See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/379308989

ARTIFICIAL INTELLIGENCE IN AGRICULTURE: A REVIEW

Article in International Research Journal of Modernization in Engineering Technology and Science · March 2024

CITATIONS READS

0 417

1 author:

Sunil Meghwanshi
Maharana Pratap University of Agriculture and Technology, Udaipur
7 PUBLICATIONS 0 CITATIONS

SEE PROFILE

All content following this page was uploaded by Sunil Meghwanshi on 27 March 2024.

The user has requested enhancement of the downloaded file.

 e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science
( Peer-Reviewed, Open Access, Fully Refereed International Journal )
Volume:06/Issue:03/March-2024 Impact Factor- 7.868 www.irjmets.com

ARTIFICIAL INTELLIGENCE IN AGRICULTURE: A REVIEW

Sunil Meghwanshi*1
*1Maharana Pratap University Of Agriculture And Technology, Udaipur, India.
ABSTRACT
According to the United Nations World Population Forecast-2022, India's population may reach 166.8 crores by
2050. And with this the demand for food and work is also increasing. The traditional practices of farmers were
not sufficient to meet these objectives. As a result, new automated processes were developed. Agriculture has
changed as a result of artificial intelligence. Artificial intelligence has the potential to solve challenges faced by
farmers such as climate change, pest and weed infestations that reduce yields. This technology is designed to
protect crop yields from various factors such as climate change, population growth, labor issues and food
security concerns. AI is being used in applications such as weather forecasting and automatic machine
adjustment for disease or pest identification. By using sensors and other devices incorporated in robots and
drones, artificial intelligence can be used in agriculture for irrigation, weeding, spraying, etc. These
technologies will reduce irrigation water, pesticide consumption, precise application of herbicides, maintain
soil fertility and help in efficient farming. Utilization of manpower, thereby increasing productivity and
improving quality. The main objective of this work is to analyze the advantages and disadvantages of artificial
intelligence in agriculture and the opportunity to implement it in India.
Keywords: Artificial Intelligence, Food Production, Agricultural Problems.
I. INTRODUCTION
By the 1960s, AI had already been developed in computer science. John McCarthy, often called the “founder” of
the field, first defined artificial intelligence in 1956 as “the science and engineering of creating intelligent
machines” (Andresen, 2002). In 1983, researchers wrote about the first time computers were used in
agriculture. This marked the beginning of artificial intelligence in the field (Gourvamoy et al., 2018). The
history of machines replacing humans in agriculture dates back to the year 1794 when Eli Whitt invented the
cotton gin, which was used to extract seeds from cotton fibers. It brought about a major revolution in the
cotton industry by increasing the speed of removing seeds from cotton fibers. The machine could remove seeds
from 50 pounds of cotton seeds in a single day. In the 20th century, computers introduced artificial intelligence-
powered machines in the agricultural sector. Started imagining. (Woodbury, 1960) Currently, a lot of research
has been done in this field to find out where artificial intelligence can be applied to improve agriculture. Many
countries have implemented it and seen the best results. Agriculture has changed as a result of artificial
intelligence. Artificial intelligence has the potential to solve challenges faced by farmers such as climate change,
pest and weed infestations that reduce yields. This technology is designed to protect crop yields from various
factors such as climate change, population growth, labor issues and food security concerns. These technologies
will reduce irrigation water, pesticide consumption, precise application of herbicides, maintain soil fertility and
help in efficient farming. Al is being used in applications such as weather forecasting and automatic machine
adjustment for disease or pest identification. Monitoring crops, irrigation, and pest control using sensors and
robots can help save resources, increase efficiency, and improve productivity and quality. AI has become an
important tool in solving agricultural problems and helping experts around the world find better solutions.
Utilization of manpower, thereby increasing productivity and improving quality.
II. CLASSIFICATION OF ARTIFICIAL INTELLIGENCE
Artificial Narrow Intelligence (ANI): Also known as weak AI involves applying AI only to specific tasks. e.g.,
Alexa, Siri, Sofia, Self-driving cars.
Artificial General Intelligence (AGI): Also known as a strong AI involves machines that possess the ability to
perform any intellectual task that a human being can. e.g., Robots in Agriculture.
Artificial Super Intelligence (ASI): It is a term referring to the time when the capability of computers will
surpass humans.

www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science

[4358]
 e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science
( Peer-Reviewed, Open Access, Fully Refereed International Journal )
Volume:06/Issue:03/March-2024 Impact Factor- 7.868 www.irjmets.com
III. APPLICATION OF AI IN AGRICULTURE
In agriculture, Artificial Intelligence can be used in many ways such as weather forecasting, managing water
resources, controlling weeds, enhancing crop growth, detecting diseases and pests, providing nutrients and
spraying fertilizer. . Agri-bots or AL robots have been developed to work like modern combine harvesters,
increase crop yields and work faster than human labor (Nawaz et al., 2020). Artificial Intelligence has become
increasingly popular in India. Many regions have adopted this system, attracting youth and encouraging
interest in agriculture and farming.
3.1. SENSORS:
Sensors are devices that detect or measure physical properties such as temperature, light, pressure, or motion,
and then convert these into signals that can be interpreted by other devices or systems. They play an important
role in many applications, including consumer electronics, automotive systems, industrial automation, health
care, and environmental monitoring. In this way, sensors are used in the field of agriculture to enhance the
operation of tractors and other equipment. They are also used at the climatology level, with weather stations
located at agricultural sites and soil sensors that show soil fertility indicators such as moisture.
3.2. SATELLITE AND AERIAL PICTURES:
Satellite pictures are captured using cameras mounted on satellites orbiting the Earth, providing a bird's-eye
view of large areas. Aerial pictures, on the other hand, are taken from aircraft, drones, or balloons and offer a
more detailed perspective of smaller areas. Both types of images are used for various purposes, including
mapping, urban planning, environmental monitoring, agriculture, disaster response, and surveillance.
3.3. AGRICULTURAL ROBOTS:
Agricultural robots, also known as agribots or agrobots, are automated machines designed to perform various
tasks in agriculture. These tasks include planting, watering, weeding, harvesting, and monitoring crop health.
They aim to increase efficiency, reduce labor costs, and optimize resource usage in farming operations.
Examples include autonomous tractors, drones for crop monitoring, robotic harvesters, and robotic weeders.
3.4. SOIL MANAGEMENT:
Soil management and AI can intersect in various ways, primarily through data analysis and precision
agriculture. AI can help analyze soil data to optimize nutrient management, predict crop yields, detect soil
erosion, and recommend personalized treatments for specific soil conditions. AI-powered drones or sensors
can collect real-time data to monitor soil health, moisture levels, and nutrient content, allowing farmers to
make informed decisions and minimize environmental impact. Using a colorimetric testing technique, IBM built
a tiny soil testing system in 2018 that is capable of evaluating five indicators. On the card's microfluidic chip,
chemical analysis is performed, and artificial neural networks (ANN) can forecast the moisture content of soil
(Sarkar, 2021), according to research. The vision algorithm also forecasts the results of the colorimetric test
(Sanuade, 2018). A supervised Al-based machine learning algorithm is called a Support vector machine (SVM).
The mean weight diameter of the soil was predicted by it (Bhattacharya, 2021). AI can recognize the carbon
sources and sinks in various locations. Different models were utilized as input inputs in ARIES (2018). The
carbon flow model, potentially stored carbon release sink model, carbon sequestration source model, and
greenhouse gas emission model are suggested by ANN (Sarkar, 2021). MOM or management-oriented modeling
is an AI- driven approach to soil management. It is a useful instrument for preventing nitrogen leaching (Li, M.,
& Yost, R. S. 2000). Decision support systems are yet another crucial soil management technique (SRC-DSS).AI
neural networks can assess the hydraulic conductivity of soil (Ghanbarian-Alavijeh, 2012). AI can predict
biological parameters like soil enzyme activity as well as physical parameters (Tajik, S., Ayoubi, 2012)
3.5. WEATHER FORECASTING:
Weather forecasting using artificial intelligence involves the utilization of machine learning algorithms to
analyze vast amounts of weather data and generate accurate predictions. AI models can process data from
satellites, weather stations, radar systems, and other sources to understand patterns and correlations in
weather patterns. These models can incorporate various factors such as atmospheric pressure, temperature,
humidity, wind speed, and historical weather data to predict future weather conditions. By continuously
learning from new data and refining their predictions, AI-powered weather forecasting systems can improve
www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science
[4359]
 e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science
( Peer-Reviewed, Open Access, Fully Refereed International Journal )
Volume:06/Issue:03/March-2024 Impact Factor- 7.868 www.irjmets.com
accuracy over time. By analyzing and manipulating enormous data sets transmitted from a weather satellite,
relay station, and radiosondes, the Numerical weather prediction (NWP) model, a well-known machine
learning model, may deliver short-term weather forecasts and long-term climate change projections (Al-Yahyai,
2010). Additionally, AI can provide insights into extreme weather events, climate change impacts, and localized
weather phenomena, enabling better decision-making for individuals, businesses, and governments. Overall, AI
enhances the reliability and precision of weather forecasting, helping to mitigate risks and optimize resource
management in various sectors.
3.6. SEED SOWING ROBOT:
Kumar and Ashok developed an Automatic Seed Sowing Robot, which consists of a single robotic arm that sows
seeds from a seed container. Using a cleverly built mechanical mechanism, this technology totally automates
the seed sowing procedure. This robot saves time and money by reducing the effort and overall cost of sowing
seeds (Kumar & Ashok, 2020).
3.7. IRRIGATION:
The aim is to use technology, including artificial intelligence, to optimize water use in agricultural sectors. It is
important that we build an irrigation system that guarantees the correct use of water resources because 85
percent of freshwater is used in agricultural operations worldwide (Talavia et al., 2020). The soil has to be kept
wet for the growth of plants and this is irrigation. Low crop yields are a direct result of inefficient irrigation
systems, which can also contribute to the wastage of water resources and leaching of chemicals into the soil
[Eisenhauer, 2021]. Soil and water management is clearly important to prevent crop failure and soil erosion.
In agriculture, irrigation is often done by farmers using ancient irrigation techniques such as watering cans or
buckets. These old systems should be replaced with current approaches using artificial intelligence. Artificial
intelligence (AI) used in machine-based irrigation control systems guarantees effective management of both
soil and water [Angeline Blessy and Kumar, 2021]. This is how artificial intelligence works
Smart Sensors: Sensors installed in the soil measure moisture levels, temperature and other relevant factors.
These sensors provide real-time data on soil conditions, allowing farmers to make informed decisions about
irrigation.
AI Algorithms: Artificial intelligence algorithms analyze data collected by sensors to determine when and how
much water is needed for optimal crop growth. These algorithms can take into account factors such as weather
forecast, crop type and soil characteristics to adjust irrigation schedules and quantities accordingly.
Remote Control and Monitoring: Automation systems allow farmers to remotely control irrigation equipment
and monitor farm conditions from anywhere with an internet connection. This flexibility enables farmers to
react quickly to changing conditions and reduce water wastage.
Precision irrigation: Automation systems can deliver water directly to the plant's root zone, reducing
evaporation and runoff. This precision irrigation technology ensures that crops get the right amount of water
at the right time, thereby improving water efficiency and crop yields.
Variable Rate Irrigation: AI algorithms can also optimize irrigation rates in different areas of a field based on
their specific needs. By varying the amount of water used based on soil moisture levels and other factors,
farmers can improve water efficiency and reduce costs.
Overall, automation in irrigation helps farmers optimize water use, reduce labor requirements, and improve
crop yields, contributing to more sustainable and efficient agricultural practices.
3.8. WEED MANAGEMENT:
Weed management generally refers to the strategies and practices used to control and reduce the growth and
impact of unwanted plants, often called weeds, in agricultural areas. These practices can include cultural
methods such as crop rotation and mulching, mechanical methods such as tillage and mowing, chemical
methods such as herbicide application, and increasingly integrated approaches that combine different
techniques for effective weed control while reducing environmental impact. Weeds are one of the main things
that reduce a farmer's expected profit. Hence, laboratory-tested AI weedicides to determine proper spray
dosage and spray correctly in the desired area, reducing expenses and chances of crop damage. Identification
systems have been developed [Partel, 2019].
www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science
[4360]
 e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science
( Peer-Reviewed, Open Access, Fully Refereed International Journal )
Volume:06/Issue:03/March-2024 Impact Factor- 7.868 www.irjmets.com
3.9. CROP PRODUCTION:
Crop production refers to the process of growing crops for agricultural purposes, especially for human
consumption, animal feed or industrial use. It includes various activities like land preparation, planting,
fertilization, irrigation, pest control and harvesting. Crop production plays a vital role in providing food
security, supporting livelihoods, and contributing to economic growth around the world. Concerns such as
unpredictable climate change, rapidly increasing population and food poverty have pushed for the adoption of
artificial intelligence to ensure sustainable agriculture. (Ghosh and Singh 2020) claim that AI has been used in
many subsectors of agriculture, including general crop management systems, pest and disease control, soil and
irrigation management, weed management, and yield prediction.
3.10. PEST AND DISEASE MANAGEMENT:
Pest and disease management in agriculture includes various strategies such as cultural practices, biological
control, chemical control and integrated pest management (IPM) approaches. These methods aim to reduce the
impact of pests and diseases on crops while minimizing harm to the environment and human health. Because
of this, artificial intelligence is used to identify agricultural diseases and provide treatment recommendations
[Clara, 2019]. Traditional farmers have relied on their expertise to deal with plant diseases and pests.
Businesses now use IT systems for everything from pest control to disease analysis and control
recommendations [Sharma 2021]. Through this method of early identification and management, agricultural
plants will be less damaged by pests and diseases, resulting in higher yields.
3.11. PRECISION FARMING:
Precision farming, also known as precision agriculture, is a farming approach that uses technology to optimize
crop yields and efficiency. It involves the use of satellite imagery, GPS, sensors, drones, and other advanced
tools to monitor and manage crops, soil, and environmental conditions with precision. This allows farmers to
apply inputs such as water, fertilizers, and pesticides more accurately, reducing waste and environmental
impact while maximizing productivity.
3.12. HARVESTING:
Harvesting usually refers to the process of collecting mature crops from fields. Sadly, often the fruits/crops get
damaged in the process. (Onishi et al. 2019) used a robotic manipulator with a harvesting arm for automated
fruit harvesting. In the context of AI for crop and fruit harvesting, it typically involves the use of robotics,
computer vision, and machine learning algorithms to automate the process of identifying and picking ripe crops
or fruits from fields or orchards. This technology aims to increase efficiency, reduce labor costs, and optimize
crop yields by accurately detecting the readiness of crops and fruits for harvesting.
IV. ADVANTAGES OF ARTIFICIAL INTELLIGENCE
1. Increased Efficiency: AI-powered systems can analyze vast amounts of data to optimize various processes,
such as crop management, irrigation, and harvesting, leading to increased efficiency and higher yields.
2. Precision Farming: AI enables precision farming techniques by providing real-time monitoring of crops, soil,
and weather conditions. This helps farmers make data-driven decisions to optimize resource usage and
reduce waste.
3. Crop Monitoring and Disease Detection: AI-powered drones and sensors can monitor crop health and detect
diseases at early stages, allowing for timely intervention and reducing crop losses.
4. Predictive Analytics: AI algorithms can analyze historical data and environmental factors to predict crop
yields, market demand, and optimal planting times, helping farmers plan effectively and maximize profits.
5. Labor Reduction: AI-driven automation can reduce the need for manual labor in repetitive tasks such as
weeding, planting, and harvesting, leading to cost savings for farmers.
V. DISADVANTAGES OF ARTIFICIAL INTELLIGENCE
1. Initial Cost: Implementing AI technologies in agriculture requires significant investment in hardware,
software, and training, which can be a barrier for small-scale farmers or those in developing countries.
2. Data Privacy and Security Concerns: Collecting and storing large amounts of data about crops, weather, and
farm operations raises concerns about data privacy and the risk of cyber-attacks or data breaches.
www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science
[4361]
 e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science
( Peer-Reviewed, Open Access, Fully Refereed International Journal )
Volume:06/Issue:03/March-2024 Impact Factor- 7.868 www.irjmets.com
3. Dependency on Technology: Over reliance on AI and technology may lead to a loss of traditional farming
knowledge and skills, as well as vulnerability to system failures or disruptions.
4. Ethical Issues: The use of AI in agriculture raises ethical questions regarding issues such as genetic
modification, animal welfare, and environmental impact, which require careful consideration and
regulation.
5. Unequal Access: The benefits of AI in agriculture may not be equally accessible to all farmers, exacerbating
inequalities between large-scale commercial operations and smallholder farmers or those in remote areas.
VI. FUTURE SCOPE OF ARTIFICIAL INTELLIGENCE
The future scope of artificial intelligence (AI) in agriculture is vast and promising. Some potential areas of
application include precision farming, crop monitoring and management, pest and disease detection,
autonomous machinery, predictive analytics for weather and yield forecasting, and optimization of resource
usage such as water and fertilizer. AI can enhance efficiency, productivity, and sustainability in agriculture,
leading to improved crop yields, reduced resource wastage, and better decision-making for farmers.
VII. CHALLENGES OF ARTIFICIAL INTELLIGENCE
Challenges of AI in agriculture encompass issues like data quality and Availability, adaptability to diverse
environments, interpretability and Trust, connectivity and Infrastructure, cost, accessibility, ethical and Social
implications, and regulatory frameworks, requiring collaborative efforts for effective resolution and
widespread adoption. Addressing these challenges will require collaboration among researchers, policymakers,
farmers, and technology developers to ensure that AI contributes positively to the sustainability and resilience
of agricultural systems.
VIII. CONCLUSION
The conclusion on the role of artificial intelligence (AI) in agriculture is that it offers immense potential to
revolutionize the industry by enhancing efficiency, productivity, and sustainability. AI-powered technologies
such as machine learning, computer vision, and predictive analytics can optimize various aspects of farming,
including crop monitoring, disease detection, precision farming, and yield prediction. However, successful
implementation requires addressing challenges such as data privacy concerns, access to technology, and
ensuring that AI solutions are tailored to local contexts. Overall, AI holds promise for transforming agriculture
and addressing global food security challenges in the years to come.
IX. REFERENCE
[1] Al-Yahyai, S., Charabi, Y., & Gastli, A. (2010). Review of the use of numerical weather prediction (NWP)
models for wind energy assessment. Renewable and Sustainable Energy Reviews, 14(9), 3192-3198.
[2] Andresen, S. L. (2002). John McCarthy: Father of AI. IEEE Intelligent Systems, 17(5), 84–85.
[3] Blessy, A., & Kumar, A. (2021). Smart Irrigation System Techniques using Artificial Intelligence and IoT.
IEEE Xplore. https://ieeexplore.ieee.org/abstract/document/ 9388444 Retrieved November 20, 2021
[4] Bhattacharya, P., Maity, P. P., Ray, M., & Mridha, N. (2021). Prediction of mean weight diameter of soil
using machine learning approaches. Agronomy Journal, 113(2), 1303-1316.
[5] Clara. (2019). Applications of artificial intelligence in agriculture: A review. Technology & Applied
Science Research, 9(4), 4377–4383
[6] Eisenhauer & Suat Irmak, (2021). Irrigation efficiency and uniformity, and crop water use efficiency,
extension soil and water resources and irrigation engineering specialist.
[7] Ghosh, & Singh, A. (2020). ‘The scope of Artificial Intelligence in mankind: A detailed review,’ NASA
ADS, 1531 p. 012045
[8] Ghanbarian-Alavijeh, B., Liaghat, A. M., & Sohrabi, S. (2010). Estimating saturated hydraulic
conductivity from soil physical properties using neural networks model. International Journal of
Environmental and Ecological Engineering, 4(2), 58-63.

www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science

[4362]
 e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science
( Peer-Reviewed, Open Access, Fully Refereed International Journal )
Volume:06/Issue:03/March-2024 Impact Factor- 7.868 www.irjmets.com
[9] Gouravmoy, U. (2018). Artificial intelligence in agriculture: A literature survey. International Journal of
Scientific Research in Computer Science Applications and Management Studies IJSRCSAMS, 7(3), 1, and
Sarkar.
[10] KUMAR, P. AND ASHOK, G., 2020, Design and fabrication of smart seed sowing robot. Materials Today :
Proc., https://doi.org/10.1016/j.matpr.2020.07.432.
[11] Li, M., & Yost, R. S. (2000). Management-oriented modeling: optimizing nitrogen management with
artificial intelligence. Agricultural Systems, 65(1), 1-27.
[12] Nawaz, A. N., Nadaf, H. A., Kareem, A. M., & Nagaraja, H. (2020). Application of Artificial Intelligence in
Agriculture-Pros and Cons. Vigyan Varta, 1(8), 22-25.
[13] ONISHI, Y., TAKESHI, HIROKI, K., TAKANORI, F., HIROMU, A.AND AYAKO, I., 2019, An automated fruit
harvesting robot by using deep learning. Robomech. J., 6 : 13 - 22.
[14] Partel, V., Charan Kakarla, S., & Ampatzidis, Y. (2019). Development and evaluation of a low-cost and
smart technology for precision weed management utilizing artificial intelligence. Computers and
Electronics in Agriculture, 157, 339–350.
[15] Sarkar, A., Maity, P. P., & Mukherjee, A. (2021). Application of AI in Soil Science. Technology, 62, 131-
136.
[16] Sanuade, O. A., Adetokunbo, P., Oladunjoye, M. A., & Olaojo, A. A. (2018). Predicting moisture content of
soil from thermal properties using artificial neural network. Arabian Journal of Geosciences, 11, 1-10.
[17] Sharma, R. (2021). Artificial Intelligence in Agriculture: A review. IEEE Xplore.
https://ieeexplore.ieee.org/abstract/document/9432187?casa_token=J9Nbv7WxGUkAAAAA:
MKMZvBiZ8sQU6 RBKz-yE4tTgJrtDiLFIZsfiHCdgYD7VWwP6vITCAa - lk9jR2HQ0gWfgRQ4V.
[18] Talaviya, T., Shah, D., Patel, N., Yagnik, H., & Shah, M. (2020). Implementation of artificial intelligence in
agriculture for optimisation of irrigation and application of pesticides and herbicides. Artificial
Intelligence in Agriculture, 4(April), 58–73.
[19] Tajik, S., Ayoubi, S., & Nourbakhsh, F. (2012). Prediction of soil enzymes activity by digital terrain
analysis: comparing artificial neural network and multiple linear regression models. Environmental
Engineering Science, 29(8), 798-806
[20] Woodbury, R. (1960). The Legend of Eli Whitney and Interchangeable Parts. Technology and Culture,
1(3), 235–253. doi:10.2307/3101392

www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science

[4363]
View publication stats