big ideas for using data by brett whelan university of sydney
TRANSCRIPT
Page 1
(or making more use of data)
Presented by
Brett Whelan
Precision Agriculture Laboratory
Faculty of Agriculture and Environment
BIG ideas for using DATA
Page 2
It’s use dictates the
SIZE & EXTENT OF THE VALUE
Information about the magnitude and variability in production that is present
in a farming business is VALUABLE
Page 3
• The development and application of PA has been in parallel with an increase in the volume and sources of data.
• Long before the term ‘Big Data’ was dragged from the literature on digital data storage, through the filter of business management analysts, to now, PA has been working on Big ideas for using Data.
Data-Driven Decisions
Page 4
• The practical goal is to increase the number of (correct) decisions per hectare/animal/machine/season made in the business of farm management.
• The potential financial benefits from using data to better managing inputs to match variability in operations varies with each management unit & farming business, but the potential improvements in gross margin ($/ha) are significant.
Data-Driven Decisions
Page 5
• Optimise production efficiency
• Optimise quality
• Minimise business risk
• Minimise environmental impact
Production Objectives
Data-Driven Decisions
Page 6
Tull, J. (1731) The New Horse-Houghing Husbandry: or, an essay on the principles of tillage and vegetation. Wherein
is shewn, a method of introducing a sort of Vineyard-Culture into the corn-fields, in order to increase their product,
and diminish the common expence, by the use of instruments lately invented. Dublin: Printed by Aaron Rhames.
Production Objectives - Cropping
Page 7
Merge (large) data streams from diverse sources and scales with adaptable crop and environmental models that feed information into key decisions. Components include: • Data generation and capture (historic and real-time).
These may include yield maps, aerial/proximal sensing (vigour, disease, pest), soil, environment, economics/markets.
• Data dormitories. These may eventually store data in the cloud using wireless data transfer.
• Prescriptive agriculture. Derived from alternative options for crop management, variable-rate application and farm logistics based on probabilistic assessment of causal relationships.
Data-Driven Decisions
Page 8
Page 9
Page 10
Page 11
Page 12
Soil ECa measured using EM38h Engine load (% of total power rating)
Data supplied by Rupert McLaren, McLaren Farms ‘Glenmore’, Barmedman, NSW
Vehicle Engine Load During Sowing
Page 13
Operation
and
Production
Data
Data
Storage Instigated
Analyses
Farm
Decisions
& Actions
Public Data
Bases
Localised
Industry
Aggregation
Production Decision Support
Page 14
Farm
Decisions
& Actions Operation
and
Production
Data
Data
Storage
Public Data
Bases
Localised
Industry
Aggregation
Instigated
Analyses
Data
Storage
Production Decision Support
Page 15
Operation
and
Production
Data
Data
Storage
Farm
Decisions
& Actions
Public Data
Bases
Localised
Industry
Aggregation
Data
Storage Instigated
Analyses
Production Decision Support
Page 16
Farm
Decisions &
Actions
Operation
and
Production
Data Public Data
Bases
Localised
Industry
Aggregation
Data
Storage
Large,
Cloud-based
Proprietary
Agribusiness
Nefarious use
Production Decision Support
Page 17
3G
Wireless Coverage
2 – 75 Mbps 2 – 50 Mbps
4G Download
Page 18
3G
Wireless Coverage
1.1 – 20 Mbps 0.5 – 8 Mbps 0.5 – 3 Mbps
3G Download
Page 19
3G
Wireless Coverage 3G Upload
0.5 – 3 Mbps slower Considerably slow
Page 20
Data weight
Uploading Data (generic shp files)
UAV imagery –10 MB/ha
Spraying – 0.7 MB/ha
Planting – 13 MB/ha
Yield data – 10 MB/ha
Soil Mapping – Data 1.5 MB/ha
Downloading Data
Prescription files – 0.02 MB/ha
Source: T. Griffin. Kansas State University
Page 21
Farm
Decisions
& Actions Operation
and
Production
Data
Data
Storage
Public Data
Bases
Localised
Industry
Aggregation
Instigated
Analyses
Data
Storage
Production Decision Support
Page 22
Real-time,
Adaptable Farm
Decisions &
Actions
Real-time
Operation
and
Production
Data
Public Data
Bases
Localised
Industry
Aggregation
Data
Storage
Production Decision Support
Page 23
• A tool that contains the capability of autonomously adapting decision functions and providing farmers with alternative scenarios as input data changes across space and/or time.
• Involves the novel integration of relevant data from diverse domains, sources and scales to improve decision management at the sub-paddock level, within bounds of optimising the whole business profitability, and sustainability.
• Water, nitrogen and canopy management focus
• The Augmented Agronomist…..not the Automated Agronomist…..unless the decision/action warrants.
Production Decision Support
Page 24
McBratney, A.B. & Whelan, B.M. (1995) The Potential for Site-Specific Management of Cotton Farming Systems.
CRC for Sustainable Cotton Production, 46p.
A Vision
Page 25
It’s use dictates the
SIZE & EXTENT OF THE VALUE
Information about the magnitude and variability in production that is present
in a farming business is VALUABLE