Advancement of Prescriptive Ag and Big Data John Fulton 2016 No- - - PowerPoint PPT Presentation

Advancement of Prescriptive Ag and Big Data

John Fulton

2016 No- Till Oklahoma Conference, Stillwater, OK

2015 2015 Fa Farm Evalua aluations tions & Decisions Decisions

‐ Stand evaluation (wet spring ‐‐‐ replant?) ‐ Soil Compaction (pinch rows, machine paths) ‐ N status in corn (Side‐dress: YES / NO) ‐ Disease (Fungicide: YES / NO) ‐ Hybrid selection and placement

Investment cost versus paycheck… $2/ac to $35/ac

Food, Agricultural and Biological Engineering

Precision Ag Evolutionary Phases

• The Start ‐ Early Pioneers ‐ Mid‐1990’s
• Technology Settlers ‐ Late‐1990’s and early 2000’s
• Efficiency – Boom of Mid‐ to late‐2000’s
• Automation ‐ 2010
• Connectivity ‐ 2012
• Digital Agriculture (decision agriculture) ‐ Today & Tomorrow

Has been a bit painful over this stretch but has brought opportunities.

Food, Agricultural and Biological Engineering

Precision Ag Evolutionary Phases

Automation & Collection ‐ 2010

‐ Precision ag is main stream ‐ Precision sampling along VR fertilizer and seeding standard services ‐ Grid versus Zone??? ‐ Even larger equipment with embedded technologies to automate operation ‐ iPADs ‐ The Cloud ‐ Incompatibility of hardware and software ‐ Inputs tied to Precision Ag services ‐ Sustainability discussions

Food, Agricultural and Biological Engineering

Precision Ag Evolutionary Phases

Connectivity ‐ 2012

‐ Wireless and telemetry ‐ Smartphones and tablets ‐ APPs ‐ Cloud technology on the full radar of agriculture ‐ Data, data, data ‐‐‐‐‐ BIG DATA…

• Infusion of VC funding to data companies
• Decision support tools…One‐stop Shop
• CAN sniffers
• Agronomic & Machine data
• Benchmarking

‐ Sustainability calculators ‐ Incompatibility of hardware and software ‐ Environmental concerns…

Food, Agricultural and Biological Engineering

Knuth Farms

Precision Ag Evolutionary Phases

Today & Tomorrow ‐ Digital Agriculture

‐ Electronic drives versus mechanical and hydraulic for metering inputs (planter drives, PWM nozzles, etc.) ‐ Automating machinery…M2M, M2I ‐ Prescriptive agriculture

• Data driven decisions
• RIO?

‐ Online viewing dashboards (operational centers) ‐ Agronomic, machine and imagery data (integration into individual platforms) ‐ Merger of agronomy‐technology‐business ‐ Sustainability and Environmental Stewardship ‐ Data growing pains…Incompatibility of hardware and software

Food, Agricultural and Biological Engineering

By‐row Prescription (Rx)

• Hybrid
• Population
• Starter & pop‐up fertilizer
• Down force
• Row‐cleaner

Food, Agricultural and Biological Engineering

Rx Management

Digital Agriculture

Precision Agriculture Prescriptive Agriculture Enterprise Agriculture Big Data in Agriculture

Based on information from an Iowa AgState / Hale Group report.

Precision Ag: +70% US acres Prescriptive Ag: +15% of farms +95% of farmers will outsource data management.

Adoption

• Preseason Fertility Management

– Prescription P and K application (Precision Crop Services)

• Tillage Management

– Prescription tillage maps (AGCO; CNH)

• Multi‐Hybrids

– Prescription seeding of multi‐hybrids (Beck’s; Pioneer)

• SCN Management

– Prescription application/use of nematicides (FMC)

• In‐Season Fertility Management

– Prescription N application (DuPont Pioneer; Climate Corp)

• Irrigation Management

– Prescription Irrigation (AgSmart)

• Disease Management

– Prescription fungicide application (BASF) Producer

Da Data Ex Exchang change fo for Gr Grow

• wer

ers

Data will need to move through multiple

• rganizations and each organization will

need different data sources.

Recommendations

Food, Agricultural and Biological Engineering

Types of Data

1) Agronomic – yield, as‐applied, as‐planted, etc. 2) Machine (CAN) – engine parameters, tractor status variables, implement mode & functions

‐ CAN can also provide agronomic data

3) Production ‐ Information within home office, weather, notes, etc. 4) Remote Sensed Imagery

Food, Agricultural and Biological Engineering

Food, Agricultural and Biological Engineering

Agr Agronom

• nomic Da

Data

Yield Maps, As‐applied…

As‐Planted Data

Ma Machine Da Data

CAN messages, Health, etc.

Effective tool to evaluate operating costs and capacity ‐‐‐ FUEL USAGE, UPTIME vs. DOWNTIME, ENGINE LOAD.

Bridging Agronomic and Machine Data

Moisture Content (%) Ground Speed (mph) Fuel Usage (gallons per acre) Mean % Engine Load Mean Field Capacity (ac/hr) Hybrid A 14.8 2.8 1.71 86 10.2 Hybrid B 14.3 5.2 0.86 44 18.9

Big Data ‐ Accelerate learning

through new analytics and thereby earlier selection of favorable economic response.

BIG DATA in Agricultural Production

Refers to the use of technology and advanced analytics for processing data in a useful and timely way. Big data may significantly affect many aspects of the agricultural industry, although the full extent and nature of its eventual impacts remain uncertain.

• Public‐level big data represent records that are collected, maintained, and analyzed

through publicly funded sources.

• Private big data represent records generated at the production level and originate

with the farmer or rancher.

Source: US Congressional Research Service

Big Data does not exist today in crop production but both ag and external to ag companies are building components to enable.

MI MISSION: N:

‐‐‐‐‐‐‐‐‐‐‐‐‐‐‐‐‐‐‐‐‐‐‐‐‐‐‐‐‐‐‐‐‐‐‐‐‐‐‐‐‐‐‐‐‐‐‐‐‐‐‐‐‐‐‐‐‐‐‐‐‐‐‐‐‐‐‐‐‐‐‐‐

To organize agriculture’s information and make it universally accessible and useful.

Big Data

• Internet‐related services and products
• Founded 1998; Menlo Park, CA
• Mission: to organize the world's information and

make it universally accessible and useful.

• Revenue: $66 billion (2014)
• Net Revenue: $14.4 billion (2014)
• $502 Billion Market Capitalization
• Google processes over 3.5 Billion searches PER DAY
• Estimates of 530 Million Gmail users worldwide
• 2 High‐use Data Services

‐ Gmail ‐ Google Search

• Internet‐mobile app allowing consumers to

submit and secure trip requests.

• Contracts with individual car owners to provide

cab services

• Founded: March 2009, San Francisco, CA
• Goal: connecting riders to drivers
• Privately Held: Estimated 2015 worth $62.5B

Connecting Farmer Data and Transactions within the Ag “Ecosystem”

Internet example of linked companies “watching” my actions on 3 different websites.

New Age Business Models

• Notice these companies refer to “Users” not “Customers”
• Income generating operations are unclear or kept offline
• Basic model relies on data being fed in to the “system” at zero cost
• There is no revenue sharing intended back to the providers of data

‐ Free Email Clients ‐ Free Web Browsers ‐ Free Search Engines ‐ Free Social Media Site

The The “V “Value” of

• f In

Inform rmatio ion is is Changi Changing…. ng….

• Do not ignore the mountain of real‐time

data being generated / collected.

• Make annual copies
• Other new applications using farmer data

are emerging

• “Trust a Data Steward”
• Commit to learning more
• Commit to being better…more competitive

& improving your profitability!

Digit Digital Agr l Agricult cultur ure

Providing solutions to meet world demand

John Fulton John Fulton

Fulton.20@osu.edu 334-740-1329 @fultojp Ohio State Precision Ag Program

www.OhioStatePrecisionAg.com Twitter: @OhioStatePA Facebook: Ohio State Precision Ag

Food, Agricultural and Biological Engineering