Digital Agriculture and its Applications.pptx

na

1. 1

2. ACHARYA N. G. RANGA AGRICULTURAL UNIVERSITY AGRICULTURAL COLLEGE, MAHANANDI Master ’s Seminar : GP -591 DIGITAL AGRICULTURE AND IT’S APPLICATIONS Date: 07/01/2022 COURSE INCHARGE PRESENTED BY Dr. M. Srinivasa Reddy G. Chaitanya Kumar MAM/2020-002 Associate Professor and Head, Dept. of Agronomy. 2

3. 3

4. INTRODUCTION - AGRICULTURAL REVOLUTIONS LIMITATIONS IN TRADITIONAL AGRICULTURE DIGITAL AGRICULTURE REVOLUTION (DAR) NEED FOR DIGITAL AGRICULTURE DIGITAL AGRICULTURAL TECHNOLOGIES DA INITIATIVES IN INDIA BENEFITS OF DIGITAL AGRICULTURE BARRIERS OF DAR IN INDIA HOW TO STEP UP DA IN INDIA CASE STUDIES CONTENTS CONCLUSION WAY FORWARD \ FUTURE THRUST 4

5. Introduction Agriculture is the science, art, or practice of cultivating the soil , producing crops , and raising livestock and in varying degrees the preparation and marketing of the resulting products. • History of Agriculture began thousands of years ago – 105,000 years (Seed Collection) . • Nearly 3 billion people in the world depend on agriculture for their livelihood (FAO, 2020) . • Agriculture accounts for nearly 26% of GDP in Developing Countries and 4 % of Global GDP (The World Bank, 2018). 5

6. In Indian Context • Agriculture – Driving force and furculum for country’s economy. • India has 9% of world arable land and 2.3% of geographical area . • Indian agriculture contributes • 8% of global agricultural GDP • Support 18% of the world population • In Indian economy, agriculture contributes • 17.6% of nation’s GDP • Provides 60% of employment • Livelihood for 70% of nation’s population. Source : Ministry of Agriculture and farmers welfare 6

7. Globally, Agriculture is undergoing a series of revolutions to address the needs and challenges evolving day by day First Agricultural Revolution Arab Agricultural Revolution Second Agricultural Revolution British / Scottish Agricultural Revolution Third Agricultural Revolution Green Revolution Fourth Agricultural Revolution ??? 7

8. ( Watson, 1974) • Observed in Europe and Islamic nations. • Described by historian Antonio Garcia Maceira in 1876. • Period from 8 th to 13 th century. • Transformed with improved techniques and the diffusion of crop plants. Source : https://en.wikipedia.org/wiki/Agriculture • Sugarcane, Cotton and Fruit Trees (Orange) • During the period between the mid-17th and late 19th centuries . • Crop rotation, • Chinese plough, • Development of National market, • Transportation infrastructures, • Selective breeding of livestock. https://en.wikipedia.org/wiki/British_ Agricultural_Revolution 8

9. • Started during Mid 20 th Century (1960-1980) • Resulted in Great increase in production of food grains • Observed in Mexico and Indian Sub-Continent . • Main Crops – Wheat, Rice, Jowar, Bajra, Maize. Dr. Noraman E Borlaug Father of Green Revolution • Indian Agriculture was converted into an industrial system. • Positive Impacts • Increase in Crop Produce • Increase in Employment • Decrease in Imports (Self-sustainability) • Industrial Growth Dr. M. S. Swaminathan Father of Green Revolution 9

10. Challenges in Present Day Agriculture • Small and marginal farmers - unsustainable farm incomes and poverty . • Unsustainable farming practices leads to soil degradation and water stress . • Poor farm mechanization due to affordability challenges. • Lack of food processing, logistics and warehousing infrastructure close to farm gates, increasing wastage; • Gaps in market linkages, challenges in price discovery for farmers and price volatility in the market • Challenges in financial and digital inclusivity. • Higher cost of inputs and scarcity of Labour force 10

11. DIGITAL AGRICULTURAL REVOLUTION (DAR) (or) AGRICULTURE 4.0 11

12. Digital Agriculture is the use of new and advanced technologies, integrated into one system, to enable farmers and other stake holders within the agriculture value chain to improve food pr oduction.(FAO,2018) 12

13. Need for Digital Agriculture? Agriculture in the 21 st century faces multiple challenges . Elevated Increase in Demographics Increase in Population, Rapid Urbanization, Depletion of Natural Resources Degraded farm lands, Deforestation, Unbalanced Fertilizer Use Climate Change Reduced Productivity, GHG emissions, Variability in Precipitations 13

14. Change In Demographics Depletion of Natural Reserves 14 Source: Agriculture 4.0, February 2018, Oliver Wyman

15. DIGITAL AGRICULTURAL TECHNOLOGIES 15

16. ARTIFICIAL INTELLIGENCE (AI) In Agriculture 16

17. What is Artificial Intelligence? AI is the construction of Computers , Algorithms and Robots that mimic the intelligence observed in humans, such as learning , problem solving and rationalising . Unlike traditional computing, AI can make decisions in a range of situations that have not been pre-programmed into it by a human. Source : United Nations Global Compact 17

18. VISION “To transform the state of agriculture by deploying emerging technologies in an inclusive and sustainable way” 18

19. Applications of Artificial Intelligence in Agriculture Growth Driven by IOT Automatic Techniques in Irrigation Image Based Insight Generation Identificatio n of Optimal mix for Agronomic Practice Health Monitoring of Crops 19

20. AI STARTUPS IN AGRICULTURE 20 20

21. BIG DATA IN AGRICULTURE 21

22. Data From Diversified Sources Used to handle huge amount of data transmitted from IoT devices What is Bigdata? IBM Deep Thunder Model 22

23. Frame Work of Bigdata for Precision Agriculture 23

24. • Precision agriculture empowered by big data has become a new direction of agricultural development in the future. • The emergence of big data technology provides an effective solution to solve new problems such as data diversity, high data volume, and high speed. • Big data promotes the in-depth aggregation of multi- source data. 24

25. PRACTICAL APPLICATIONS OF BIGDATA Change in Weather, Soil Moisture, Rainfall, Smart and precise application of Pesticides. Soil Temperature Increases Supply Avoid Over Use of Chemicals and other Provide Information on Chain crop Efficiency (Tracking and Factors. Transparen cy of Food Trucks) Easy marketing Facilities Helps Taking Accurate and Precise decisions. in 25

26. enables seamless data storage and real-time reporting across the value chain 26

27. CLOUD COMPUTING • Cloud computing provides a shared pool of configurable IT resources (e.g. processing, network, software, information and storage) on demand , as a scalable and elastic service, through a networked infrastructure, on a measured basis, which needs minimal management effort, based on service level agreements between the service provider and consumers, and often utilizes virtualization resources. (Sushil Kumar ,2016) 27

28. ROLE OF CLOUD COMPUTING IN AGRICULTURE FIELD • Agriculture information data bank • High integration & sharing of agricultural information • Providing agricultural technology service & science • Improvement of the agricultural products marketing • Efficient use of agricultural resources • Promote the circulation of agricultural product and service in wider level • Management of all data related to land, location, area. 28

29. BENEFITS OF CLOUD COMPUTING IN AGRICULTURE • Data Readiness any time & any where • Local and global communication • Improve economic condition of the Nation • Enhanced the GDP of the nation • Ensure food security level • Motivation of farmers and researchers • Reduction of technical issue • Rural-Urban movement • Data availability at any time and at any location without delay • Improve market price of Food, seeds, other product 29

30. 30

31. • IoT is the network of physical objects or “things’’ embedded with electronics, software, sensors and network connectivity, which enables these objects to collect and exchange data. • IOT was proposed by KEVIN ASHTON in 1999. • Connection of each and every thing to internet. 31

32. Push the future of farming to next level. Huge opportunities for farmers to monitor crops and increase productivity . Opened up extremely productive ways to cultivate soil with use of cheap, easy-to- install sensors. To meet growing needs of food for increasing population . 24/7 visibility into soil and crop health. 32

33. 33 Wang et al . (2020)

34. SMART IRRIGATION SOIL MONITORING CLIMATIC CONDITIONS MONITORING CROP MANAGEMENT AGRICULTURE DRONES GREEN HOUSE AUTOMATION PREDICTIVE ANALYSIS, PEST & DISEASE MONITORING 34

35. Saving fertilizers and chemical crop protection agents Controlling crop state and preventing its losses when stored Tracking processing line equipment condition Boosting soil fertility due to ‘smart’ Monitoring state and location of farm animals Increasing machinery efficiency correction. 35 Swamy et al. (2020)

36. Small dispersed land holdings Complexity, scalability and affordability of technology Internet connectivity and availability Low awareness of IoT devices Lack of investment and venture capital funds 36

37. REMOTE SENSING 37

38. What is Remote Sensing? • The acquisition of information about an object or phenomenon without making physical contact with the object and thus in contrast to on-site observation, especially earth. • Remote sensing generally refers to the use of satellites or aircrafts- based sensor technologies to detect and classify objects on earth both on land and the waterbodies. 38

39. A – Energy Source / Illumination, B – Radiation and Atmosphere, C – Interaction with Target, D – Recording of energy by the sensor, E – Transmission, Reception and Processing F – Interpretation and Analysis and G - Application 39

40. MILESTONES IN HISTORY OF REMOTE SENSING YEAR MILESTONE ACHEIVED Discovery of Infrared by Sir W. Herche Photography from Balloons 1800 1859 1959 First Space Photograph of the Earth ( xplorer-6 ) 1960 1972 First Meteorological Satellite launched Explorer-6 Launched in 1959 Launch LANDSAT-I and rapid advancement in digital image processing 1982 1999 1999 Launch od LANDSAT-4 with new generation of sensors (TM) Launch EOS : NASA Earth observing mission Launch of IKONOS , very high spatial resolution sensor systems IKONOS Landsat-1 40

41. Applications of Remote Sensing • Crop Production Forecasting • Assessment of Crop Damage and Crop Progress • Crop Identification • Crop Acreage Estimation: • Crop Yield Modelling and Estimation • Identification of Pests and Disease Infestation • Soil Moisture Estimation • Soil Mapping • Monitoring of Droughts • Water Resources Mapping 41

42. ADVANTAGES OF REMOTE SENSING OVER TRADITIONAL AGRUCLUTRE SURVEYS • Capability of synoptic view • Potential for fast survey • Capability of repetitive coverage to detect the changes • Low cost involvement • Higher accuracy • Real time data analysis • Use of hyperspectral data for increased information 42

43. DRONES TECHNOLOGY Drones are Unmanned Aerial Vehicles with • Potential to cement the gap of Human error and inefficiency in traditional agriculture. • Provide Acute and Real time Temporal and spatial Data. 43

44. Drone technology in Agriculture • Enhanced Production • Effective and Adaptive Techniques • Greater Safety To Farmers • Irrigation Monitoring • Crop Health Monitoring and Surveillance • Crop Damage Assessment • Field Soil Analysis • Planting Method • Agricultural Spraying • Faster data for quick decision making • Less Wastage of Resources • 99% accuracy Rate • Livestock Tracking • Useful for Insurance Claims • Evidence for Insurance Companies 44

45. Robots • Robotics are being introduced to the dairy, poultry and Agricultural industries. • Applications include Weed Identification, Fertilizer Application, Pesticide Application, Fruit Picking and Field Operations. 45

46. ADVANTAGES OF ROBOTS IN FARM • Elimination of labor - It brings us an opportunity of self employment for those who are unemployed and thinks the farming profession as a nightmare. • It is one time investment - expenditure of the farming will drastically. • Use of Pesticides, Fungicides etc,. Are reduced to large extent. • It brings revolution in the farming, agriculture and cattle grazing. • Productivity will be increased to a lot extent. • Robotics gives us perfect results that perhaps increases the quality. 46

47. 47

48. INITIATIVES OF DA TECHNOLOGIES IN INDIA INITIATED BY SET UP PILOT PROJECT YEAR AT INITIATIVE FEATURES Digital Agriculture Minister of To support and accelerate projects September Started in 6 Mission Agriculture based on new technologies like AI, 2021 states and 28 2021 – 2025 & Farmers block chain, remote sensing and GIS Welfare technology and use of drones and robots Districts Agricultural Digital Infrastructure (ADI) Cisco To enhances farming and knowledge August Kaithal ( Haryana ) sharing 2019 Morena (MP). Jio Agri ( JioKrishi) Reliance It digitises the agricultural ecosystem February Jalna and Nashik Pvt. Ltd along the entire value chain to 2020 (Maharashtra). empower farmers Site Specific Crop Advisory - ITC’s e - Choupal 4.0 ITC Convert conventional crop-level September Sehore and generic advice into a personalised 2021 Vidisha (MP) site-specific crop advisory for farmer 48 Source : https://www.ibef.org/blogs/digital-agriculture-the-future-of-indian-agriculture

49. INITIATIVES OF DA TECHNOLOGIES IN INDIA INITIATIVE INITIATED BY FEATURES AgroPad (AI-powered technology) IBM AI-powered technology helping farmers check soil and water health. Results are Provided within 10 Seconds. Plantix PEAT Helps in identification and subsequent (crop disease identification over WhatsApp) German Start Up diagnosis and treatment of a Plant Disease. Trringo & EM3 Agriservices Reliance Pvt. It provide rental services of Farm Machinery and Tractors on a pay use basis to save time, money and ensure timely operations. Ltd (Ubers of the Agriculture sector) Swamitva Government of Drawing Digital maps and Revenue boundaries of every revenue area of a particular Village and provide a property card for each property holder. India Grain Bank model of ERGOS Agri-tech landscape Enable Farmer to Convert their grains into a tradable digital asset to avail Credit against those assets with partner banks. 49 49 Source :Abhishek Beriya, Digital Agriculture: Challenges and Possibilities in India

50. BENEFITS OF DIGITAL AGRICULTURE INPUT HUB PRODUCTION HUB POST HARVEST HUB CONSUMER HUB 50

51. INPUT HUB Increased access to quality inputs Increased access to machinery hiring services Provision of personalized advice on input usage Increased access to credit, finance, and insurance Improved abilities to detect counterfeits 51

52. Enablement of precision farming and smart farm management Improved pests and disease management Improved access to extension services Improved producer cooperation PRODUCTION HUB 52

53. Improved market and price information transparency Improved access to transportation and storage Improved market integration Improved processing and storage efficiency Enablement of efficient logistics Improved transport efficiency POST HARVEST 53

54. Improved food safety Improved traceability Improved market matching CONSUMER HUB 54

55. BARRIERS OF DIGITAL AGRICULTURE IN INDIA 55

56. BARRIERS OF DIGITAL AGRICULTURE IN INDIA • Lack of Internet Connectivity to Rural Areas • Digital Illiteracy • High Input cost of the Equipment • Lack of Awareness Camps • Small Land Holdings • Renting and Sharing Practices 56

57. 57

58. HOW TO MAKE DA SUCCESS IN INDIA Customised approach would be needed to implement digital agriculture to a typical Indian small farm. 1. Low Cost Technology 2. Portable Hadwares 3. Renting and Sharing platforms 4. Academic Support 5. Increase in Digital Literacy 6. Establishing Series of Networks For Higher Connectivity 7. Performing Training and Awareness Camps 8. Govt. Support to Digi Startups 58

59. Case studies 59 This Photo by Unknown author is licensed under CC BY .

60. Sanghavi et al . • The work is to adapt an Internet of Things (IoT) based approach to predict the occurrence of Downey and Powdery Mildew grape diseases at an early stage. • Location – Vineyards of Materwadi & Sakura in Nashik. • Sensors Used – Temperature & Humidity ( DHT11) and Rainfall ( Nil) Sensor ’s . • IoT Device Used – NodeMCU (NodeMCU ESP8266, 2020). 60

61. ARCHITECHTURE OF THE SYSTEM Sanghavi et al . ficial Intelligence in Agriculture 61

62. ALGORITHMS IN CENTRAL PROCESSOR For Rainfall r Powdery and Downy Mild Rainfall hr -1 Interpretation Range Interpretation <0.1 inch Light Rainfall (2) nRange=0 fTemperature=18-25 Temperature Heavy Rain Downy Mildew 0.10 to 0.30 inch Moderate Rainfall (1) nRange=0 fTemperature=25-30 Cloud and Rain Warn Powdery Mildew >0.30 inch High Rainfall (0) n Level = Read Water Level If n level < 0.1 = 2 nRange=0 fTemperature=>25 Only Heavy Rain nRange=0 fTemperature=>30 Cloud and Rain Warn If n level 0.10 – 0.30 = 1 If n level >0.30 = 3 fTemperature – Read Temp. fHumidity – Read Humidity nRange – Check Rainfall. 62

63. 63

64. Comparison of proposed system with existing systems Parameters Early Detection of Grapes WSN Monitoring of Weather and Current work Diseases Using Machine Crop Parameters for Possible Learning and IoT Disease Risk (Das et al ., 2009) (Patil and Thorat, 2016) Diseases Covered Downey Powdery Downey Powdery Downey Powdery Bacteria Leaf Spot Anthracnose Early Stage Detection Yes Yes Yes Notification Technique Used Accuracy No No Yes IOT WSN IOT Downey 90.9% Powdery 90.9% Downey 87% Powdery 84% Downey 94.4% Powdery 96% Cloud based Year No Yes Yes 2016 2014 2020 64

65. Revanasiddappa et al . (2020) • To obtain real-time detection of weed plants using a video feed from low altitude flying drones. • Segmentation Units used - U-Net, LinkNet and LinkNet-34. • Drone Used – Nano Tello Drone with ubuntu OS. • AIM- To perform object segmentation with high time complexity by using Semantic Segmentation models. • Location – Mysuru, Karnataka 65 65

66. Experimenta result o weed detection in pulse grain field using three differen semanti segmentation models Revanasiddappa et al . (2020) Approach Training Number Validation Mean Pixel Mean IoU Testing Mean Pixel Accuracy of Testing Data Mean IoU Speed of Testing Images of Weed Samples Images Accuracy of of Data Validation Data Data Validation Data U-Net 0.712 0.824 0.549 0.573 0.704 0.812 0.527 0.312s 0.553 0.176s LinkNet 297 1467 30 967 LinkNet- 34 0.867 0.898 0.843 0.581 0.217s Karnataka International Journal of Agricultural Technology 2020. 66 66

67. Approach Type of Pixel F1 Score Weed (Parthenium) Background 0.1633 U-Net Weed 0.8367 (Parthenium) Pulse Grain with soil as background 0.1084 0.8973 0.8916 0.1027 LinkNet Weed (Parthenium) Pulse Grain with soil as background 0.0368 0.943 0.9632 0.057 LinkNet-34 Weed (Parthenium) Pulse Grain with soil as background 0.0257 0.9743 Karnataka International Journal of Agricultural Technology 2020. 67 67

68. Input Image Perception of Weed Detection System Generated Weed Map 68

69. Paddy (Oryza sativa L.) Crop Acreage Estimation using Geo-spatial Technologies in Shorapur Taluk of Yadgir District Desai et al . • To Estimate acreage of Paddy crop in Shorapur. • Satellite utilised – RESOURCESAT-1 & Landsat – 8 • Sensors Used – LISS-III of RESOURCESAT-1. • Location Shorapur, Yadgir, Karnataka, India. • GIS software's - ERDAS IMAGINE 2014 and Arc GIS 9.0 • Proximal Sensors – NDVI meter, SPAD meter, infrared gun, Canopy analyzer. Karnataka Research Frontiers in Precision Agriculture 69

70. Pre and Post Processed Satellite Images 70 Images From Landsat - 8 Images From LISS-III

71. Supervised Classification RESOURCESAT LISS-III, January 2017 Image and Unsupervised Classification of Landsat-8, April 2017 for Accuracy Assessment 71

72. Area Covered under Paddy as Observed from Classified NDVI Values of LISS-III January, 2017 Sl. No NDVI Values -0.100 – 0.199 0.199 – 0.254 0.254 – 0.315 0.315 – 0.380 0.380 – 0.454 0.454 – 0.722 Total area Area (ha) 1644.20 5734.79 7542.80 10632.47 3151.80 124.68 1 2 3 4 5 6 28830.74 NDVI values of 0.254 to 0.722 covers paddy. (19397.55 ha covers paddy) Comparison of Remote Sensing and DOA Acreage Estimates Remote Sensing (ha) DOA (ha) RD (%) 28830.74 23900.34 +17.10 72

73. Automated irrigation systems for wheat and tomato crops in arid regions Ghobari et al . • To Investigate how electronic controllers in irrigation systems effectively save water. • Location - Experimental Farm of the College of Food and Agriculture Sciences, Riyadh. • Automated Irrigation System - Hunter Pro-C (ET System). • He studied effect of AIS on Wheat and Tomato Water use efficiencies. WATER SA SAUDI ARABIA 73

74. Architecture of Irrigation Systems (AIS & CIS) 74

75. Effects of the AIS and CIS on wheat water use efficiencies Irrigation treatments Etc AIW WUE IWUE (mm) m -3 h -1 (mm) m -3 h -1 (kgm -3 ) (kgm -3 ) 2013-14 growing season AIS 400.06 4000.56 453.29 4532.90 1.27 CIS 538.25 5382.53 573.51 5735.06 1.13 2014-15 growing season 1.12 1.06 AIS 363.94 3639.43 364.43 4362.30 1.64 CIS 514.31 5143.07 627.17 6271.75 1.47 1.37 1.21 SAUDI ARABIA WATER SA 75 75

76. Effects of the AIS and CIS on Tomato water use efficiencies Irrigation treatments Etc AIW WUE IWUE (mm) m -3 h -1 (mm) m -3 h -1 (kgm -3 ) (kgm -3 ) 2013-14 growing season 5947.60 7961.50 AIS 520.30 5203 594.76 CIS 653.70 6537 796.15 7.50 5.72 6.56 4.70 2014-15 growing season AIS 560.50 5605 633.76 6337.6 7.15 CIS 689.20 6891.80 854.79 8547.9 5.33 6.32 4.30 SAUDI ARABIA WATER SA 76 76

77. Conclusion Digital Agricultural technology is the key to address all Digital technologies provide Better, Faster, Quality products/services which increase small holder farmer productivity, Poverty reduction, Nutrition, Education and Income. Compared to other mutagenesis, this technique is efficient in creating widespread mutation but often leads to unpredictable phenotype.

78. 78