TIJER || ISSN 2349-9249 || © May 2023 Volume 10, Issue 5 || www.tijer.

org

UTILIZATION OF ARTIFICIAL
INTELLIGENCE IN THE AGRICULTURE AND
FOOD INDUSTRY
MR. ARVIND CHAUHAN, MS. MANISHA
ASSISTANT PROFESSOR, ASSISTANT PROFESSOR
RAYAT BAHRA UNIVERSITY

Abstract

The world population is increasing day by day and it is expected that it will reach over 15
billion by upcoming 25 years. With the growth in population we require agricultural and food
production by 75% to fit the need. It is a serious challenge for the country and agri-food
industry. Artificial Intelligence is a technology which is developed for the motive of
understanding the nature of machines. AI is used in machines and computers. Artificial
intelligence and machine learning has a multiple predictive methods amalgamation to
ameliorate the food and agriculture sector. It has some limitations that should be analyzed by
contributor.
Keywords: Artificial intelligence, machine learning.

Introduction:

The sustainability of the agricultural sector is the key to ensuring food security and the
eradication of hunger for the ever-growing population because it is estimated that the global
food production must increase by 60–110 percent to feed 9–10 billion people by 2050. A well-
documented traceability system has become a requirement for quality control in the food chain
as a result of the emergence of several food safety scandals and incidents, such as akin to
dioxin in poultry and bovine spongiform encephalopathy. In addition, weather and climate
change conditions, as well as sustainable water management due to water scarcity, are crucial
challenges in the coming years. For these reasons, urgently, the establishment of a well-
documented traceability system is needed. Helping farmers and stakeholders improve their
decision-making through the adoption of sustainable agriculture practices is a vital choice for
anticipating effective solutions, especially the use of digital technologies like cloud
computing, artificial intelligence (AI), and the Internet of Things (IoT) Also widely utilized
are location intelligence technologies combined with the subgroups of AI (machine and deep
learning algorithms). Our review's major objective is to outline the key uses of machine
learning and artificial intelligence in the agri-food industry.
Artificial Intelligence and Machine Learning Approach:
Artificial intelligence (AI) is a tool for creativity that models how technology, primarily
computer systems, robots, and digital equipment, comprehend human intelligence and ability.
Artificial intelligence (AI) has several uses, including natural language processing (NLP) to
understand spoken human language, computer vision to view analog-to-digital conversions
TIJER2305322 TIJER - INTERNATIONAL RESEARCH JOURNAL www.tijer.org 636
 TIJER || ISSN 2349-9249 || © May 2023 Volume 10, Issue 5 || www.tijer.org
like video, and speech recognition and expert systems to imitate judgments. The three
cognitive processes that go into AI encoding are learning, reasoning, and decision-making.
Learning involves gathering data and then developing algorithms to turn it into usable
information, and self-correction (constantly adjusting designed algorithms to ensure that they
deliver the most accurate results). Artificial intelligence (AI) is a tool for creativity that
replicates human intelligence and aptitude processes through technology, primarily computer
systems, robots, and digital equipment [4]. For example Natural language processing (NLP)
can comprehend spoken human language, while computer vision can observe an analog-to-
digital conversion, such as a video, and voice recognition and expert systems can simulate
judgment. The AI encoding is based on learning (acquiring data and then developing
algorithms to transform it into actionable information), reasoning (selecting the appropriate
algorithm to arrive at a desired result), and As three cognitive abilities, self-correction
(constantly tweaking created algorithms to ensure they deliver the most accurate results).

Applications of Artificial Intelligence in Agriculture and the Food Industry:

The employment of ML algorithms in the primary four clusters of the agriculture supply chain
(preproduction, production, processing, and distribution) is currently gaining importance [15].
In fact, ML technologies are applied throughout the preproduction stage, particularly for the
forecasting of crop yield, soil characteristics, and irrigation needs. The ML could be utilized
for illness identification and weather forecasting in the following step of the production phase.
Utilizing ML techniques is used in the third cluster of the processing phase, particularly to
predict the production planning to achieve a high and secure product quality. ML algorithms
could be applied to the distribution cluster as well, particularly for consumer analysis, storage,
and transportation. The first step is the preproduction cluster.
The first link in the supply chain for agricultural goods is the preproduction cluster. It
primarily addresses crop yield forecasting, soil characteristics, and irrigation needs. For better
plant management, many studies stress the significance of crop yield production. In fact, by
incorporating input data (equipment needs, nutrients, and fertilizers) into effective models
based on ML algorithms, these precision agriculture tools seek to encourage stakeholders and
farmers to support the best decisions in crop yield forecasting and advance smart farming
techniques. The Bayesian network, regression, decision tree, clustering, deep learning, and
ANN are some of the recent ML techniques utilized for crop yield prediction. Multiple ML
algorithms are applied in learning in accordance with the predicted soil management
properties.
18 different table olive cultivars from around the world were examined by Ben Ayed et al.
[16] using morphological, biological, and physicochemical criteria as well as the Bayesian
method to examine the effects of these factors on tolerance, production, and oil content. They
demonstrated that the crop's tolerance had a significant impact on oil content. The regulation
of irrigation, which has a significant impact on the crops' quality and yield, is another critical
factor in the preproduction cluster. In fact, researchers used soil moisture data, precipitation
data, evaporation data, and weather forecasts as input data for simulation and optimization of
predicted models based on ML appropriate algorithms to achieve a successful irrigation
system (better timing, location, and irrigation volume decisions).The second stage of the

TIJER2305322 TIJER - INTERNATIONAL RESEARCH JOURNAL www.tijer.org 637

 TIJER || ISSN 2349-9249 || © May 2023 Volume 10, Issue 5 || www.tijer.org
agricultural supply chain is the production cluster. Numerous variables have an impact on and
are important in the phase of crop production. They include crop protection against biotic
stress factors (weeds and diseases) and abiotic stress factors (nutrient and water deficit), crop
quality management, and harvesting. The weather forecasts (sunlight, rainfall, humidity, etc.)
are also included.

Limitations and Issues with Artificial Intelligence (AI) and Machine Learning (ML):
Nevertheless, despite all these benefits, there are also disadvantages to the AI technology that
pose difficulties. First and foremost, the greatest social problem is potential unemployment.
Since robots and intelligent machines could take over most monotonous jobs, there will be a
significant decline in human involvement, which will have a negative impact on employment
standards. Other technological issues, such the fact that machines can only perform the jobs
for which they have been designed or programmed, and that if they are asked to perform
anything else, they often fail or provide useless results, could be a significant hindrance.
The high cost of building and maintaining intelligent machines and computers could also be
seen as a technological limitation of AI, especially given that AI is constantly evolving and
that means that hardware and software must also be updated over time to keep up with the
most recent demands. Machines require costly repairs and upkeep.
Due to the complexity of the devices, the creation needs significant costs. These applications'
high cost, which could raise the cost of the goods, is another problem. In addition, there may
be certain sustainability risks and concerns beyond the benefits provided by smart and
computerized technology, such as the enormous energy consumption, the e-waste problem,
market concentration, employment displacement, and even the ethical framework.

Conclusions
The food and agriculture sectors are among the most important to humanity. In order to get to
the final user or customer, the first agricultural products are utilized as inputs in a number of
multifactor distributed supply chains, including four clusters or phases (preproduction,
production, processing, and distribution) of the agriculture supply chain It is urgent to use
digital technologies at various stages of the agriculture supply chain, such as the automation of
farm machinery, use of sensors and remote satellite data, artificial intelligence, machine
learning for improved crop monitoring, and water, due to a number of challenges facing the
agriculture and food sector in the future as well as various factors like climate change,
population growth, technological advancement, and the state of natural resources (such as
water).
References

1. A. Suprem, N. Mahalik, and K. Kim, "A review on application of technology systems,

standards, and interfaces for agriculture and food sector," Computer Standards &
Interfaces, vol. 35, no. 4, pp. 355-364, 2013, view at: Publisher Site | Google Scholar.

2. M. Mohri, A. Rostamizadeh, and A. Talwalkar, "Foundations of Machine Learning," MIT

Press, Cambridge, MA, USA.
TIJER2305322 TIJER - INTERNATIONAL RESEARCH JOURNAL www.tijer.org 638