“Yield Prophet & Precision Agriculture”
     “A Suitable Tool For Risk Management &
   Increased Productivity In The NAR of WA?”
                         `
Craig Topham – Agrarian Management – Geraldton WA
Where Have We Come From Historically
1.   Small machinery, Slow planting speed
2.   Small paddocks, often fenced to soil type
3.   Labour intensive , multiple pass cropping system
4.   Greater intensity of tillage = greater wind / water erosion
5.   Greater levels of fuel usage = greater emissions / ha
6.   Delayed sowing = lower yields
7.   Lower input and Overhead costs – less capital intensive
8.   90’s less seasonal variability – Expectation of Rain
90’s Thought that “No Till” would drought proof farming , low rainfall inputs increased


        00’s Realization that Technology was needed to minimise
                  impact of adverse seasonal conditions

“Adverse Seasonal Conditions Have Always Been An Expected Circumstance
               Rather Than An Exceptional Circumstance”
         Future Direction

    Ability To Allocate Capital
         Proportionately
According To Expected Conversion
           Into Revenue

  Yield Prophet & Zone Management
Large Seasonal Production Volatility
                       5 out of 13 Seasons above average


                                  2 of 13 Average



                               6 of 13 well below average


                                 Real profit made in 4
                                 out of every 10 years




                            Key is to minimise losses
                                  in the 60% of
                             Loss making seasons
The Modern NAR Farmer
•   Younger, well educated, very computer literate
•   Large scale, rapid sowing pace
•   No fences, large paddocks, increased soil variation
•   Large % dry sown, Increased capital at risk
•   Large % of Capital expended at Sowing
•   High degree of mechanization, reduced labour
•   Highly automated machinery
•   High level of precision ( Guidance, Placement, Zone Management, VRT)

•   Greater awareness of variability = Soil, Productivity, Profitability = Water holding capacity

•   Yield Prophet has increased farmer knowledge of Soil water holding capacity

                                                   Intense summer fallows and moisture conservation

                                                   Concept of bucket size becoming well understood

                                                    Farmer acceptance of modelling tools
Experiences From Last 2 Years Involvement with Yield Prophet
 Limitations to Adoption

 Adoption limited due to lack of understanding by Farmers
 Lack of exposure – limited to a few consultants – NAR WA

 Exposure largely limited to DAFWA & GRDC project participants
 - Farmer awareness / understanding increasing rapidly after exposure
 - Enthusiasm directly correlates with accuracy of model

 Accuracy in WA diminished by limited data base of locally characterised soil types

 Soil testing strategy needs refinement to be adapted to local environment
 Experienced advisor required to accurately set up model
 Good understanding of sub soil constraints and effects on plant rooting depths required
 Nitrogen model very useful, needs tailoring to WA conditions

 Experience suggests a general lack of understanding of WA soils & conditions by modellers
Yield Profit, Yield Prediction Results 2010
Morawa Poor Soil Fit – Sub Soil Constraints




                                              Three Springs year 2 Well Characterised soil


                                                            Accurate Rooting Depth
                                                            Results In Accurate Yield Prediction




                                                              More Soil Investigation Prior To
                                                              Set Up Improves In Season
                                                              Yield Prediction
Accurate Soil Characterization = Very Accurate Model
Provides Ability To Measure, Manage
               & Predict Plant Available Water

Probabilities from Historical weather patterns very powerful tool

Increases ability to play and judge the season

Experienced operator required to achieve accuracy
Thorough understanding and assessment of sub soil constraints required

Accurate measurement of plant rooting depth vital

Soil type specific – need greater understanding of within field variation
Using Yield Prophet And VRT Zone Management To Reduce Seasonal Risk

        Test Strips located over Yield Prophet sites
Shallow Roots due to Al Toxicity
Deep Rooting depth – No Sub soil Constraint
Acid Soils Zone 1 & 2              Zone 3

-Reduced Tillering                 -Deeper rooting depth
-Less heads / m²                   -Visual root growth to 1.2m
-Shallow Rooting depth 30 / 40cm   -Soil moisture assessable to roots
-Bulge of soil N built up          -Greater access to soil nitrogen
- not accessed by roots
                                   -Lower risk soil type
                                               = less yield Variability
 Moisture 30 – 40cm

  Very high soil N pre sowing
  not accessible by plant roots
Integration Of Yield Prophet & EM 38 Soil Mapping To Develop VRT Cropping Systems
   EM 38 & Gamma Radiometrics used to develop production zones within fields.
   Yield Prophet sites located within each soil zone
   Soil characterization of each production zone – (PAWC / Zone)
   Long Term Yield prediction with Yield Prophet climate change report

                                                                     Up to 2 T / ha
                                                                   variation in long
                                                                term ave yield within
                                                                    field, all due to
                                                                  variation in PAWC
Nola Downs 2010 VRT Research Trial Results
Nola Downs D1 – Management Zone / Yield

Blue Zone – High Input - High Clay content Sand Burnt off 38 - 50% screenings

Green Zone Standard inputs – Good sand Highest Yield - 30% Screenings

Red Zone – Low inputs – Poor Acid sand - 8.2% Screenings




         Low                         Standard                     High
    23.6N,7.6P,5.9K              34.7N,10.6P,10.7K          45.9N,13.7P,10.7K
Zone 3 High Input




                     Zone 2 Standard Input




Zone 3 Low Input
Nola Downs D1 Yield & Change in GM from VRT
                                       Nitrogen and Phosphate Trial
                                                                    Zone 1 Decreased Yield with Increased inputs
       Nola Downs D1 Wheat Yield / Soil zone                        Zone 2 Yield increase with Standard inputs not significant
                     2.5

                                                                    Zone 3 High inputs = Reduced yield (Screening 38 – 50%)
                      2
Wheat yield (t/ha)




                                                                    Dry Finish lowest inputs best
                                                23N; 7.6P, 5.9K     – finishing rain would be vastly different
                     1.5


                      1
                                                34N; 10.6P,8.3K
                     0.5                                                                   GM / Ha (Fert Only) / Soil Zone
                                                45N; 13.77P,10.7K                    800
                      0
                           1       2        3                                        700

                                Soil zone                                            600

                                                                    GM (fert only)
                                                                                     500                         23N; 7.6P, 5.9K
                                                                                     400
Zone 1 $92 increase in GM by Decreasing inputs                                       300                         34N; 10.6P,8.3K
                                                                                     200
Zone 2 $9 increase in GM by decreasing inputs
                                                                                     100
Screenings 30% more rain would respond to inputs                                                                 45N; 13.77P,10.7K
                                                                                       0
Zone 3 Made $15 / Ha by decreasing inputs                                                  1       2        3
Screenings up to 50% - Burnt off
                                                                                                Soil zone
Questions

More Related Content

PPTX
Improving N Efficiency through Managing Soil Nitrate
PPTX
Redesigning Dairy Systems for Improved N Use
PPT
Identifying target environments drought rbc 2012
PPTX
Are controlled traffic and permanent beds sustainable for CA? Don Yule
PDF
Irrigate for the Future - Save, Cypriot
PDF
Irrigating the Vegetable Garden - Colorado University
PDF
EarthGuard Case Study Taylor Highway - Alaska Dept of Transportation
PPT
Towards Sound Strategies For Soil-Water And Nutrient Retention A Cawt Case…
Improving N Efficiency through Managing Soil Nitrate
Redesigning Dairy Systems for Improved N Use
Identifying target environments drought rbc 2012
Are controlled traffic and permanent beds sustainable for CA? Don Yule
Irrigate for the Future - Save, Cypriot
Irrigating the Vegetable Garden - Colorado University
EarthGuard Case Study Taylor Highway - Alaska Dept of Transportation
Towards Sound Strategies For Soil-Water And Nutrient Retention A Cawt Case…

Similar to Yield Prophet and precision agriculture - a suitable tool for risk management and increased productivity in the Northern Agricultural Region of WA? - Craig Topham (20)

PPTX
Decision support systems in practice - some observations. David Freebairn
PPTX
Workshop Trade-off Analysis - CGIAR_19 Feb 2013_CRP 1.1_Anthony Whitbread
PPT
0893 Conventional Rice vs SRI - Prospects
PDF
Simulating the Impact of Climate Change and Adaptation Strategies on Farm Pro...
PDF
Ringler w bpresentation_mitigation_smallsize
PDF
[Day 2] Center Presentation: IFPRI
PPTX
Assessing production risks in agricultural systems - a modelling study with A...
PDF
A Bianchini
PDF
S1.1 Glimpsing the Future by Looking back : Abiotic Stress Tolerance in Maize
PDF
S1.1 edmeades 11th asian maize conf 8 nov11
PPTX
23 25 jan 2013 csisa kathmandu overview eup bihar dr malik
PDF
De Pinto - Mitigation opportunities and challenges: An economic perspective
PDF
Ever crop for low rainfall areas
PDF
003 lac the worlds future rice bowl, robert zeigler
PDF
Latin america worlds_future_rice_bowl
PPTX
Spatial variation of soil constraints and its implications for site-specific ...
PDF
Sas presentation
Decision support systems in practice - some observations. David Freebairn
Workshop Trade-off Analysis - CGIAR_19 Feb 2013_CRP 1.1_Anthony Whitbread
0893 Conventional Rice vs SRI - Prospects
Simulating the Impact of Climate Change and Adaptation Strategies on Farm Pro...
Ringler w bpresentation_mitigation_smallsize
[Day 2] Center Presentation: IFPRI
Assessing production risks in agricultural systems - a modelling study with A...
A Bianchini
S1.1 Glimpsing the Future by Looking back : Abiotic Stress Tolerance in Maize
S1.1 edmeades 11th asian maize conf 8 nov11
23 25 jan 2013 csisa kathmandu overview eup bihar dr malik
De Pinto - Mitigation opportunities and challenges: An economic perspective
Ever crop for low rainfall areas
003 lac the worlds future rice bowl, robert zeigler
Latin america worlds_future_rice_bowl
Spatial variation of soil constraints and its implications for site-specific ...
Sas presentation
Ad

More from Climate Change Research Strategy for Primary Industries (20)

PPTX
Can we reduce nitrous oxide emissions from crops? - Sally Officer
PPT
Is it commercially viable to use dicyandiamide on a dairy farm in south-weste...
PPT
How will the impact of elevated carbon dioxide on grain production vary with ...
PPTX
A field study on the impact of the nitrification inhibitor DMPP on nitrous ox...
PPTX
Securing pulses under changed climates - Rebecca Ford
PPTX
Nutrient supply, below ground processes and elevated CO2 change the nutrition...
PPT
Impact of climate change on wheat phenology in the NSW wheat belt - De Li Liu
PPTX
Will climate change negate better farm management for improving water quality...
PPTX
Managing crop production uncertainties and climate variability through a map-...
PPT
Can flexibility be built into cropping systems for adapting to climate uncert...
PPT
Managing future agricultural production in a variable and changing climate - ...
PPTX
An integrated assessment of land use change in the Border Rivers-Gwydir catch...
PPTX
Agricultural adaptation during times of change - Thilak Mallawaarachchi
PPT
Future Farm Industries Cooperative Research Centre: profitable perennials - B...
PPT
Practical management of climate variability in a changing climate - Peter McI...
PPTX
An historical analysis of the changes in pasture production and growing seaso...
PPT
Attitudes to climate change in southern NSW - Jan Edwards
PPT
Resilience surfaces for pasture production under climate change scenarios - B...
PPTX
Grains best management practice for managing climate threats and opportunitie...
PPTX
Will managing for climate variability also manage for climate change? - Andre...
Can we reduce nitrous oxide emissions from crops? - Sally Officer
Is it commercially viable to use dicyandiamide on a dairy farm in south-weste...
How will the impact of elevated carbon dioxide on grain production vary with ...
A field study on the impact of the nitrification inhibitor DMPP on nitrous ox...
Securing pulses under changed climates - Rebecca Ford
Nutrient supply, below ground processes and elevated CO2 change the nutrition...
Impact of climate change on wheat phenology in the NSW wheat belt - De Li Liu
Will climate change negate better farm management for improving water quality...
Managing crop production uncertainties and climate variability through a map-...
Can flexibility be built into cropping systems for adapting to climate uncert...
Managing future agricultural production in a variable and changing climate - ...
An integrated assessment of land use change in the Border Rivers-Gwydir catch...
Agricultural adaptation during times of change - Thilak Mallawaarachchi
Future Farm Industries Cooperative Research Centre: profitable perennials - B...
Practical management of climate variability in a changing climate - Peter McI...
An historical analysis of the changes in pasture production and growing seaso...
Attitudes to climate change in southern NSW - Jan Edwards
Resilience surfaces for pasture production under climate change scenarios - B...
Grains best management practice for managing climate threats and opportunitie...
Will managing for climate variability also manage for climate change? - Andre...
Ad

Recently uploaded (20)

PPTX
Internet of Everything -Basic concepts details
PDF
5-Ways-AI-is-Revolutionizing-Telecom-Quality-Engineering.pdf
PDF
CXOs-Are-you-still-doing-manual-DevOps-in-the-age-of-AI.pdf
PDF
Co-training pseudo-labeling for text classification with support vector machi...
PDF
substrate PowerPoint Presentation basic one
PPTX
Module 1 Introduction to Web Programming .pptx
PPTX
Presentation - Principles of Instructional Design.pptx
PDF
Advancing precision in air quality forecasting through machine learning integ...
PDF
Transform-Your-Streaming-Platform-with-AI-Driven-Quality-Engineering.pdf
PDF
Electrocardiogram sequences data analytics and classification using unsupervi...
PDF
Auditboard EB SOX Playbook 2023 edition.
PDF
Build Real-Time ML Apps with Python, Feast & NoSQL
PDF
NewMind AI Weekly Chronicles – August ’25 Week IV
PDF
Early detection and classification of bone marrow changes in lumbar vertebrae...
PDF
Introduction to MCP and A2A Protocols: Enabling Agent Communication
PDF
EIS-Webinar-Regulated-Industries-2025-08.pdf
PDF
A hybrid framework for wild animal classification using fine-tuned DenseNet12...
PPTX
Build automations faster and more reliably with UiPath ScreenPlay
PDF
Planning-an-Audit-A-How-To-Guide-Checklist-WP.pdf
PDF
Transform-Your-Factory-with-AI-Driven-Quality-Engineering.pdf
Internet of Everything -Basic concepts details
5-Ways-AI-is-Revolutionizing-Telecom-Quality-Engineering.pdf
CXOs-Are-you-still-doing-manual-DevOps-in-the-age-of-AI.pdf
Co-training pseudo-labeling for text classification with support vector machi...
substrate PowerPoint Presentation basic one
Module 1 Introduction to Web Programming .pptx
Presentation - Principles of Instructional Design.pptx
Advancing precision in air quality forecasting through machine learning integ...
Transform-Your-Streaming-Platform-with-AI-Driven-Quality-Engineering.pdf
Electrocardiogram sequences data analytics and classification using unsupervi...
Auditboard EB SOX Playbook 2023 edition.
Build Real-Time ML Apps with Python, Feast & NoSQL
NewMind AI Weekly Chronicles – August ’25 Week IV
Early detection and classification of bone marrow changes in lumbar vertebrae...
Introduction to MCP and A2A Protocols: Enabling Agent Communication
EIS-Webinar-Regulated-Industries-2025-08.pdf
A hybrid framework for wild animal classification using fine-tuned DenseNet12...
Build automations faster and more reliably with UiPath ScreenPlay
Planning-an-Audit-A-How-To-Guide-Checklist-WP.pdf
Transform-Your-Factory-with-AI-Driven-Quality-Engineering.pdf

Yield Prophet and precision agriculture - a suitable tool for risk management and increased productivity in the Northern Agricultural Region of WA? - Craig Topham

  • 1. “Yield Prophet & Precision Agriculture” “A Suitable Tool For Risk Management & Increased Productivity In The NAR of WA?” ` Craig Topham – Agrarian Management – Geraldton WA
  • 2. Where Have We Come From Historically 1. Small machinery, Slow planting speed 2. Small paddocks, often fenced to soil type 3. Labour intensive , multiple pass cropping system 4. Greater intensity of tillage = greater wind / water erosion 5. Greater levels of fuel usage = greater emissions / ha 6. Delayed sowing = lower yields 7. Lower input and Overhead costs – less capital intensive 8. 90’s less seasonal variability – Expectation of Rain
  • 3. 90’s Thought that “No Till” would drought proof farming , low rainfall inputs increased 00’s Realization that Technology was needed to minimise impact of adverse seasonal conditions “Adverse Seasonal Conditions Have Always Been An Expected Circumstance Rather Than An Exceptional Circumstance” Future Direction Ability To Allocate Capital Proportionately According To Expected Conversion Into Revenue Yield Prophet & Zone Management
  • 4. Large Seasonal Production Volatility 5 out of 13 Seasons above average 2 of 13 Average 6 of 13 well below average Real profit made in 4 out of every 10 years Key is to minimise losses in the 60% of Loss making seasons
  • 5. The Modern NAR Farmer • Younger, well educated, very computer literate • Large scale, rapid sowing pace • No fences, large paddocks, increased soil variation • Large % dry sown, Increased capital at risk • Large % of Capital expended at Sowing • High degree of mechanization, reduced labour • Highly automated machinery • High level of precision ( Guidance, Placement, Zone Management, VRT) • Greater awareness of variability = Soil, Productivity, Profitability = Water holding capacity • Yield Prophet has increased farmer knowledge of Soil water holding capacity Intense summer fallows and moisture conservation Concept of bucket size becoming well understood Farmer acceptance of modelling tools
  • 6. Experiences From Last 2 Years Involvement with Yield Prophet Limitations to Adoption Adoption limited due to lack of understanding by Farmers Lack of exposure – limited to a few consultants – NAR WA Exposure largely limited to DAFWA & GRDC project participants - Farmer awareness / understanding increasing rapidly after exposure - Enthusiasm directly correlates with accuracy of model Accuracy in WA diminished by limited data base of locally characterised soil types Soil testing strategy needs refinement to be adapted to local environment Experienced advisor required to accurately set up model Good understanding of sub soil constraints and effects on plant rooting depths required Nitrogen model very useful, needs tailoring to WA conditions Experience suggests a general lack of understanding of WA soils & conditions by modellers
  • 7. Yield Profit, Yield Prediction Results 2010 Morawa Poor Soil Fit – Sub Soil Constraints Three Springs year 2 Well Characterised soil Accurate Rooting Depth Results In Accurate Yield Prediction More Soil Investigation Prior To Set Up Improves In Season Yield Prediction
  • 8. Accurate Soil Characterization = Very Accurate Model
  • 9. Provides Ability To Measure, Manage & Predict Plant Available Water Probabilities from Historical weather patterns very powerful tool Increases ability to play and judge the season Experienced operator required to achieve accuracy Thorough understanding and assessment of sub soil constraints required Accurate measurement of plant rooting depth vital Soil type specific – need greater understanding of within field variation
  • 10. Using Yield Prophet And VRT Zone Management To Reduce Seasonal Risk Test Strips located over Yield Prophet sites
  • 11. Shallow Roots due to Al Toxicity
  • 12. Deep Rooting depth – No Sub soil Constraint
  • 13. Acid Soils Zone 1 & 2 Zone 3 -Reduced Tillering -Deeper rooting depth -Less heads / m² -Visual root growth to 1.2m -Shallow Rooting depth 30 / 40cm -Soil moisture assessable to roots -Bulge of soil N built up -Greater access to soil nitrogen - not accessed by roots -Lower risk soil type = less yield Variability Moisture 30 – 40cm Very high soil N pre sowing not accessible by plant roots
  • 14. Integration Of Yield Prophet & EM 38 Soil Mapping To Develop VRT Cropping Systems EM 38 & Gamma Radiometrics used to develop production zones within fields. Yield Prophet sites located within each soil zone Soil characterization of each production zone – (PAWC / Zone) Long Term Yield prediction with Yield Prophet climate change report Up to 2 T / ha variation in long term ave yield within field, all due to variation in PAWC
  • 15. Nola Downs 2010 VRT Research Trial Results
  • 16. Nola Downs D1 – Management Zone / Yield Blue Zone – High Input - High Clay content Sand Burnt off 38 - 50% screenings Green Zone Standard inputs – Good sand Highest Yield - 30% Screenings Red Zone – Low inputs – Poor Acid sand - 8.2% Screenings Low Standard High 23.6N,7.6P,5.9K 34.7N,10.6P,10.7K 45.9N,13.7P,10.7K
  • 17. Zone 3 High Input Zone 2 Standard Input Zone 3 Low Input
  • 18. Nola Downs D1 Yield & Change in GM from VRT Nitrogen and Phosphate Trial Zone 1 Decreased Yield with Increased inputs Nola Downs D1 Wheat Yield / Soil zone Zone 2 Yield increase with Standard inputs not significant 2.5 Zone 3 High inputs = Reduced yield (Screening 38 – 50%) 2 Wheat yield (t/ha) Dry Finish lowest inputs best 23N; 7.6P, 5.9K – finishing rain would be vastly different 1.5 1 34N; 10.6P,8.3K 0.5 GM / Ha (Fert Only) / Soil Zone 45N; 13.77P,10.7K 800 0 1 2 3 700 Soil zone 600 GM (fert only) 500 23N; 7.6P, 5.9K 400 Zone 1 $92 increase in GM by Decreasing inputs 300 34N; 10.6P,8.3K 200 Zone 2 $9 increase in GM by decreasing inputs 100 Screenings 30% more rain would respond to inputs 45N; 13.77P,10.7K 0 Zone 3 Made $15 / Ha by decreasing inputs 1 2 3 Screenings up to 50% - Burnt off Soil zone