big data: discovering the value of an underutilized asset...400 600 800 1000 1200 1400 1600 1800...

!!

Big Data: Discovering the Value!of an Underutilized Asset!

No-Till Conference!

Cincinnati, Ohio!Jan. 16, 2015!

S.A. Shearer

Food, Agricultural and Biological Engineering

Presentation Ground Rules!•  I will talk about the future… no guarantees that I’m

right (or wrong)!!•  No intent to endorse one product or technology over

another.!•  I will connect observations (mine and others) to suggest

how agriculture will change.!•  I’ve borrowed heavily from materials available via the

internet, and have tried my best to credit the respective individuals.!

•  Scarlet and Gray are the primary colors of the presentation -- observation of who pays my salary. !

AgState Task Force!

digital agriculture – family of activities related to farming that includes precision agriculture, prescription agriculture and enterprise agriculture; and depends on the collection, use, coordination, and analysis of data from a multiplicity of sources with the goal of optimizing productivity, profitability and sustainability of farming operations.!

Technologies that will shape the future of agriculture…!

Google Glass?!

http://www.agriculture.com/farm-management/technology/google-glass-is-on-its-way-to-farm_322-sl32330!

Topcon Positioning Systems IP-S2 HD!

http://www.topconpositioning.com/products/mobile-mapping!

http://www.ibm.com/smarterplanet/us/en/ibmwatson/!

Google Car!

http://www.extremetech.com/extreme/147940-google-self-driving-cars-in-3-5-years-feds-not-so-fast!

Market forces that will shape the future of agriculture…!

http://foodbabe.com/!

Reducing Fertilizer Use in Agriculture. Walmart is requiring suppliers who use commodity grains, such as corn, wheat and soy in their products, to develop a fertilizer optimization plan that outlines clear goals to improve performance based on Index research. Through this program, the company and its suppliers have the potential to reduce fertilizer use on 14 million acres of farmland in the U.S. by 2020.!

Current precision ag technologies…!

What is Big Data?!

NSF recently referred to Big Data as large, diverse, complex, longitudinal, and/or distributed data sets generated from instruments, sensors, Internet transactions, email, video, click streams, and/or all other digital sources.!

What is the value of “Big Data”!if we don’t produce"

actionable information?!

What’s driving planter development?!

Precision Planting Sensing/Control !

http://precisionagsystems.com/!

Kinze Multi-Hybrid!

www.agrinews-pubs.com!

http://www.cleanseedcapital.com/index.html!

CleanSeed CX-6 Smart Seeder!

Controlling Canopy Architecture"Torres, Vossenkemper, Raun and Taylor (Oklahoma State University)!

OSU/Beck’s Field Investigations!

OSU/Beck’s Field Investigations!

Telematics offerings…!

Fuel Use Rate Distributions!

0!

1000!

2000!

3000!

4000!

5000!

6000!

0! 2! 4! 6! 8! 10!

12!

14!

16!

18!

20!

22!

24!

26!

28!

30!

32!

34!

36!

38!

40!

42!

44!

Freq

uenc

y!

Fuel Use Rate (L/h)!

Planting!

0!

500!

1000!

1500!

2000!

2500!

3000!

3500!

4000!

4500!

0! 3! 6! 9! 12!

15!

18!

21!

24!

27!

30!

33!

36!

39!

42!

45!

48!

51!

54!

57!

60!

63!

66!

69!

72!

75!

78!

其他!

Freq

uenc

y!

Fuel Use Rate (L/h)!

NH3 Application!

How big is too big?!

http://www.bauerbuiltmfg.com/db-series-planters.html!

29

Spray Application Accuracy!

(Fulton, et al.)!

Trends in ballasted GVW?!

Now 685 Hp (80,000 lb.)?!

Class%X%–%565%hp%Class%XI%–%629%hp%Class%XII%–%693%hp%Class%XIII%–%757%hp%

Combine Classes?!

http://www.youtube.com/watch?v=WUXY4hQDtpI!

Machine! ! !

Trafficked Area!(%) ! !

Yield Reduction Prediction!(200 bu/ac No-Till Corn Base)!Normal! Wet!

Trafficked Yield (bu/

ac)!

Field Avg. Yield (bu/

ac)!

Trafficked Yield (bu/

ac)!

Field Avg. Yield!

(bu/ac)!Grain Cart!

(Balzer 2000)! 14.0! 175! 196! 148! 193!Planter, 36 Row!(Case IH 1260)! 6.7! 190! 199! 171! 198!

Class IX Combine, 16 Row!(Deere S690)! 17.1! 176! 196! 150! 192!

Self-Propelled Sprayer!(RoGator RG1300)! 4.5! 198! 200! 182! 199!Manure Application!

(Houle 48-8D)! 44.7! 189! 195! 168! 186!

Compaction Penalty!

Data driven decisions… the future of digital agriculture!!

Machine Data Generation!

•  As-Applied Files (.shp)!–  Spraying [0.3 MB/ac]!–  NH3 application [4.3 MB/ac]!–  Planting [5.5 MB/ac]!

•  Yield Data [4.3 MB/ac]!•  Prescription Files [0.01 MB/ac]!•  Soil/Fertility Data [0.6 MB/ac]!•  Total [0.5 KB/plant]!

Remote Sensing Data Generation!

•  24 bits per pixel!•  2.5 cm/pixel!•  17.2 MB/ac of image data!

www.trimble.com !

www.sensefly.com!

FAA Grants UAS Exemptions "!

Companies receive commercial exemptions for aerial surveying, construction site monitoring and oil rig flare stack inspections (Dec. 10, 2014).!

•  Trimble Navigation Limited!•  VDOS Global, LLC!•  Clayco, Inc.!•  Woolpert, Inc.!

High Resolution Imagery!

Woolpert, Dayton, OH!

Stand Counts via Remote Sensing!

Herbicide Carryover!

N Application Errors!

Compaction Study!

43

Compaction Study!

44

Compaction Study!

Hybrid Differences!

Lightweight Hyperspectral Cameras !

Rikola Ltd 300 g Hyperspectral Camera!500-900 nm (10 nm resolution)!

Headwall Photonics Micro-Hyperspec (1.8 lb.)!400-1000 nm (324 bands) !

!

Hyperspectral Reflectance - Corn!

400 600 800 1000 1200 1400 1600 1800 2000 2200 24000

0.05

0.1

0.15

0.2

0.25

0.3

0.35

0.4

0.45

0.5

Wavelength (nm)

Refle

ctan

ce

Mean of all Plants for each Corn Hybrid

P1 MeanP2 MeanP3 MeanP4 MeanP5 MeanP6 MeanP7 MeanP8 MeanP9 MeanP10 MeanP11 MeanP12 MeanP13 MeanP14 MeanP15 MeanP16 Mean

400 600 800 1000 1200 1400 1600 1800 2000 2200 24000

0.05

0.1

0.15

0.2

0.25

0.3

0.35

0.4

0.45

0.5

Wavelength (nm)

Refle

ctan

ce

Mean of all Plants for each Corn Hybrid

P1 MeanP2 MeanP3 MeanP4 MeanP5 MeanP6 MeanP7 MeanP8 MeanP9 MeanP10 MeanP11 MeanP12 MeanP13 MeanP14 MeanP15 MeanP16 Mean

400 600 800 1000 1200 1400 1600 1800 2000 2200 24000

0.05

0.1

0.15

0.2

0.25

0.3

0.35

0.4

0.45

0.5

Wavelength (nm)

Refle

ctan

ce

Mean of all Plants for each Corn Hybrid

P1 MeanP2 MeanP3 MeanP4 MeanP5 MeanP6 MeanP7 MeanP8 MeanP9 MeanP10 MeanP11 MeanP12 MeanP13 MeanP14 MeanP15 MeanP16 Mean

400 600 800 1000 1200 1400 1600 1800 2000 2200 24000

0.05

0.1

0.15

0.2

0.25

0.3

0.35

0.4

0.45

0.5

Wavelength (nm)

Refle

ctan

ce

Mean of all Plants for each Corn Hybrid

P1 MeanP2 MeanP3 MeanP4 MeanP5 MeanP6 MeanP7 MeanP8 MeanP9 MeanP10 MeanP11 MeanP12 MeanP13 MeanP14 MeanP15 MeanP16 Mean

3rd Round of Hyperspectral Measurements!

1st Round of Hyperspectral Measurements!

4th Round of Hyperspectral Measurements!

2nd Round of Hyperspectral Measurements!

!

400 600 800 1000 1200 1400 1600 1800 2000 2200 24000

0.1

0.2

0.3

0.4

0.5

0.6

Wavelength (nm)

Refle

ctan

ce

Mean of all Tassels for each Corn Hybrid

P1 MeanP2 MeanP3 MeanP4 MeanP5 MeanP6 MeanP7 MeanP8 MeanP9 MeanP10 MeanP11 MeanP12 MeanP13 MeanP14 MeanP15 MeanP16 Mean

Hyperspectral Measurements of Tassels!

400 600 800 1000 1200 1400 1600 1800 2000 2200 24000

0.1

0.2

0.3

0.4

0.5

0.6

Wavelength (nm)

Refle

ctan

ce

Mean of all Silk for each Corn Hybrid

P1 MeanP2 MeanP3 MeanP4 MeanP5 MeanP6 MeanP7 MeanP8 MeanP9 MeanP10 MeanP11 MeanP12 MeanP13 MeanP14 MeanP15 MeanP16 Mean

Hyperspectral Measurements of Silk!

Hyperspectral Reflectance - Corn!

In-Field Phenotyping!

http://vigir.missouri.edu/targetgeolocation.htm!http://www.plant-phenomics.ac.uk/en/!

http://newsroom.hwtrek.com/?p=626!

Continuing trend toward automation….!

Deere MachineSync!AGCO GuideConnect!

http://www.farms.com/FarmsPages/ChatDeshBoard/ChatThreadView!

http://www.deere.com!

Current Products!

Autonomous Tractor vs. Baxter?!

http://www.rethinkrobotics.com/index.php/products/baxter/!

Future of Agriculture?!

Tractor of the future…!

•  Technical obsolescence and mechanical life will coincide – machine life of 6-7 cropping seasons.!

•  Fully (or supervised) autonomous tractors will be 50-60 hp and under 8,000 lb. GVW.!

•  Tractors will be reconfigurable for ground clearance and track width.!

•  Tractors will utilize spark ignition engine – multi-fuel (gasoline, ethanol and CNG) and reduced emissions.!

•  Automation (sensor-rich environment) will accelerate data generation. !

Agricultural Data Warehouses

Existing Data Warehouses!

•  Monsanto/Climate Corp. - FieldScripts!•  John Deere – MyJohnDeere!•  DuPont’s - Pioneer Field360!•  Cargill’s - NextField DataRx!•  Beck’s - FARMserver!•  FarmersEdge – PrecisionEdge !

Producer Concerns over Data!

•  Privacy and security!•  Limited access to their data – contained in

proprietary message (CAN) formats!•  Loss of control once data is uploaded to the

cloud – uncertain of how data will be used !•  Aggregators of producer data will use it to

control markets!•  Unlikely to share in value of data!•  Government access !

Basic Scenarios!

Wireless Cloud-Based Platform

Manual Transfer

Emerging Scenario!

API!

Ag Tech!

API!

Producer-Centric Ag Data Warehouse

(Third Party)

Standardization Cleaning

Certification Anonymization

Aggregation

ADW Value to Producers!

•  Producers will be in control of their data!•  Ag Data Warehouse (ADW) will become the

trusted, third party manager of data!•  Scalable – serves small and large farmers alike !•  APIs will provide access to proprietary CAN

messages!•  Summary data will be made available for

benchmarking!•  More opportunities to realize value !•  Accelerated data aggregation!•  FOIA not applicable!

ADW Value to Agri-Business!

•  Acceleration of data aggregation!•  Certification process will improve overall data

quality!•  Ability to share development costs – reduced

cost of providing data services to customers!•  Improved services for clients!•  Reduced liability for data security!•  Reduced compliance costs!

Questions?!