Document Type : Research Paper
Author
Professor of the Management Department of , University of Mohaghegh Ardabili
Abstract
Keywords
Main Subjects
Extended Abstract
Objectives
The purpose of this research was to design a model of the consequences of using digital technologies and point out the benefits and challenges of using these technologies in the agricultural sector. In 2020, the United Nations set out the directions for sustainable development of the global economy until 2030. One of the key areas was the development of information and communication technologies in the field of agriculture.In the 21st century, artificial intelligence techniques have experienced a resurgence following simultaneous advances in computing power, large amounts of data, and theoretical understanding. Artificial intelligence techniques have become an essential part of technology and help solve many challenging problems in computer science, software engineering, and operations research (Saigal et al., 2023).
Methods
The present study is a qualitative study conducted using thematic analysis method, which is exploratory-
inductive in terms of purpose and fundamental in terms of data collection. In this study, in order to interpret the semantic applications of digital technologies in the agricultural sector, library documents and articles, personal perspectives and individual experiences of university professors, managers, experts and specialists in digital agriculture and IT in the provinces of East Azerbaijan, Ardabil and Tehran who had at least 5 years of work experience were used. Data collection was carried out through in-depth and semi-structured interviews with 18 experts, specialists and university professors who had experience in working and teaching in the field of digital agriculture and were capable in terms of having knowledge-based indicators and the field of research-related trends, who were introduced and selected using the snowball method. It should be noted that the interview with the twelfth person led to theoretical saturation and after that, almost all the information and data were repeated, but for greater certainty and the possibility of obtaining new data, the interview was continued until the eighteenth person.
Results
In this study, Brown and Clarke's (2006) method was used for theme analysis, which has 6 main stages. The first stage is familiarization with the data. The second stage is creation of initial codes. The third stage is searching for themes. The fourth stage is reviewing themes. The fifth stage is defining and naming themes. The sixth stage is compiling the report. The Kendall correlation test was used to verify the developed model. Therefore, for the validation of the model, experts and specialists who were selected through purposive sampling were selected in the qualitative section. After determining the sample members, a questionnaire was prepared and compiled based on the analysis of the interviews and the proposed model and made available to the experts and specialists. After collecting the questionnaires and evaluating the results and analyzing the experts' views, in the second round, all the factors were again made available to all the experts and panelists, along with the average views of the members in the first round and also the previous views of the same member, and in the third round, the same process was repeated, taking into account the results of the second round. In the Kendall correlation test, the concordance coefficient is used to determine the level of consensus among the respondents. This coefficient indicates that the experts who have arranged several categories according to their importance have used essentially the same indicators to judge each of the important categories and are in agreement with each other in this regard. Complete concordance or agreement is equal to one, and in the absence of complete concordance, it is equal to zero.
Discussion
Understanding how farm technology and big data can improve farm productivity could significantly increase global food production by 2050 in the face of limited arable land and declining water levels. While much has been written about the potential of digital agriculture, little is known about the costs and benefits of these emerging systems. This research aligns with research by Sabish and Mahto (2021) under Automation and Digitalization of Agriculture Using AI and the Internet of Things, under Transformative Technologies in Digital Agriculture: Using the Internet of Things, Remote Sensing, and AI for Smart Crop Management, under Applications of AI in Agriculture, under Artificial Intelligence in Agriculture: Benefits, Challenges, and Trends.
Farms in developed countries now have tractors with navigation systems and built-in sensors that monitor all macroscopic and microscopic elements in the field. Today, as farms are increasingly connected and internet-enabled, the true potential of IoT and related technologies can be effectively utilized in monitoring tractor performance. The agricultural sector is constantly facing challenges due to shortage of skilled labor and low productivity. Technological advancements have introduced tractors and plows that require minimal human dependency. Farmland is undoubtedly the best place to use autonomous machines, as they are free from crowds and pedestrians and activities can be carried out with minimal risk. Sensors such as radars and lasers are usually used in an autonomous vehicle to detect any obstacles and manage them intelligently.
The introduction of drones in agriculture has become another success in automating many agricultural tasks such as pesticide spraying, land monitoring, etc. Most ground control stations are equipped with a user interface for monitoring the drone. Hardware is essential in controlling the row, pitch and yaw of the drones. The drone device consists of actuators and motors to perform the necessary operations, a set of sensors such as laser, radar, camera, gyroscope, accelerometer, compass, GPS receiver to read environmental information and a central processing unit.
“Data available on request from the authors”
The authors avoided data fabrication, falsification, plagiarism, and misconduct.
The author declares no conflict of interest.
)