AFTAB K
MIRJANAYAK
PG22AGR14023
Sr. M.Sc.(Agri.)
Department of Agronomy
UNIVERSITY OF AGRICULTURAL SCIENCES, RAICHUR
COLLEGE OF AGRICULTURE, RAICHUR
DEPARTMENT OF AGRONOMY
Digital technology: Boon or bane in agriculture
Master’s Seminar - I
3.
Sequence of seminar
Introduction
What is digital farming?
Components of digital farming
Applications of digital farming
Conclusion
4.
Introduction
World population- 7.8 billion and predicted - 9.9 billion in 2050.
India population- 1.4 billion (2023).
Total world population - 16% live in developed world (Northern America,
Europe, and Oceania), while 84% - developing world.
In 2030, 856 million additional people will be living in developing countries as
compared to 34 million in developed countries.
Fig. 1: Population and food supply
5.
Digital farming
“Consistent applicationof the methods of precision
farming and smart farming, internal and external
networking of the farm and use of web-based data
platforms together with big data analytics”
Remote sensing
Remote sensingis acquisition of
information about an object or a
phenomenon without coming in
contact with it by using EM
radiations.
Applications:
Crop monitoring
Soil management
Precision agriculture
Yield forecasting
Land use planning
9.
Global Positioning System(GPS)
It is a space-based satellite navigation
system that provides location and time
information in all weather conditions,
anywhere on or near the Earth where there
is an unobstructed line of sight to four or
more GPS satellites.
Applications:
Tracking livestock
Tractor guidance
Fertilization and crop protection
Yield monitoring
Soil sampling
10.
Geographic Information System(GIS)
It is a type of data base containing geographic data combined with
software tools for managing, analyzing and visualizing the data.
Applications:
Agricultural mapping
Soil analysis
Precision farming
Historical data comparisions
11.
IoT isinter-networking of physical devices.
• This system has ability to transfer data over a network without
requiring human to human or human to computer interaction
Applications:
• Crop water management
• Pest management and control works
• Precision agriculture
Internet of Things (IoT)
12.
Big data analytics
Bigdata: Enormous amount of information collected from
different sources and for the longer period like sensor data,
social networking data and business data.
Data collection:
Process oriented
Machine generated
Human source
The process used to combine
the business and traditional
analytics is called as
Big data analytics.
13.
Artificial Intelligence (AI)is the simulation of human
intelligence processes by machines, especially computer
systems
AI is when machines
Exhibit intelligence
Perceive their environment
Make decision to maximize chance of success at a goal
Artificial Intelligence (AI)
14.
AgroPad 10: AI-poweredtechnology helping farmers
check soil and water health
Any device, tool or application that permits the exchange or
collection of data through interaction or transmission
Information and Communication Technology (ICT)
Dhulipala et al.,2021
ICRISAT, Hyderabad
It is a joint initiative of IMD,
IITM, ICAR and ICRISAT
24×7 access
12 Indian languages and English
Location specific weather based
agro-advisories
More than 2,11,000 users, highest
in Karnataka (27,031)
IMD- Temperature, RH, Rainfall,
wind direction and wind speed
Notification in users mobile
regarding warnings about
cyclones, thunderstorms and
cloudbursts etc
Fig. 3: Meghdoot - a mobile app to access location specific weather based
agro-advisories
19.
Fig. 4: SmartTV application that shows the weather forecast
University of Salamanca, Salamanca Villarrubia, 2017
20.
Rebecca et al.,2020
University for Development Studies, Ghana
Fig. 5: Weather app used by the farmers
21.
University for DevelopmentStudies, Ghana Rebecca et al., 2020
Fig. 6: Whats app group used by the farmers
22.
Fig. 7: Farmer’sperceptions of the relevance or usefulness of the digital tools
and weather forecast information and data shared compared to
channels formerly used for dissemination of forecast data
University for Development Studies, Ghana Rebecca et al., 2020
Fig. 10: Laserland leveling working mechanism
Tomar et al., 2020
RVSKVV, Gwalior
28.
Table 1 :Time required and suitability of different land leveling
techniques
Land leveling
techniques
Capacity
(ha day-1
)
Leveling
accuracy
(cm)
Animal 0.08 +/- 4-5 cm
Hand tractor 0.12 +/- 4-5 cm
Blade 0.5-1.0 +/- 4-5 cm
Bucket 0.5-1.0 +/- 4-5 cm
Laser up to 2 ha +/- 1 cm
Anil, 2017
PJTSAU, Hyderabad
Uneven distribution of
irrigation water under
traditional land leveling
Laser-levelled field
prepared for rice
transplanting
29.
Table 2: Comparisonof conventional and laser guided land leveling
Parameters
Conventional
leveling
Laser land
leveling
Paddy Wheat Paddy Wheat
Irrigation depth (cm)
110-
115
30-35 90-95 20-25
Water productivity (kg m-3
) 0.37 1.5 0.47 2.44
Profit over convention(Rs. ha-1
)
1st
year 1000-1200
2nd
year 4000-5000
Saxena et al., 2021
CIAE, Bhopal
Project: Andhra Pradesh(AP) Primary Sector Mission (Rythu Kosam Project)
Partners: Government of AP, Microsoft India (R&D) Pvt. Ltd. and ICRISAT
Anon., 2017
ICRISAT, Hyderabad
SMS received through
sowing advisory app
showing boron and zinc
deficiency in the field
Fig. 11: Sowing advisory app
Messages contained essential information such as:
Land preparation
Seed treatment
Sowing time
Soil test based fertilizer application
FYM application
Plant density
Preventive weed management
Observing boron and zinc deficiency in field and
applying nutrients if needed
Harvesting
Shade drying of harvested pods
Correct storage practices
32.
Soil type
Composition (%)
(clay:silt: sand: gravel)
Seeding
accuracy (%)
Speed
(rpm)
Dry clay soil (fine) 40: 30: 20: 10 94.83 55
Sandy soil (medium
coarse)
20: 25: 25: 30 82.75 48
Very coarse soil 10: 15: 30: 45 72.41 42
Divya et al., 2013
DSCE, Bengaluru
Table 3: Automated robot seeding accuracy and machine speed
tested in different soil
Treatment
Grain
yield
(kg ha-1
)
WUE
(kg ha-
cm-1
)
Water
saved
(%)
COC
(Rs.ha-1
)
Gross
returns
(Rs. ha-1
)
Net
returns
(Rs. ha-1
)
B:C
ratio
T1 : Surface irrigation as per PoP 2580 39.1 - 36185 75593 39408 2.08
T2 : Drip irrigation at weekly
interval
2762 58.9 28.8 45170 80986 35816 1.79
T3 : Drip irrigation at 50% DASM 3560 92.7 41.7 46920 104176 57256 2.22
T4 : Drip irrigation at 75% DASM 2243 61.3 44.5 45670 65842 20172 1.44
T5 : Green SMI based drip
irrigation
3658 88.1 37 46870 106964 60094 2.28
T6 : Red SMI based drip irrigation 2445 65.2 43.1 45790 71684 25894 1.56
T7 : Sensor based automated drip
irrigation at 25% DASM
3984 79.4 23.8 50420 116465 66045 2.31
S. Em.± 157 - - - 1342 890 0.01
CD (p=0.05) 484 - - - 4165 2916 0.03
Nanda, 2021
GKVK, Bengaluru
Table 4: Grain yield, WUE, water saved and economics of sensor based automated
irrigation system in finger millet
SMI-Soil moisture indicator , DASM-Depletion of available soil moisture
37.
Table 5: Effectof sensors on plant height, dry matter production, yield and
water use efficiency of maize
Treatment
Plant
height at
harvest
(cm)
Dry matter
production
at 90 DAS (g
plant-1
)
Kernel
yield
(kg ha-1
)
Stover
yield
(kg ha-1
)
Water use
efficiency
(kg ha-cm-1
)
T1 : Surface irrigation 184.6 350.4 6551 8007 91.6
T2 : Drip irrigation at 3 days interval 194.1 416.0 8331 9485 126.2
T3 : Green SMI based drip irrigation 200.0 436.0 10441 11975 148.1
T4 : Yellow SMI based drip irrigation 194.7 365.7 7548 9145 120.8
T5 : Sensor based drip irrigation at 25 %
DASM 203.4 479.5 10676 12273 149.3
T6 : Sensor based drip irrigation at 50 %
DASM 195.6 432.6 8436 9690 128.8
T7 : Sensor based drip irrigation at 75 %
DASM 187.3 354.4 6555 8033 110.2
Chaithra et al., 2020
GKVK, Bengaluru
38.
38
Table 6: Responseof tomato yields, WUE for the two irrigation systems (AIS
and CIS) in the two seasons
King Saud University, Riyadh Ghobari et al., 2017
Character
First season (2013–2014)
Second season (2014–
2015)
AIS CIS AIS CIS
Plant height (cm) 44.0 39.0 46.7 38.7
Number of branches 6.0 5.0 6.63 5.10
Fruit length (cm) 6.3 5.7 7.1 6.3
Avg. fruit wt. (g) 95.0 93.0 93 84
Total yield (t ha-1
) 39.0 37.40 40.1 36.70
WUE (kg m-3
) 7.50 5.72 7.15 5.33
Note: AIS (Automated irrigation system): Automatically calculate Crop ET and local microclimate using
electronic sensors and controller, CIS (Conventional irrigation system): normal crop ET based irrigation
Drip: Tomato
WUE= Yiled/ETc (mm), Irrigation WUE= Yield/seasonal irrigation depth (mm)
39.
Table 7: Estimatedamount of water for different irrigation techniques in paddy
cultivation
Stages of growth
Manual–
flood
irrigation
(mm)
Drip
irrigation
(mm)
Smart drip
irrigation
method (mm)
Field preparation 200–300 200–300 200–300
Planting 400– 450 300–400 300–350
Flowering 400– 450 100–200 100–150
Maturity 100–150 50–100 10–25
Total span (100%) 1100–1350 650–1000 610– 825
Average 1225 825 717.5
Percentage utilization of water
With respect to flood
irrigation
100 67.35 58.57
With respect to drip
irrigation
148.8 100 86.97
With respect to Smart
drip irrigation
170.73 114.98 100
Barkunan et al., 2019
Anna University, Coimbatore
Wang et al.,2019
Fig. 16: Comparison of control efficacy on wheat aphids and working
efficiency in the wheat field of the unmanned aerial vehicle, boom
sprayer and two conventional knapsack sprayers
SCAU, Beijing
Note: (A)Unmanned aerial vehicle (UAV) sprayer (B) Self- propelled boom (SPB) sprayer
(C) Knapsack mist-blower (KMB) sprayer (D) Electric air-pressure knapsack (EAP) sprayer
51.
51
Fig. 17: Controlefficacy of four sprayers against wheat aphids in the field
tests at one, three and seven days after treatment
Wang et al., 2019
SCAU, Beijing
52.
Sprayer
Tank capacity
(L)
Spray area
(ha)
Spraytime
(hr)
Working
efficiency
(ha hr-1
)
UAV Sprayer 5 0.39 ± 0.04 0.095 ± 0.01 4.11
SPB Sprayer 280 0.93 ± 0.06 0.39 ± 0.03 2.38
KMB Sprayer 18 0.22 ± 0.02 0.14 ± 0.01 1.57
EAP sprayer 16 0.039 ± 0.004 0.19 ± 0.01 0.21
Table 12: Working efficiency (ha hr-1
) of four sprayers
Wang et al.,
2019
SCAU, Beijing
NOTE: Unmanned aerial vehicle (UAV) sprayer, Self- propelled boom (SPB)
sprayer, Knapsack mist-blower (KMB) sprayer, Electric air-pressure
knapsack (EAP) sprayer
53.
Jitendra et al.,2016
IARI, New Delhi
Fig. 18: Hyperspectral reflectance of aphid infested canopy measured
in mustard field
54.
Jha et al.,2019
GIT, Ahmedabad
Fig. 19: Grape disease detection system using ML algorithm
Kadeghe et al.,2020
University of Georgia, Athens
Fig. 20: Automatic cotton harvesting robot
57.
Particular
Divisions
Robot Experienced
labour
Average
labour
Beginner
labour
Work hours(h) 137 ± 0.03 170 ± 1.83 244 ± 1.28 336 ± 2.21
Number of days * (day) 5.7 7.1 10.2 14.0
Average production per
hour ** (kg/h)
8.9 42.8 29.9 21.7
Average production per day
*** (kg/day)
213.6 171.2 119.6 86.8
Average weight of each strawberry = 15 g
Average total production = 1215 kg
Based on this, the robot’s work hours and daily average production and the human’s required for daily average
production were calculated using the “Delmia Quest simulation program”.
*Working Time/24
** Robot = Total production/days × 24, Human= Total production/days/24 × 4
*** Robot =Average production per hour × 24, Human = Average production per hour × 4
Woo et al., 2020
Kyungpook National University, South Korea
Table 13: Average daily output of strawberry harvesting robot
and human labour as compared to total production
58.
Conclusion
Automated sensorbased irrigation systems have high potential to
increase WUE and grain yield
Foliar application of nutrients by agricultural drones is more profitable
compared to manual spray in greengram
Harvesting of greenhouse vegetable/fruit crops by using automated
robots is found to be advantageous over human labour
There is a need to develop holistic artificial intelligence and bid data
analytic technologies which guide the farmers from sowing to marketing
of the produce
There is need to develop economically feasible smart farming
technologies for small and marginal farmers 58