The main purpose of this research was to identify the challenges facing development of precision agriculture in Iran. A descriptive survey research was undertaken and questionnaire was used to collect the data. The research population included agricultural specialists and experts familiar with precision agriculture (N=450) and by using proportional stratified sampling, a sample of 117 was selected based on the Cochran formula. Data were collected using a questionnaire, which its validity was confirmed by a panel of experts. Its reliability was established by collecting 30 questionnaires and Computed Cronbach’s alpha score was 81%, which indicated that the questionnaire was highly reliable. All survey data were analyzed using the Statistical Package for Social Sciences (SPSS 16.0). The results indicated that 50 percent of the variances in the challenges of developing precision agriculture could be explained by infrastructural and educational, content, managerial, human resources, extensional and program planning.

Agriculture is a complex system science and the knowledge of it is consisting of much concepts and relationships. Examinations in connection with site-specific farming have been carried out by our institute since 1998. Precision farming is a way of agricultural production, which takes into account the in-field variability, a technology where the application-seeding, nutrient replacement, spraying, etc. has taken place to act on the local circumstances of a given field. The geographic information system (GIS) created by computing background makes possible to generate complex view about our fields and to make valid agro technological decisions. With the advent of the satellite-based Global Positioning System, farmers gained the potential to take account of spatial variability. Our goal was to compare two systems for marking out further research tasks, because in some cases there have been misunderstandings among the researchers, and the information provided by given companies seems to be complicated for potential users. This article provides an overview of worldwide development and current status of precision agriculture technologies and Application of GIS and GPS in Precision agriculture.

The purpose of this descriptive-analytical study was to assess the educational needs of Guilan agricultural experts on applying precision agriculture. The statistical population consisted of all experts in different field of agriculture (Agronomy, Horticulture, Extension, Mechanization and Engineering) in Guilan (N=234). The sample size (n=133) was determined by using Bartlett Minimum Sample Size Table for the given population and cluster sampling method was applied to select them. In order to assess these educational needs, a questionnaire based on Borich Needs Model was provided. Data analysis was performed using SPSS21. These educational needs were analyzed and ranked using Mean Weighted Descriptive Scores (MWDS). Results showed that competencies such as geographic information system and variable rate technology were noticed as the most important priorities for education, respectively.However, information technology was in the last rank in the educational needs list. Findings indicated that all competencies were placed at the high level of importance. Findings of Mann-Whitney U and Kruskal-Wallis tests revealed that there was no significant difference between men and women, level of education, attending the prior education program, age, experience and organizational position at 0.05 significant level. Then, there was a contingency on education needs.

The purpose of this study was to identify obstacles hampering the use of precision agriculture from the viewpoints of managers regarding farming production cooperatives of Dezful Township. The research used a survey method to conduct the study. The instrument used for data collection was a questionnaire. Its validity was gained by the use of a panel of experts and its reliability by using Cronbach's alpha (0. 735) was approved. The population included 136 managers of farming production cooperatives of Dezful Township were selected through census method. To identify the obstacles, a factorial analysis with principal components model was used. Based on the results of a factorial analysis regarding obstacles hampering the application of precision farming, 5 main factors were identified, which included: the lack of economic and technical requirements, lack of requirements for cognitive domain, low socialization, lack of support services and conflicts with environmental and social conditions. After using orthogonal factor rotation varimax method, it was found that these obstacles in regard to the use of precision farming, 57. 65 percent of the total variance explained.

With the rise of new powerful statistical techniques and neural networks models, the development of predictive species distribution models has rapidly increased in ecology. In this research, a learning vector quantization (LVQ) and multi-layer perceptron (MLP) neural network models have been employed to predict, classify and map the spatial distribution of A. repens L. density. This method was evaluated based on data of weed density counted at 550 points of a fallow field located in Faculty of Agriculture, Shahrood University of Technology, Semnan, Iran, in 2010. Some statistical tests, such as comparisons of the means, variance, statistical distribution as well as coefficient of determination in linear regression were used between the observed point sample data and the estimated weed seedling density surfaces by two neural networks to evaluate the performance of the pattern recognition method. Results showed that in the training and test phases non-significant different was observed between average, variance, statistical distribution in the observed and the estimated weed density by using LVQ neural network. While this comparisons was significant except statistical distribution by using MLP neural network. In addition, results indicated that trained LVQ neural network has a high capability in predicting weed density with recognition error less than 0.64 percent at unsampled points.While, MLP neural network recognition error was less than 14.6 percent at unsampled points. The maps showed that, patchy weed distribution offers large potential for using site-specific weed control on this field.