Data Products & Problems in Agriculture
- 1. Open Data for Agriculture Intro to Big Data 29/11/2013 Athens, Greece Joint offering by Supported by EU projects
- 2. Data Products & Problems in Agriculture Charalampos Thanopoulos Agro-Know Technologies
- 3. Intro • This presentation aims to provide information about the open data in agriculture, examples of agricultural data problems and how these can be described with the drivetrain approach Slide 3 of 63
- 4. Objectives This presentation aims to provide basic information on data-related issues in agriculture • Provide an intro to agricultural sciences • Describe the use of open data in agriculture • Define the agricultural data formats • Provide examples of agricultural data problems Slide 4 of 63
- 5. Structure • The presentation consists of the following sections: – Intro to agriculture & agricultural sciences – Intro to agricultural market & potential – Intro to Open Data in agriculture – Review of agricultural data problems • 4 agricultural case studies Slide 5 of 63
- 6. Source: http://www.agricorner.com/shareholder-demands-to-shape-modern-agriculture/ INTRO TO AGRICULTURE & AGRICULTURAL SCIENCES
- 7. About agriculture Definition 1: “the science or practice of farming, including cultivation of the soil for the growing of crops and the rearing of animals to provide food, wool, and other products” Definition 2: “the set of activities that transform the environment for the production of animals and plants for human use. Agriculture concerns techniques, including the application of agronomic research” Slide 7 of 63
- 8. About agricultural sciences • Agricultural science: a broad multidisciplinary field encompassing the parts of exact, natural, economic and social sciences that are used in the practice and understanding of agriculture. – Veterinary science, but not animal science, is often excluded from the definition Slide 8 of 63
- 9. Source: http://www.archives.gov.on.ca/en/explore/online/agriculture/big/big_12_farmers_market.aspx INTRO TO AGRICULTURAL MARKET & POTENTIAL
- 10. a huge market, globally Food & Agricultural commodities production, http://faostat.fao.org Slide 10 of 63
- 11. some figures • Food - Gross Production Value globally in 2011: $2,318,966,621 • Agriculture - Gross Production Value globally in 2011: $2,405,001,443 • Investment in agriculture - Gross Capital Stock globally: $5,356,830,000 … they are big Slide 11 of 63
- 12. examples of EU production in 2010 Source: Eurostat Slide 12 of 63
- 13. how many businesses? Slide 13 of 63
- 14. INTRO TO OPEN DATA IN AGRICULTURE
- 15. Definition of Open Data “Open data is data that can be freely used, reused and redistributed by anyone subject only, at most, to the requirement to attribute and sharealike” Slide 15 of 63
- 16. why open data? • Open data, especially open government data, is a tremendous resource that is as yet largely untapped – individuals and organisations collect broad range of different types of data to perform their tasks • Government is particularly significant in this respect – quantity and centrality of data it collects – most is public data by law, could be made open and made available for others to use Slide 16 of 63
- 17. closed data Examples: …always bad? Slide 17 of 63
- 18. open data for businesses “new businesses and new business models are beginning to emerge: Suppliers, aggregators, developers, enrichers and enablers” “key link in the value chain for open data is the consumer…direct relevance to the choices individuals make as part of their day-to-day lives” Slide 18 of 63
- 19. Open Data in agriculture: a political priority “How Open Data can be harnessed to help meet the challenge of sustainably feeding nine billion people by 2050” Slide 19 of 63
- 20. Agriculture is about to experience a “growth shock” in order to cover the exponentially increasing food needs of the global population • Key facts about agricultural trends • All demographic and food demand projections suggest that, by 2050, the planet will face severe food crises due to our inability to meet agricultural demand – by 2050: – 9.3 billion global population, 34% higher than today – 70% of the world’s population will be urban, compared to 49% today – food production (net of food used for biofuels) must increase by 70% • According to these projections, and in order to achieve the forecasted food levels by 2050, a total investment of USD 83 billion per annum will be required Slide 20 of 63
- 21. One of the most promising routes to agriculture modernisation is the provision of Open Data to all interested parties Open data in agriculture • In an era of Big Data, one of the most promising routes to bootstrap innovation in agriculture is by the use of Open Data: – e.g. provisioning, maintaining, enriching with relevant metadata, making openly available a vast amount of information • The use and wide dissemination of these data sets is strongly advocated by a number of global and national policy makers such as: – – – – The New Alliance for Food Security and Nutrition G-8 initiative Food & Agriculture Organization of the UN DEFRA & DFID in UK USDA & USAID in the US Slide 21 of 63
- 22. examples of variety & diversity Slide 22 of 63
- 23. data sets Slide 23 of 63
- 24. maps Slide 24 of 63
- 25. photos Slide 25 of 63
- 26. databases Slide 26 of 63
- 27. Agricultural data formats • publications, theses, reports, other grey literature • educational material and content, courseware • primary data, such as measurements & observations – structured, e.g. datasets as tables – digitized, e.g. images, videos • secondary data, such as processed elaborations – e.g. dendrograms, pie charts, models • provenance information, incl. authors, their organizations and projects • experimental protocols & methods • social data, tags, ratings, etc. Slide 27 of 63
- 28. .. examples of Big Data in agriculture Slide 28 of 63
- 29. REVIEW OF AGRICULTURAL DATA PROBLEMS
- 30. CASE STUDY 1A: PRODUCING HIGHLY NUTRITIOUS GREEN VEGETABLES
- 31. Radiki.com • food scouter collecting edible plants like of wild Taraxacum officinale W. http://en.wikipedia.org/wiki/Ta raxacumbusiness • opportunity: gourmet restaurants are looking for such highly nutritious & appreciated greens Slide 31 of 63
- 32. data problems Slide 32 of 63
- 33. data problems Dried export in US Slide 33 of 63
- 34. Issues identified 1. finding right & relevant only legislation 2. finding right, natural drying techniques for these plants 3. finding scientific info on proper packaging Slide 34 of 63
- 35. 1: finding right & relevant only legislation Slide 35 of 63
- 36. Slide 36 of 63
- 37. Slide 37 of 63
- 38. 2: finding right, natural drying techniques for these plants Slide 38 of 63
- 39. Slide 39 of 63
- 40. Slide 40 of 63
- 41. 3: finding scientific info on proper packaging Slide 41 of 63
- 42. Slide 42 of 63
- 43. Slide 43 of 63
- 44. The Drivetrain approach • Enrich existing bibliographic information • Link bibliographic information with related Web resources • Allow users to access the full-text of a publication and all the information the Web knows about a specific research area in the agricultural domain • Users’ requirements • Linked data infrastructure • Selection of available data sources • Existing bibliographic information • Available additional data sources • Develop algorithms for linking data from various data sources (i.e. DBPedia, World Bank etc) using a linked-data approach involving AGROVOC Slide 44 of 63
- 45. CASE STUDY 1B: AGRO-FOOD COOPERATIVE
- 46. Stevia Hellas • Christos Stamatis – (CEO of the Stevia Coop) • Crowd funding model – 250 growers – first Greek Stevia Slide 46 of 63
- 47. Slide 47 of 63
- 48. Issues identified 1. Strengthen the knowledge about food safety 2. Where to set up the adding value processing unit 3. Organic portion of the coops cultivation 4. Define product price Slide 48 of 63
- 49. Problem 1: Strengthen the knowledge about food safety • The coop needs to strengthen the knowledge in Food Safety and to follow the standards • Needs to have access to a portal that provides access to such information • It could be extended to cover also other food products and domains • What kind of open data are needed – OER from Educational Institutions – Open courses – Data from the ministry on which are the food standards – Data from FAO e.g. FAO codex Slide 49 of 63
- 50. How such service can help • Benefits for a stakeholder – personnel that you need to ensure that you will follow the food safety standards – find the food safety standards that should be followed – define relevant training for your employees Slide 50 of 63
- 51. Problem 2: Where to set up the adding value processing unit • The cooperative would like to have a product on the shelf • Valuable information – available energy resources – shipping roots – availability of land Slide 51 of 63
- 52. Problem 3: Organic portion of the coops cultivation • A cooperative would like to invest more in organic cultivation • Valuable information – market needs in organic products and stevia specifically – prices of the last years for conventional products – climate conditions – soil quality maps Slide 52 of 63
- 53. Problem 4: Define product price • Estimate the price for coops’ product • Valuable information – sugar prices – international prices of stevia – meteo data – import prices in Greece Slide 53 of 63
- 54. CASE STUDY 2A: PRODUCE TRAINING MATERIAL FOR NATURAL PRODUCTS
- 55. APIVITA • creating natural effective and holistic products since 1979 to promote health & beauty – Lately involved in the agricultural education and training – Producing training material, creating courses etc. related to the ingredients of APIVITA natural products Slide 55 of 63
- 56. APIVITA finding OER material for natural products Slide 56 of 63
- 57. The Drivetrain approach Creating additional services for APIVITA web site • Existing (generic) user requirements • Existing appropriate functionalities • Data models available to support the functionalities of the new web site • APIVITA-owned content • External Open Educational Resources with related content • Requirements from the expected users of the APIVITA micro-site • Feedback (rating/reviews) of available resources from the APIVITA users Develop algorithms for • Filtering results from the linked data stes, • Fine-tuning content based on the feedback received • Revising user interface/facets based on new requirements Slide 57 of 63
- 58. CASE STUDY 2B: ORGANIZE TRAINING MATERIAL FOR ORGANIC PRODUCTS
- 59. Association of organic products • SEAE: Sociedad Española de Agricultura Ecologica • A non-profit organization promoting organic agriculture in Spain • Organizes training events and Conferences/Workshops – Produces training material and collects publications from Conference submissions Slide 59 of 63
- 60. Issues identified • Issue: – Material produced not described with metadata – Only available (partially) in SEAE website – All information only available in Spanish Slide 60 of 63
- 61. Slide 61 of 63
- 62. The Drivetrain approach Create a collection of multilingual metadata for describing resources and publish metadata in other websites • Multilingual metadata authoring tool (e.g. AgLR) • Automatic translation tools • Agricultural educational portals • Training material produced by SEAE • Conference submissions, publications & proceedings • Develop algorithms for the selection of content for the SEAE collection • Publication of multilingual metadata in other OER web portals Slide 62 of 63
- 63. Thank you! Charalampos Thanopoulos Agro-Know Technologies cthanopoulos@agroknow.gr