1 / 60

Helping the World’s Farmers Adapt to Climate Change

Learn about TWI weather insurance aiding farmers in adapting to climate change with advanced simulations and technologies.

efix
Download Presentation

Helping the World’s Farmers Adapt to Climate Change

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Helping the World’s Farmers Adapt to Climate Change Strata Conference Oct 2012 Siraj Khaliq, CTO, The Climate Corporation

  2. Fritchton, IN – late summer, 2012

  3. Louisville, IL

  4. Wichita, KA

  5. Click to edit Master title style 1956 2012 1988 Worst US Droughts in the Last Fifty Years • Click to edit Master text styles • Second level • Third level • Fourth level • Fifth level

  6. Click to edit Master title style -16% 2012 Estimated Corn Yield (USDA)

  7. Click to edit Master title style +6% World food prices month-on-month change in July 2012 (UNFAO)

  8. Farm Economics • Large capital outlays at start of season (April) • Seed, equipment, pesticide, and land • Revenue comes in at harvest • 1-2 years of revenue shortfall could be catastrophic • Futures help with price volatility, not weather

  9. A real-life example Farmer Rich Vernon talks to NPR's David Schaper (audio)

  10. This is set to continue

  11. Click to edit Master title style

  12. Click to edit Master title style Our Mission To help all the world's people & businesses manage and adapt to climate change

  13. Evaluating Markets

  14. Click to edit Master title style $4.2 Trillion 2012 Estimated Corn Yield (USDA)

  15. Total Weather Insurance (TWI)

  16. TWI Demo

  17. HOW?

  18. Policy Weather Data Outcome

  19. Structure Modeled Outcomes Weather Simulations

  20. How does weather impact crop yield? Structure

  21. Varies based on many inputs: • Temperature • Precipitation • Soil type • Topography • Farming practices • Crop varietal Structure

  22. Agronomically deduced candidates • Model at large scale • Every farm in the US (20M) Structure

  23. Structure

  24. Structure Modeled Outcomes Weather Simulations

  25. What weather dowe expect? Weather Simulations

  26. 1M locations (2.5mi x 2.5mi grid) 10k scenarios/location going 2 years out 2 measurements Weather Simulations 60Tb of data per simulation set every couple of weeks

  27. Weather Simulations

  28. 2.5 x 2.5 Square Miles

  29. Expensive computation • Parallelizing hard due to correlations • Would take 80+ years on one fast modern server-class machine • We need to generate these within days Weather Simulations

  30. Soil Moisture Modeling What's the soil moisture at farm X?

  31. Soil Moisture Modeling soil type, weather, topography, crop

  32. Evolution of Our Technology

  33. Java frontend MySQL Pricing Server (Rserve) 2007 • 400 stations • All data in MySQL • Pricing servers (Rserve) • Java-based webapp

  34. Java frontend MySQL Pricing Server (Rserve) Disk 2008 • 2000 stations • Weather data now on disk • Versioning hard • Java-R bridge messy

  35. Java frontend MySQL Pricing Server (java) Simulation Service Weather data Service 2009-2010 • 22,000 locations • Rserve replaced by java • Simulations & S3/SimpleDB • Model gen in Hadoop • Moved fully to EC2 Sim gen (hadoop) SimpleDB / S3 SimpleDB / S3

  36. Rails frontend MySQL Pricing Server (java) Marty (HBase) Geo data store S3 Sim gen (cascalog) 2011 – today • 1,000,000 locations • Own big geo-data store • Many more hadoop jobs • Eliminated SimpleDB Soil moisture dataset gen (cascalog) Other hadoop jobs Structures gen (cascalog)

  37. MapReduce at TCC • Python (Hadoop streaming) • Some native java • Most are higher-level frameworks

  38. Big Wins • Cascalog/Clojure • EC2 Spot Instances • “NoSQL”

  39. Big Win #1 - Cascalog (defn weather-map-q   "Creates a Cascalog query to extract individual measurement values of   ObservationSet data and produces tuples of [date JSON-encoded map], in   which each JSON-encoded map is keyed by station-id"   [stations interval measurement sources start end nostra]   (<- [?date ?json-aggregated-values] ; from hfs-textline     (stations ?station-id)     (fetch-obs-for-station [interval measurement sources start end nostra]                            ?station-id :> ?obs)     (extract-values-by-date ?obs :> ?date ?value)     (aggregate-values ?value :> ?aggregated-values)     (json/generate-string ?aggregated-values :> ?json-aggregated-values)))

  40. Big Win #1 - Cascalog • Easily composable workflows • Can unit test Hadoop flows • Quick iteration

  41. Big Win #2 – EC2 Spot Instances • Good fit to our compute approach • Can be very cheap • Good availability

  42. MapReduce at TCC

More Related