By Prashant : An Aspiring Data Leader

1
Areas to be covered…
1. AI Overview
2. What is AI
3. Evolution of AI
4. AI and its Components
5. Potential Artificial Intelligence Application Areas
6. Indian Agriculture
7. Precision Agriculture
8. Ecosystem crucial for benefits of Precision Agriculture
9. AI Driven Agriculture initiatives
10. Application of AI in Agriculture
Soil health monitoring and restoration:
Crop health monitoring and providing real time action advisories to farmers:
Increasing efficiency of farm mechanization
Increasing the share of price realization to producers

2
Areas to be covered…
11) AI Implementations
11.1) AI Applications for soil care
11.2) AI sowing app
11.3) AI for herbicide optimization
11.4) AI for Precision Farming
11.5) Examples of precision farming management
11.6) Machine Learning in Plant Stress Identification
12) Some Startup Work on Agriculture AI
CropIn
Intello Labs
Gobasco
Gramophone (Agstack Technologies)

13) What’s Next?

3
AI refers to the ability of machines to perform cognitive tasks like thinking,
perceiving, learning, problem solving and decision making. Initially conceived
as a technology that could mimic human intelligence, AI has evolved in ways
that far exceed its original conception.

With incredible advances made in data collection, processing and computation

power, intelligent systems can now be deployed to take over a variety of tasks,
enable connectivity and enhance productivity. As AI’s capabilities have
dramatically expanded, so have its utility in a growing number of fields.

4
2) What is AI

5
3) Evolution of AI

6
4) AI and its Components

7
5) Potential Artificial Intelligence Application Areas
Areas has the potential to provide large incremental value to a wide range of
sectors globally, and is expected to be the key source of competitive advantage for
firms.
 a) Healthcare:
 b) Agriculture:
 c) Smart Mobility, including Transports and Logistics:
 d) Retail:
 e) Manufacturing:
 f) Energy:
 g) Smart Cities:
 h) Education and Skilling:

8
6) Indian Agriculture
 While India has come a long way from being categorized as purely an
agrarian economy,

 Agriculture and allied sector still accounts for 49% of India’s workforce,

 16% of the country’s gross domestic product (GDP) ,

 Ensures food security to roughly 1.3 billion people.

9
7) Precision Agriculture
 Precision Farming The phrase “Right Place, Right Time, Right Product”
sums up precision farming.

 This is a more accurate and controlled technique that replaces the

repetitive and labor-intensive part of farming.

 It also provides guidance about crop rotation,

 Optimum planting and harvesting time, water management, nutrient

management, pest attacks and so on

10
8) Ecosystem crucial for benefits of Precision Agriculture

11
9) AI Driven Agriculture initiatives
 In 2016, approximately 50 Indian agricultural, technology based startups
(‘AgTech’) raised USD313 million18. For the first time, this sector is seeing
widespread participation by startups. Intello Labs, for example, uses image-
recognition software to monitor crops and predict farm yields. Aibono uses
agridata science and AI to provide solutions to stabilize crop yields.

 Trithi Robotics uses drone technology to allow farmers to monitor crops in real
time and provide precise analysis of their soil.

 SatSure, a startup with roots in India, uses ML techniques to assess images of

farms and predict economic value of their future yield

12
10) AI Applications

13
Application of AI in Agriculture
1. Soil health monitoring and restoration:
2. Crop health monitoring and providing real time
action advisories to farmers:
3. Increasing efficiency of farm mechanization
4. Increasing the share of price realization to
producers

14
Soil health monitoring and restoration:

 Soil health monitoring and restoration: Image

recognition and deep learning models have enabled
distributed soil health monitoring without the need of
laboratory testing infrastructure. AI solutions
integrated with data signals from remote satellites, as
well as local image capture in the farm, have made it
possible for farmers to take immediate actions to
restore soil health.

15
Crop health monitoring and providing real time action
advisories to farmers
 The Indian agriculture sector is vulnerable to climate change due to being rain
dependent. Varying weather patterns such as increase in temperature, changes
in precipitation levels, and ground water density, can affect farmers especially
in the rainfed areas of the country.

 AI can be used to predict advisories for sowing, pest control, input control can
help in ensuring increased income and providing stability for the agricultural
community. For example, many agronomic factors (such as vegetation health
and soil moisture) can be monitored up to the farm level through remote
sensing.

 Using remote sensed data, high resolution weather data, AI technologies, and
AI platform, it is possible to monitor crops holistically and provide additional
insights to the extension workers/farmers for their farms as & when required.

16
Increasing efficiency of farm mechanization

 Image classification tools combined with remote and local sensed data
can bring a revolutionary change in utilization and efficiency of farm
machinery, in areas of weed removal, early disease identification,
produce harvesting and grading.

 Horticultural practices require a lot of monitoring at all levels of plant

growth and AI tools provide round the clock monitoring of these high
value products.

17
Increasing the share of price realization to producers

 Current low levels of price realization to farmers (as low as 20% in fruits and
vegetables19) are primarily due to ineffective price discovery and dissemination
mechanisms, supply chain intermediary inefficiency and local regulations.

 Predictive analytics using AI tools can bring more accurate supply and demand
information to farmers, thus reducing information asymmetry between
farmers and intermediaries.

 As commodity prices are interlinked globally, big data analysis becomes

imperative. Data from e-NAM, Agricultural Census (with data on over 138
million operational holdings), AGMARKET and over 110 million Soil Health
Samples provide the volumes required for any predictive modeling.

18
11) AI Implementations

19
11.1) AI Applications for soil care
 Berlin-based agricultural tech startup PEAT has developed a deep
learning application called Plantix that reportedly identifies potential
defects and nutrient deficiencies in the soil.

 The analysis is conducted by software algorithms which correlate

particular foliage patterns with certain soil defects, plant pests and
diseases.

 The image recognition app identifies possible defects through images

captured by the user’s smartphone camera. Users are then provided
with soil restoration techniques, tips and other possible solutions.

20
11.2) AI sowing app
 Microsoft in collaboration with ICRISAT, developed an AI Sowing App powered by
Microsoft Cortana Intelligence Suite including Machine Learning and Power BI.

 The app sends sowing advisories to participating farmers on the optimal date to sow. The
best part – the farmers don’t need to install any sensors in their fields or incur any capital
expenditure.

 All they needed was a feature phone capable of receiving text messages. The advisories
contained essential information including the optimal sowing date, soil test based
fertilizer application, farm yard manure application, seed treatment, optimum sowing
depth, and more. In tandem with the app, a personalised village advisory dashboard
provided important insights into soil health, recommended fertilizer, and seven-day
weather forecasts.

 In 2017, the program was expanded to touch more than 3,000 farmers across the states of
Andhra Pradesh and Karnataka during the Kharif crop cycle (rainy season) for a host of
crops including groundnut, ragi, maize, rice and cotton, among others. The increase in
yield ranged from 10% to 30% across crops.

21
11.3) AI for herbicide optimization
 Blue River Technology has designed and integrated computer vision
and machine learning technology that enables farmers to reduce the
use of herbicides by spraying only where weeds are present, optimizing
the use of inputs in farming – a key objective of precision agriculture.

22
11.4) AI for Precision Farming
 NITI Aayog and IBM have partnered to develop a crop yield prediction
model using AI to provide real time advisory to farmers.

 IBM’s AI model for predictive insights to improve crop productivity, soil

yield, control agricultural inputs and early warning on pest/disease
outbreak will use data from remote sensing (ISRO), soil health cards,
IMD’s weather prediction and soil moisture/temperature, crop
phenology etc. to give accurate prescriptions to farmers.

 The project is being implemented in 10 Aspirational Districts across

the States of Assam, Bihar, Jharkhand, Madhya Pradesh, Maharashtra,
Rajasthan and Uttar Pradesh.

23
11.5) Examples of precision farming management:

 Identification of stress level in a plant is obtained from high-resolution

images and multiple sensor data on plants. This large set of data from
multiple sources needs to be used as an input for Machine Learning to
enable data fusion and feature identification for stress recognition.

 Machine learning models trained on plant images can be used to

recognize stress levels in plants. The entire approach can be classified
into four stages of identification, classification, quantification and
prediction to make better decisions

24
11.6 ) Machine Learning in Plant Stress Identification

25
12) Some Startup Work on
Agriculture AI

26
CropIn – Using AI to Maximize per-Acre Value

 CropIn is a Bengaluru-based startup which claims to be an intuitive,

intelligent, and self-evolving system that delivers future-ready farming
solutions to the agricultural sector.

 Essentially, CropIn uses technologies such as AI to help clients analyze and

interpret data to derive real-time actionable insights on standing crop and
projects spanning geographies. Its agri-business intelligence solution called
SmartRisk “leverages agri-alternate data and provides risk mitigation and
forecasting for effective credit risk assessment and loan recovery assistance.

 Proprietary machine learning algorithm built on satellite and weather data is

used to give insights at plot and region level

27
Intello Labs – Using Deep Learning for Image Analysis

 Bengaluru-based Intello Labs claims to provides advanced image recognition

technology that can recognize objects, faces, flora fauna and tag them in any
image.
 Intello Labs claims to provide:

1. Agricultural Product Grading: Automated quality analysis of images of food

products is an accurate and reliable method for grading fresh products
(fruits, grains, vegetables, cotton etc.) characterized by color, size and shape.
Their solution reads the image that a farmer has taken on his phone and
determines the product quality in real time, without any manual
intervention.
2. Alerts on Crop Infestation: Farmers can click an image of their crop and use
their solution to understand the pests, diseases, and foreign plants (weeds)
growing in their farms. The solution uses deep learning and image
processing models to identify any crop diseases or pest infestation in the
crops. Along with the parameters, it gives recommendations on how that
disease can be cured and prevented from increasing further.

28
Gobasco — The Intelligent Agri Supply Chain
 Gobasco claims to employ real-time data analytics on data-streams
coming from multiple sources across the country aided with AI-
optimized automated pipelines to dramatically increase the efficiency
of the current agri supply chain. “Our data-driven online agri-
marketplace affords the best prices for both the producers and buyers
at their fingertips.
 Gobasco uses AI and related technologies in the various stages of the agri
supply chain to ensure it is efficient and fast. Some of them are listed
below:

 Transition Discovery: Real-time data analysis on multiple data-streams

along with crowd-sourced data from producer/buyer marketplaces and
transporters feeds their automatic transaction discovery algorithm to
obtain high-margin transactions

29
Gobasco …
 Gobasco uses AI and related technologies in the various stages of the agri supply chain to
ensure it is efficient and fast. Some of them are listed below:

 Transition Discovery: Real-time data analysis on multiple data-streams along with crowd-
sourced data from producer/buyer marketplaces and transporters feeds their automatic
transaction discovery algorithm to obtain high-margin transactions.

 Quality Maintenance: Computer vision and AI-based automatic grading and sorting is
done for vegetables and fruits for creating an international agri-commodity standard for
reliable trading across country boundaries.

 Credit Risk Management: Crowd-sourced data, algorithms and analytics overcome the
credit default problem, the most challenging problem of current supply-chain, to ensure
a very low risk operation.

 Agri-Mapping: Deep-learning based satellite image analysis and crowd-sourced

information fusion obtains a real-time agri map of commodities at a resolution of 1 sq-
km.

30
Gramophone (Agstack Technologies) –
Image Recognition for Soil Science
 Gramophone claims to leverage the power of image recognition and soil
science to help farmers with timely information, technology, and right kind of
inputs to achieve better yields.
 “Our technology platform uses AI and machine learning to predict pest and
disease, forecast commodity prices for better price realizations and
recommends products to farmers
 “Image recognition technology in tandem with our proprietary database gives
diagnosis of problems. We use temperature, humidity and
pathology/entomology data to give accurate advisory to the farmers. Our
primary focus is to digitize agriculture science and convert it into actionable
information for the farmers to provide personalized farm management solution
which would guide farmers across the cropping cycle.”
 Gramophone claims to reach out to more than 100,000 farmers in the state
with a productivity improvement of more than 50 percent in the three
cropping cycles that they have been associated with.

31
13) What’s Next?
 Thanks to the success of AI-driven modifications in the farming sector in India,
the path has been forged and is followed by plenty of upcoming technologies.
The challenge is to reduce costs so as to make it marketable in a mass way. It is
predicted by technology experts that crop and soil monitoring techniques will
remain important tools even as climate change is being increasingly studied
and documented.

 The tools currently seek to address the core issues in the agricultural sector
such as crop yield increase, soil health and pest prevention. It is even
anticipated that AI robots might soon start making an impact in this sector.

 While there is significant progress, the ground is fertile for newer technologies
to take root in the Indian home soil of agriculture.

32
Thanks…..
For more Information
Please contact
Prashant
[email protected]

33