AI and Robots in

Smart Farming
C7
Dr Wida Susanty Haji Suhaili
What is AI?
• Commonly defined as machine’s ability to perform cognitive functions we
associate with human minds.
• Such as perceiving, reasoning, learning, interacting with the environment,
problem solving and even exercising creativity.
• Some emerging technologies evolving from AI to solve agricultural
problems:
• Robotics
• Computer vision
• Machine learning
• Agricultural robotics useful in soil and crop monitoring even predictive
analytics
AI for sustainable farming?
• AI is the integral part of the future sustainable agriculture’s industry armor
to face climate change.
• Optimization of agriculture processes of planting and herbicide usage are all
with the assistance of computer vision. This help to detect signs of disease
in crops
• Can be used to address
• Overconsumption of freshwater resources,
• Overuse of pesticides
• Biodiversity loss
• Fragmented supply chains.
• Since AI will help to constantly improve how we grow.
How is this possible?
• Offering plants individualized attention at scale.
• Historical data were gathered from thousands of growth cycles for each crop grown and continuously tweaks
growing conditions to further hone in on the most effective environment.
• Works by collecting billions of data points through an extensive network of sensors and cameras to feed the
proprietary machine-learning algorithms to be interpreted in real time.
• By doing so can simultaneously identify if plant needs more light
• It gets smarter with each grow cycle, gaining a deeper understanding about the conditions of each crop that truly
needs to thrive.
• Get the environmental conditions for plant to flourish (Crop recipe) [Bowery,
• Seeds
• Fertilizer
• Harvest season
• Geographic location of the farm itself.
• These recipes are from the highest rate of success (healthiest plants and crop yields) refined and scaled
automatically throughout.
• AI allows researchers to test, iterate and scale scientific exploration at a pace not previously achievable in
agriculture. It all falls on the amount of data collected.
Preferable indoor where factors can be
monitored.
• Even if its applied indoor, an entirely new set of granular factors/variables can be
considered:
• Spectra of light
• Photoperiod (day/night cycles)
• Intensity of light,
• Irrigation schedules
• Nutrient
• Airflow,
• Temperature
• Humidity
• CO2.
• These can be adjusted hour by hour or minute by minute in order to optimize for
plant health and ultimate flavor.
Machine learning
• Machine learning has enabled deep learning into automated technologies to
be directed for use in agriculture. Machines communicate with different
databases and produce solutions to timely problems faced by farmers.
• Adopting smart technologies, AI, the IoT, and robotics for various
applications in advanced farming can be highly beneficial to farmers.
• These technologies have reduced the involvement of labour in the processes,
thus reducing the number of human-made mistakes as well as optimizing the
processes, which have resulted in high efficiency of production as well as
high yield.
• However, future research and development is needed to overcome the
shortcomings associated with these smart technologies in advanced farming.
Utilize AI for yield prediction & optimization.
•Crop yield prediction is difficult because many factors come into play, like environment and genotype. We can
only attain accurate yield prediction after understanding how these factors influence crop yields. That’s where
artificial intelligence comes in.
•By feeding machines with the right datasets, it’s possible to predict crop yield. AI systems can use historical crop
yield data and compare with recent data, and over time, accurately determine crop yield.
•Accurate yield prediction will allow growers to make data-driven decisions about farm management. Let’s not
forget about their finances.
•AI system can help farmers identify the amount of light received by their crop’s foliage. If some plants are not
receiving enough sunlight, they can alter crop spacing to create enough space for sunlight penetration. Manual
observation of the foliage gap is costly and time-consuming.
•Visual-enabled AI systems can also observe and analyze the changes of plants daily to determine their growth
rate. Such systems can make use of data from infrared sensors, satellite imagery, and thermal cameras.
•When farmers apply fertilizers and pesticides, the system can record and measure the response of the crops.
Growers can use the data to identify underperforming crops and take the right steps to address the cause of the
problem.
•IoT and AI solutions can get integrated into autonomous tractors to help collect real-time data about soil health,
including water levels, temperature, and PH. Farmers can also use drone cameras, satellite captured images, and
other sensors to track crop health. When analyzed, the results can help growers identify nutrient deficits in the soil
and crop pests & diseases.
AI and Automation are Transforming
Farming
• Big companies are already leveraging the power of AI to develop autonomous tractors that
a farmer can control remotely. Self-driving tractors will not only reduce labor costs but
also increase the efficiency of farm operations and crop yield.
• Autonomous drones will allow farmers to capture images of crops and monitor their
conditions remotely. Using the UAVs, growers can apply crop treatments like pesticides
and fertilizers from the air. AI-powered cameras can get mounted on drones and deployed
to large-scale farms. The cameras will help growers detect issues with crops, count fruits,
and even forecast crop yield.
• AI also allows the automation of other farming activities, like harvesting, seeding,
weeding, and crop sorting. In fact, a farm in Australia leverages the power of AI and
robots to conduct hands-free farming.
• To manage all the data coming in, farmers can make use of powerful and efficient AI
platforms. The power of data can help reduce the cost of labor, increase yield production,
and reduce the environmental footprint of farming. 
• Furthermore, it can help farmers evaluate their farming strategies and resource
management for maximum productivity and profits.
Smart Farming using AI & IoT
• AI and Smart farming are the future of the agriculture industry. They will
improve farming by helping to detect crop pests and diseases while increasing
the quality of produce.
• Accurate crop yield prediction via AI will help countries achieve food security.
• As you can see, the benefit of Artificial Intelligence in the agriculture industry
is undeniable. It allows for more strategic operation, increased efficiency, and
reduced production costs. But despite being the future of agriculture, it can’t
work alone; it requires other technology.
• With that said, AI adoption comes with several challenges, including a lack of
diverse datasets and a lengthy learning curve. Other challenges include privacy
and security concerns and digital illiteracy.
Robotics
Role of Robotics in Advanced Farming
• Various types of robots are capable of conducting diverse farming operations such as
planting, field inspection, field data gathering, weed control, precise spraying, and
harvesting.
• Planting: time and effort needed as it requires high level of consistency and precision
and typically spans a large agricultural area.
• For crops such as corn, wheat, autonomous systems have been established to solve
the issues of manual planting.
• Example: Agribot used to create an autonomous seedling robot, making use of
infrared (IR) sensor in the development to verify the integrity of the seed tank, row in
identification and precision in the distance between seeds.
• Other planting activities are used in modern farming resulting in a superior planting
quality and made more proficient and suitable for future use.
Usage of Robotics in Farming #1
• Weed control and spraying
• Compared to blanket spraying, targeted spraying for weed control using robot has given
satisfactory outcomes and decreased herbicide consumption.
• As the outcome of interdisciplinary cooperation initiatives among several worldwide research
groups
• Field inspection and data collection
• Can perform the inspection process without the use of human eyesight.
• Computer vision increasingly being utilized to substitute human vision in the examination of
plants in agriculture.
• Autonomous inspection is typically carried out by mounting a camera in a static point on a
transportable robot or drone.
• Deterrence of diseases and the quality testing of commodities will become more precise and
effective as a result of self-governing strategy and its execution in the inspection procedure,
ensuring future food security.
Usage of robotics in farming #2
• Harvesting
• Increased harvesting efficiency and lower labour costs will assure
sophisticated food production yield and affordability.
• Considered as an alternate option to solving expenses and labour
unavailability.
• Autonomous recognition: simple monochrome camera, multi-template
matching algorithm, symmetry analysis, combined colour distance method,,
RGB-D data analysis for apples and sweet peppers, stereo vision for the
detection and usage of convolutional neural netwoks and deep leaning
algorithms for the recognition of fruits and evasion of hindrance in very
condensed foliage
Example: AI Farming
• Bots are now totally capable of growing our food. In fact, it is
already happening. We can look forward to a future where
we grow potatoes in the Metaverse while bots grow real in
the field.
• What does the future hold for farming? From here, the road
ahead is exciting. It will be fully automated, and very
environmentally friendly. In fact, the move to fully automated
farming is already underway.
• Google has been in the AI farming game for years – they have a
wing called the Moonshot Factory. They realize that if farmers are
going to map every plant in a field that’s a huge data problem.
Farming with Smaller Bots
• Agricultural engineer Kit Franklin from Harper Adams University
in the U.K. says that one percent of the population produce the
food for the other 99 percent. And that one percent has got to
deal with a continually growing world population. They are also
battling climate change. He says to mitigate this, future farmers
will need to do what he calls, “precision farming.”
• That is, we need to break up our land areas into smaller parts,
and be more precise with the way in which we farm. The idea is
to reduce waste and increase efficiencies by managing each
individual part of the field as a smaller and smaller part. The aim
is to do it right in all aspects wrt the collected historical data .thin
Current Machinery
• Current machinery isn’t always very exact – for example, the combine harvester.
The machines have got bigger and less precise. A huge sprayer can cover a
mammoth amount of area. But it treats everything the same. These big machines
are great for output, but not good for precision
• Another problem is poor soil health. Compacted soil isn’t very healthy for growth.
The soil becomes compacted thanks to the huge machines that are run across
field.
• There are other drawbacks to these massive machines. In the rain, these huge
machines can get bogged. The dig-out can destroy even more soil. Says Franklin,
“We humans don’t seem to learn a lot, because years ago we had the very same
problem using steam engine tractors. It destroys the soil structure, and this has
caused yields to plateau.
• Other drawbacks to these massive machines, in the rain these huge machines can
get stucked. The dig-out can destroy even more soil.
Farming output
• Can be increased in two basic ways
• Intensification: Increasing yield per unit area
• Extensification: Expanding the area under cultivation
• Sustainable intensification required – goal to increase production from existing farmland while
minimising environmental damage, thereby maintaining the land’s capacity to continue to produce
food and also help to preserve biodiversity.
• Key component of sustainable intensification is smart farming or precision farming. It combines
remote sensing, IoT devices, robotics, big data analytics, artificial intelligence, and other emerging
technologies into an integrated high-resolution crop production system.
• Green technology: a suite of technologies and farming practices involving high-yielding crop
varieties, agro-chemicals (fertilizers, herbicides, and pesticides) irrigation and mechanisation.
• Industrial-scale agriculture use genetically modified crops.
• High levels of input, the development of resistance to pesticides and herbicides and the use of large,
expensive and environmentally damaging farm machinery.
Drawback of industrial-scale farming
• Use of large, heavy machinery such as tractors, sprayers and
harvesters which compact the soil and compromise ta crop plant’s
ability to develop a healthy root system.
• Soil compaction is an important factor in the slowing of crop yield
• Low resolution – when chemicals applied via sprayers, some may miss
target, lead to wasteful but also create environmental pollution
harming beneficial organisms and compromise ecosystem services.
• Can be addressed by replacing with multiple small autonomous
devices, backed u by modern IT infrastructure with the goal to unlock
flatlining crop yield curves.
Smart AKIS – European Agricultural Knowledge and Innovation Systems (AKIS)

• Smart-AKIS is a Horizon 2020 thematic network which aims to increase the adoption of Smart Farming
Technologies by the European farming community. It strives to bridge the gap between the field and research
on the identification and delivery of new Smart Farming solutions to fit farmers’ needs. Towards innovation-
driven research in Smart Farming Technology.
• The application of modern Information and Communication Technologies (ICT) into agriculture leading to a
Third Green Revolution
• Third Green Revolution is based upon the combined application of ICT solutions such as precision equipment,
IoT, sensors and actuators, geo-positioning systems, Big Data, Unmanned Aerial Vehicles (UAVs, drones) ,
robotics etc.
• Smart Farming has a real potential to deliver a more productive and sustainable agricultural production, based
on a more precise and resource-efficient approach.
• This project aim to showcase and assess over 400 research project results and available smart farming
technologies and solutions on its platform, leading to the adoption of over 50 Smart Farming solutions,
involving over 700 stakeholders at specific events.
• From the farmer’s point of view, SF provide farmer with added value in the form of better decision making or
more efficient exploitation operations and management.
• Smart Farming strongly related to 3 interconnected technology
• Management Information Systems
• Precision Agriculture
• Agricultural automation and robotics
Smart AKIS
• Management Information Systems: Planned systems for collecting, processing,
storing, and disseminating data in the form needed to carry out a farm’s operations
and functions.
• Precision Agriculture: Management of spatial and temporal variability to improve
economic returns following the use of inputs and reduce environmental impact. It
includes Decision Support Systems (DSS) for whole farm management with the goal
of optimizing returns on inputs while preserving resources, enabled by the
widespread use of GPS, GNSS, aerial images by drones and the latest generation of
hyperspectral images provided by Sentinel satellites, allowing the creation of maps of
the spatial variability of as many variables as can be measured (e.g. crop yield, terrain
features/topography, organic matter content, moisture levels, nitrogen levels, etc).
• Agricultural automation and robotics: The process of applying robotics, automatic
control and artificial intelligence techniques at all levels of agricultural production,
including farmbots and farm drones.
Challenges and Recommendation
• Major challenges is the lack of proper knowledge of farmers who practice them in the
field.
• Thus need to simultaneously educate farmers about the insights of technological devices and
produce a proper information base from individual farming lands to optimized the devices in the
future.
• Fear of technological devices and automation to replace labour create reluctance towards
technologies among farmers.
• Hands-on experiences with the technologies to introduce them.
• Not accepted due to safety considerations
• More precise sensors and controlling technologies developed and employ autonomous
agricultural machinery, combine with IoT technologies to ensure machinery safety.
• Explore both cultivation and domestication of species to make it easier for farmers to use.
• The major challenge for sensor development and agricultural robotic technology is the
required spatial and resolution data being unable to be measured as they vary extremely
and hence pose difficulties in measuring them. The goal of new analytical methods is to
extract new knowledge by combining data and fusing disparate information layers.
• Network applications must be trustworthy and scalable in order to manage these complex
systems
References
• Kose, U et al (2023) Artificial Intelligence and Smart Agriculture Technology.
https://www.researchgate.net/publication/360401702_Smart_Farming_Using_Artificial_Intelligenc
e_the_Internet_of_Things_and_Robotics_A_Comprehensive_Review/link/62973310431d5a71e771
ced4/download
• Mahendra, S (2022) Smart Farming using AI & IoT
https://www.aiplusinfo.com/blog/smart-farming-using-ai-and-iot/
• Buckler, N (2022) AI farming: Artificial Intelligence and Bots are Now Growing our Food.
https://beincrypto.com/ai-farming-artificial-intelligence-and-bots-are-now-growing-our-food/
• McLellan C. ( Smart Farming: How IoT, robotics, and AI are tackling one of the biggest problems of
the century. chrome-extension://efaidnbmnnnibpcajpcglclefindmkaj/https://utechnologies.co.za/
wp-content/uploads/2019/01/IoT-Robotics-and-AI-Enabling-Farming.pdf
• Smart Farming Thematic Network (2022)
https://www.smart-akis.com/index.php/network/what-is-smart-farming/
• Bowery Farming, (Dec 2022) AI in agriculture: The future of Sustainable Farming,
https://boweryfarming.com/artificial-intelligence/#:~:text=AI%20Unlocks%20Efficiency%20and%20
Scale&text=It%20works%20with%20our%20AgTech,opportunity%20to%20become%20more%20su
stainable