features in algorithms, and using the Feature Pyramid Network (FPN) method in object detection algorithms. Was. The output of the networks was evaluated in terms of the number of detections, the exact location of detection and the time of detection in the field. ViTs is based on the Transformer architecture that was originally developed for NLP tasks. Transformers use self-awareness mechanisms that allow the model to capture complex relationships between elements in a sequence. In the case of ViTs, sequence elements are image patches. In using the transformer architecture for visual data, it is dividing the image into small and non-interfering parts. Each patch typically consists of a grid of pixels. These patches are considered the "words" of the image sequence. Spatial embeddings are added to image patches to provide spatial information to the model. Spatial embeddings are necessary because transformers do not have built-in notions of order or spatial relationships. ViTs use multi-series self-awareness mechanisms to capture relationships between different image patches, and the representation of each patch is updated by attention to other patches. Data separation is very important in data watch transformers for two reasons a) the model needs data to learn and b) we need data to measure the model because the model may not be able to extract the information correctly.Results and Discussion The best network in terms of positioning accuracy was the transform model (ViTs) with an average accuracy of 0.95. In addition to this, the network considered in this research managed to recognize 503 of the 535 target weeds, and this means that our network is able to recognize 95% of these weeds. The presented method has been able to reach the highest accuracy compared to other existing methods and has been able to detect existing grasses in a much shorter period of time. Compared to other methods, the reset50 algorithm has been able to detect more than 88%, although its execution time is about 2.5 times that of the proposed method.In comparing the efficiency of algorithms, execution time is as important as accuracy. By making comparisons and considering 70% of the data as training data and 30% as test data, the presented algorithm has been able to detect the weeds in the field with an accuracy of over 90% in just 13 seconds.Conclusion: Today, deep learning methods are much more efficient than other methods, so we can use the new methods available in deep learning in the field of agriculture.Keywords: Optimization, accuracy, agriculture, weed, deep learningAll right reserved.
Agricultural mechanization
Majid Namdari; Shahin Rafiee; Soleiman Hosseinpour
Abstract
Introduction Considering the essential role of the agricultural sector in Iran's economy, it is very important to investigate and identify optimal production methods from an economic point of view. The purpose of this study is to calculate the economic indicators of sugar beet production, use of the ...
Read More
Introduction Considering the essential role of the agricultural sector in Iran's economy, it is very important to investigate and identify optimal production methods from an economic point of view. The purpose of this study is to calculate the economic indicators of sugar beet production, use of the Data Envelopment Analysis (DEA) method to identify the efficient units, and use of the Adaptive Neuro-Fuzzy Inference System (ANFIS) method to predict the benefit-cost index based on the consumption of production inputs in Hamedan province.Materials and Methods In this study, 88 farmers were studied. Data were collected from Hamadan province, Iran. Inputs included labor, machinery, diesel fuel, electricity, seeds, chemicals, farmyard manure, chemical fertilizers, and irrigation water. The indices of gross revenue, net income, gross income, economical productivity and benefit-cost ratio were calculated using information obtained from farmers. Then technical, pure technical, scale and cross efficiencies were calculated using CCR and BCC models for farmers. The benefit-to-cost ratio was considered as the economic index criterion in modeling with ANFIS. In this modeling, value of various inputs used for sugar beet production were selected as input variables. Various membership functions such as Triangular, Trapezoidal, Gaussian, Logarithmic and Gbell functions were tested. Also, different configurations were examined to provide the best configuration that predicts the model. In order to measure the accuracy of ANFIS models for estimating the observed values some quality parameters including the coefficient of determination (R2), root mean square error (RMSE) the mean relative error (RME) between the observed and the predicted values were applied to evaluate the performance of different models with different configurations.Results and Discussion The results showed that most of the production costs were in the category of variable costs. Variable costs account for 84% and fixed costs account for 16% of the total costs of sugar beet production. Cost of labor, water consumption, and land rent have the largest share of costs among all fixed and variable costs. The indexes of gross income, net income and benefit-cost ratio were obtained as 1188.99 $ha-1, 694.28 $ha-1 and 1.34, respectively. The results of data envelopment analysis showed that from the total of 88 farmers, considered for the analysis, 19 and 55 farmers were found to be technically and pure technically efficient, respectively. In other words, the farmers who are identified with the BCC model are more efficient than the farmers who are identified with the CCR model. Average technical efficiency, net technical efficiency, and scale efficiency were calculated as 0.73, 0.94 and 0.77, respectively.Data envelopment analysis indicates that farmers should focus on increasing the degree of mechanization of production by reducing the cost of human labor. The saving percentage of total input costs in the CCR model is higher than the BCC model. Optimization of input consumption in sugar beet production decreased the cost by 51.64% in the CCR model and by 28.27% in the BBC model. To predict the economic performance using inputs in sugar beet production, the three-layer arrangement with seven parameters obtained the best results. The modeled ANFIS is able to predict economic performance values with R2 of 0.96. This prediction is acceptable due to its high coefficient of determination and can be used in modeling.Conclusion Considering the high share of variable costs compared to fixed costs, it can be concluded that by applying appropriate management methods, the total costs of sugar beet production in Hamadan province can be significantly reduced. By mechanizing farms, the variable costs of farms can be reduced significantly. If the cultivated land does not have a problem with weeds, the use of conventional seeds can also reduce production costs. The DEA results showed that based on the CCR model, about 78.4% of farmers produce outside the efficiency and by providing management solutions taken from efficient DMUs (the recommendations of this study), they can reduce consumption costs by keeping product yield constant. The results of multi-level ANFIS implementation showed that the three-level ANFIS structure including four ANFIS models in the first level, two ANFIS models in the second level and a final model in the third level have the best performance for benefit-cost ratio prediction. It is proposed that implementation of multi-level ANFIS is a useful tool in helping to predict the economic indices of agricultural production systems.
Shamim Shirjandi; A Khademalrasoul; Adel Moradi Sabzkuhi; Hadi Amerikhah
Abstract
IntroductionSoil degradation is a phenomenon which destructs the soil structure and mitigates its capacity for production. Among several processes that cause soil degradation, soil erosion as one of the most common forms of soil degradation leads to loss of soil surface and including on-site and off-site ...
Read More
IntroductionSoil degradation is a phenomenon which destructs the soil structure and mitigates its capacity for production. Among several processes that cause soil degradation, soil erosion as one of the most common forms of soil degradation leads to loss of soil surface and including on-site and off-site effects. Although soil erosion is a natural process on the earth, but destructive human activities such as burning agriculture residue, deforestation, overgrazing, and lack of proper soil conservation practices; accelerate the soil erosion and enhance the negative outcomes of erosion. Selecting and implementing of management scenarios requires assessment of soil losses from different management operations. Generally, management practices consist of structural and non-structural methods that used to reduce erosion, prevent nutrient removal, and increase soil infiltration capacity. Application of simulation models is an appropriate technique to evaluate erosional conditions. GeoWEPP is a process-based, distributed parameters and continuous simulation model of water erosion in watersheds with the possibility to simulate hillslopes and hydrographical network. Locating problems in real world usually face with a large amount of information and decision space that need to be optimized using evolutionary algorithms due to the variety of aims considered. Considering diversity of evolutionary algorithms, NSGA-II is one of the most common and a usable multiobjective evolutionary algorithm (MOEA) which is very powerful tool for solving problems with conflicting objectives. Development of simulation models along with optimization algorithms that are capable of analyzing very complex systems, have found to be very efficient in real world problems. Simulation-optimization models are powerful tools for solving problems for least cost and best performance.Methods and materialsTo predict sediment yield and runoff in the studied watershed, the GeoWEPP integrates WEPP model with TOPAZ (Topography Parameterization), CLIGEN (Climate Generation) and GIS tool (ArcGIS). The GeoWEPP model provides the processing of digital data including DEM ASCII file, soil ASCII file and landcover ASCII file. To generate climate file, the CLIGEN module which is a stochastic weather generation model was utilized. Furthermore in TOPAZ part the CSA (critical source area) and MSCL (minimum source channel length) to delineate streams and also the outlet point of studied watershed were defined using GeoWEPP linked to ArcGIS. Using the basic maps including DEM, slope, soil great groups and soil database the GeoWEPP model simulates and generates the hillslopes automatically; therefore this is an important advantage of GeoWEPP compared to WEPP model which is capable of performing the simulation of watershed components spontaneously. In this study in order to optimize the placement of Gabions, 118 channels and 5110 candidate sites for gabion construction were simulated and evaluated. For optimization process; regarding the number of objectives firstly the AHP technique was used to prioritize the effective factors on the placement of Gabions. Analytical hierarchy process is a structured technique for organizing and analyzing complicated decisions based on mathematical calculations. The AHP depicts the accurate approach for quantifying the weights of criteria and estimates the relative magnitudes of factors through pair-wise comparisons. The AHP technique includes creating hierarchical structure, prioritizing and calculating relative weights of the criteria, calculating the final weights and system results compatibility. The main criteria (objectives) for our study were minimum distance from road, minimum distance from residential area, maximum length of main channel, maximum sediment yield, maximum discharge volume and maximum volume structure. Indeed using the AHP technique it was possible to restrict the decision making space and the number of possible options, therefore simplify the optimization process. Then NSGA-II (Non-dominated Sorting Genetic Algorithm) was applied in order to find the best solutions, i.e. the Pareto front, of alternatives for optimal location of structures based on the two objectives with higher priority and distance constraint. Results and discussionThe results of paired comparison matrix and prioritizing showed that the length of main channel in the watershed is the main effective criterion in locating Gabion structures. The first priority is considered as the most critical channel which produces the highest sediment yield; therefore the most expensive structure is established on that channel. After channel length, the volume discharge was the second priority of effective factors for gabion placement. Using the results of AHP, based on channel length and discharge volume the non-dominated sorting genetic algorithm (NSGA-II) was performed and the priority of critical channels and the specific position was determined from 1 to 35 among 5110 candidate sites for Gabion construction. Using the ArcGIS, slope map and the lowest width of the critical channels the place for gabion construction as a point was determined. Moreover the main output of GeoWEPP is the spatial distribution of sediment yield and based on this map the sediment yield was classified in the watershed. Based on this map the red color was the highest amount of sediment yield (more than 4 ton) in the watershed. ConclusionResults confirmed that application of simulation-optimization techniques helps to select the best sites to construct the Gabion as structural best management practice therefore is a cost-effective technique.
N Norouzi; shaban ghavami jolandan; M. J Sheikh Davoodi; S.M. Safieddin Ardabili
Abstract
IntroductionToday, with advances in all sciences, we must always look for a way to make the best use of plant residues and turn them into valuable products. A consequence of improving family life standards and consistent industrial development is a higher demand for energy usage. Nowadays, agricultural ...
Read More
IntroductionToday, with advances in all sciences, we must always look for a way to make the best use of plant residues and turn them into valuable products. A consequence of improving family life standards and consistent industrial development is a higher demand for energy usage. Nowadays, agricultural residues are produced in huge quantities and could be considered as a promising source for renewable energy generation. Bagasse is one of the major sources of sugarcane production. The production of valuable products from Bagas, in addition to having economic benefits, can reduce the environmental damage caused by burning them. In recent years, there has been an increasing trend in the utilization of sugarcane bagasse as a major by-product of the sugarcane industry. Another very valuable substance produced from sugarcane bagasse, which we will discuss in this study, is bio compressed coal. Valorization of sugarcane bagasse to engineered biochar using hydrothermal carbonization (HTC) presents a perspective source to substitute conventional fossil fuels. HTC process offers the benefits of converting the sugarcane bagasse into biochar and bio-oil. In this process, biomass is usually conducted in the temperature range of 180–250 ◦C. HTC technique is promoted as one way of reducing carbon dioxide (CO) emissions, which mostly generated through open burning of crop residues. Besides the utilization for power/heat generation for sugarcane industries, Bagasse may find other potential applications, for instance: electricity generation, biogas production, livestock feed/compost production, and also bioethanol production. The unique features of biochar generated through HTC process are its portability, high volumetric energy density, hydrophobicity, and wear ability. Materials and MethodsIn this research, sugarcane waste was obtained from Hakim Farabi Sugarcane Cultivation and Industry Company in Ahvaz. The hydrothermal carbonization process was performed in a batch reactor at Shahid Chamran University of Ahvaz. The parameters studied in this study include the retention time of the material inside the reactor (30, 75, and 120 minutes), bagasse mass to water ratio (0.15, 0.20, and 0.30) and the pressure inside the reactor (10, 12.5 And 15 bar). In order to measure the pressure, a Nuova FiMa barometer was used, which was able to measure the pressure values up to 25 bar. A temperature control system model HANYoung ED6 was used, which was equipped with a ceramic heater with a diameter of 230 mm and a height of 230 mm to provide heat for the process. The PARR1266 calorie bomb device was employed to measure the calorific value of the samples. The moisture content of the samples was also measured using ASTM-2010a standard. In this experimental work, the response surface method was employed to investigate the effect of input parameters (i.e., pressure, residence time, and water-to-biomass) on the response parameter (i.e., HHV and energy consumption). Design Expert ver.10 software was used to predict the corresponding models. The obtained models provided a good relationship between the independent/dependent parameters. Results and DiscussionThe HTC process has been analyzed using a Response Surface Method to derive predicted models for the HHV and energy parameters. The results obtained showed that all models provided could successfully predict the HTC process. According to the results, the models developed were statistically significant at the level of 1%. The multi-regression models between the input/response variables were obtained as second-order quadratic equations. The F-value for the residence time, and water-to- bagasse, and pressure were 2417, 286, and 1185, respectively. The value of F-value of each derived model indicates the significance of the studied parameters. The parameters of water-to-bagasse and pressure had a more significant effect compared to the residence time factor. The R-square value for this study was achieved as 0.0996, indicating that the proposed model was able to evaluate the experimental data thoroughly. A multi-objective optimization technique was used to achieve an optimal HTC process condition with the maximum possible amount of desirability value. ConclusionThe optimum amount of water-to-bagasse, pressure, and residence time was calculated using the response surface techniques. A pressure of 11 bar, the residence time of 38 min, and water-to-bagasse of 0.15 were found to be optimal values. The findings of this study indicate that at optimal input variables, the value of calorific value and used energy was 21 Mj/kg and 0.09 kWh, respectively. Keywords: Hydrothermal carbonization, Sugarcane bagasse, Response surface method, Optimization
L Naderloo; R alimardani; M Omid; F Sarmadian; H Javadikia; M. Y Torabi
Abstract
Introduction: Social, technical and economic factors in addition to environmental, soil and climate factors affect crop yield and cultivation. This study was implemented to know the impact of age, experience and literacy level of farmers as social factors and access to water supply, roads, silo, labor, ...
Read More
Introduction: Social, technical and economic factors in addition to environmental, soil and climate factors affect crop yield and cultivation. This study was implemented to know the impact of age, experience and literacy level of farmers as social factors and access to water supply, roads, silo, labor, tractors and machinery and conservation tillage as technical-mechanization factors on crop yield. Fuzzy rule-based inference system converts the complex decision-making problems to the smaller criteria and makes easier the multi-criteria evaluation process. So we decided to use fuzzy approach to modeling the social and technical-mechanization indices. The main disadvantage of fuzzy systems is their inability to learn. So, the optimization of fuzzy systems is the most important step in its implementation. Genetic algorithm (GA) approach is used as a complementation of fuzzy model to optimize fuzzy rules. One method to optimize the fuzzy rules is Pittsburgh method in GA. In this method, one gene is used for every rule and the gene value finds out the rule.The kind of membership function will have a great impact on the result. The kinds of membership function for fuzzy sets involve triangular, trapezoidal, generalized bell, Gaussian, Gaussian combination, Sigmoidal, product of two sigmoidal, difference between two sigmoidal, Π, Z and S shapes. The objectives of this study are: 1- providing two fuzzy models for the social and technical-mechanization indices for wheat production 2- optimizing the fuzzy rules and the type of membership function for the fuzzy set. Materials and Methods: Fuzzy toolbox of MATLAB software ver. 7.8.0 (R2009a) was used to design fuzzy model. Fuzzy inference system (FIS) used in this study was Mamdani type that is based on if-then rules. The age, experience and literacy level of farmers were selected as input data for fuzzy social model. Access to water supply, roads, silage, labor, tractors and machinery and conservation tillage equipment were selected as input data for fuzzy technical-mechanization model. Mamdani fuzzy inference system was used to design models. Fuzzy rules were written by a mechanization expert knowledge. To correct written rules, the method of Pittsburgh in GA was used to optimize the fuzzy rules for all FISs. Then, a program was written in MATLAB software to get the best combination of membership functions to achieve the best result. The program tested 24 kinds of combined membership functions for medial and side fuzzy sets of input variables. The result was the best when the relationship between obtained index and crop yield had the highest value of the correlation coefficient (R2), minimum value of mean square error (MSE) and mean absolute error (MAE). So the fuzzy-GA model will produce the social and technical-mechanization indices while the fuzzy rules of model have been optimized and the best combination of membership functions has been selected. Results and Discussion: The coefficients of determination were obtained 0.11 for fuzzy social model and 0.51 for technical-mechanization model before optimization of fuzzy rules. The error of fitness function decreased with rising generation numbers of GA until the best answer was obtained. After optimization of fuzzy rules by genetic algorithm, these values increased to 0.50 and 0.71 for the fuzzy social and technical-mechanization models, respectively. This result showed that optimizing the fuzzy rules had a significant impact on results of models. After implementation of the written program, to select the best type of membership functions for fuzzy input variables, coefficient of determination varied from 0.14 to 0.51 and 0.1 to 0.73 for the fuzzy social and technical- mechanization models, respectively. This result showed that the effect of social factors on wheat yield was less than technical-mechanization factors and yield can be predicted by technical-mechanization factors with more accuracy than social factors. In the social model for input of experience, the lowest MSE and the highest R2 belong to a FIS with three fuzzy sets and S, Π and Z-shaped membership functions for the right, medial and left fuzzy sets, respectively. In the technical model for input of road availability, the lowest MSE and the highest R2 belong to a FIS with three fuzzy sets and s, trapezoid and z- shaped membership functions for the right, medial and left fuzzy sets, respectively. These results showed that the type of membership functions for fuzzy sets had considerable importance for the accuracy of the model. Conclusion: It can be concluded that the accuracy of the fuzzy model with optimized rules by GA and the best type of membership function for fuzzy sets are considerable. Effect of technical-mechanization factors on wheat yield was more than social factors. This result also showed the strength of fuzzy–GA method in modeling of such issues.