Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

Jeff Bradshaw, Founder, Adaptris

291 views

Published on

Jeff Bradshaw is the founder of Adaptris and Group CTO of Adaptris/F4F/DBT within Reed Business Information. He has spent his career integrating data wherever it resides and in-flight across a number of industries including Agriculture, Airlines, Telecommunications, Healthcare, Government and Finance.
Jeff has worked with and contributed to a number of international standards bodies and continues to work with large enterprises to help them extract value from their data silos and share data seamlessly with their trading partners to achieve business benefit. For the last few years Jeff has been focusing on Big Data and how to gather that across a wide range of sources to help gain insight into the agri-food supply chain.

Abstract Summary:

Precision agriculture – Predicting outcomes for farmers using machine learning to help feed the world:
Agricultural data is vast, often unstructured and includes many challenges when working with legacy farm systems on premise in rural areas. For instance, traditional farm equipment such as tractors, sprayers, and combines aren’t often from the same vendor, and it’s complex moving data between them. This is further complicated with the vast array of other systems used by our farmers. Furthermore, the number of sensors in agriculture is astonishing, whether it is sensors that measure the gait of the cow walking into the dairy parlor, or chickens that are pecking. All this data needs to turn into usable information on a global scale to improve the yields farmers get and provide greater visibility into what’s going on both in and out of the farm. In this session, a case study will be shared on how data was collected, normalized and analyzed leveraging the open source HPCC Systems platform from remote Farm Management Systems (used by farmers to manage their farms), and when merged with weather data, soil data and actual machinery data, the analyzed predictions is used to feed Agronomists and Crop Protection/Seed Manufacturers to get recommendations back. The goal is to deliver a precision agriculture solution, helping farmers increase their yield, which then helps feed the growing population of the world.

Published in: Technology
  • Be the first to comment

Jeff Bradshaw, Founder, Adaptris

  1. 1. Using big data to help feed the world Private and confidential
  2. 2. Who are Proagrica Proagrica, the global agricultural division of RELX, drives growth and improves efficiency by delivering high-value insight and data, critical tools and advanced technology solutions
  3. 3. Who are Proagrica Proagrica, the global agricultural division of RELX, drives growth and improves efficiency by delivering high-value insight and data, critical tools and advanced technology solutions
  4. 4. Agriculture is at the Centre of Global Change
  5. 5. How could data help?
  6. 6. Precision Agri: Our Data Landscape / Assets Vast amounts of data spread across the Agricultural landscape. Proagrica is consolidating, organising and enhancing this data to help drive value across the entire industry, from the farm gate all the way to the super market shelf Farm Machinery Every piece of equipment on the farm is now generating data and wants to be precise Agronomist Providing farm advice, shape files and data to farmers Manufacturers & Distributors Adaptris manages supply chain connectivity between MFRS and their Distributors Weather Data Global current and historical weather and soil moisture data at sub-field level Farm Management Information Systems (FMIS) A wide spectrum of tools used by Farmers all generating data Satellites / Drones Ability to identify yield and crop issues from space / drones Sensors Ground and animal sensors measuring everything from animal fertility to soil moisture Soil Global soil type horizons
  7. 7. An overview of the approach
  8. 8. ProAgrica HPCC Platform
  9. 9. What does it deliver? ▶ Global insight through fully integrated ESB data, Data As A Service and a range of Analytics tools ▶ An agile, scalable, resilient and secure platform that can consume data from any source, consolidate, enrich and expose global agricultural data from everything soil to animals and all the way to satellites ▶ Precision Ag covering the full Ag value chain from Mfr, through Agronomist, CO-OP, Farmer and Distributor ▶ A range of Analytics solutions focused on Pesticides, Herbicides, Fertilizers, Seeds, Cattle, Milk, etc. that provide insight at market, region, farm, field and sub- field levels ▶ Enabling the industry to increase yield and profitability whilst reducing inputs and improving environmental impact
  10. 10. Patterns of OSR using Principal Component Analysis ▶ Why was the 2016 harvest in the UK so awful? ▶ What correlates to higher yields? ▶ How effective are pesticides? ▶ Are hybrids better?
  11. 11. A few gotchas…….. ▶ Correlation doesn’t equal causation…….. ▶ Some unusal yields ………. Maximum yield: 36,784,867 kg/ha
  12. 12. 570 million Farms, 25 million Tractors, 50 billion chickens, 1 billion sheep, 1 billion pigs, 80 million turkeys, 1.5 billion cows in the world with 100% of them with passports in the UK vs 36% of the US population…. …and Big Brother / Data is here, for Animals at least as they are all being monitored / reporting data
  13. 13. A few gotchas…….. ▶ Growers aren’t very skilled at data entry Planted Seed Variety DK Excaliber DK Excalibur Excalibur + Coating Excalibur Stock Excalibur and Catana Rolled OSR + 15:10:28 Planted Seed Variety Excalibur Excalibur Excalibur Excalibur Other Other Other
  14. 14. How has yield varied over the last 10 years? ▶ Average yield is 3,766 kg/ha
  15. 15. The spread in yield 3,750 kg/ha 5,250 kg/ha 2,250 kg/ha ▶ Most growers are within 1,496 kg/ha of the average
  16. 16. …. But this isn’t constant!
  17. 17. Could it be related to variety choice?
  18. 18. Popularity of hyrid varieties by location
  19. 19. Variety trait differences by location
  20. 20. How do we visualise the data? ▶ Over 150 pairs of variables to investigate ▶ No idea what is linked before we start……
  21. 21. Agriculture is at the Centre of Global Change
  22. 22. How about now?
  23. 23. How to read the graphs Two variables that are high at the same time
  24. 24. How to read the graphs Two variables that are high at opposite times
  25. 25. How to read the graphs Two variables that have nothing to do with each other
  26. 26. The market for OSR varieties
  27. 27. What causes variation in yield – it’s a similar story ▶ Degree days ▶ Fertiliser treatments ▶ Fungicide treatments ▶ Insecticide treatments ▶ Month of first insecticide application ▶ High wind events ▶ Temperatures ▶ Average rainfall ▶ Coldest week ▶ Total radiation ▶ Wettest weeks ▶ Driest weeks ▶ Soil moisture ▶ Precipitation ▶ Lattitude & Longitude ▶ Soil content
  28. 28. How could data help?
  29. 29. The answers……….. ▶ Why was the 2016 harvest in the UK so awful? ▶ Wet spring and/or dry winter ▶ What correlates to higher yields? ▶ Warm spring, wet winters and proper pesticide application ▶ How effective are pesticides? ▶ Yes for fungicide, “perhaps” for insecticide ▶ Are hybrids better? ▶ Not really
  30. 30. Take home messages ▶ If you’re a farmer ▶ There are probably too many varieties of OSR in the world! ▶ OSR does better in wet springs and warm winters ▶ If you’re in to analytics ▶ Working with big data is a lot of fun ▶ Dimension reduction is great for picking out correlations in complex data
  31. 31. Over 3,600 integrated agricultural customers

×