SlideShare a Scribd company logo
Real-time pasture biomass
estimation
Mark Trotter, Karl Andersson, Andrew Robson, Derek
Schneider, Ashley Saint, Lucy Frizell
Participant teams: Lewis Kahn, Paul Reynolds, Tony Butler,
Brad Wooldridge, Chris Blore, Peter Schroder, Jim Shovelton,
Ian Gamble
B.GSM.0010, P4.18
Real Time Pasture Biomass Estimation
Aims and why
What we’re doing
Some results
Mobile app
Future directions
Aims
1. Evaluate the potential for Active Optical
Sensors (AOS)
2. Develop a series calibrations for use by
producers
3. Develop a Mobile Device Application
(MDA) to support AOS
Aims:
Current
biomass
Growth
rate
Paddock 963 23
Black leg 750 21
Plumb tree 894 25
Parkers 675 11
Parkers west 762 18
Gumtree 1 1256 31
Gumtree 2 1766 34
500
1000
1500
Export data
Why?
Pasture utilisation
Estimate biomass compared to benchmarks
Help make objective decisions on stocking rates
Calibrate other methods (e.g. pastures from
space)
Why?
 Pasture utilisation
 Help make objective decisions on stocking rates
 Estimate biomass compared to benchmarks
 Calibrate other methods (e.g. pastures from space)
Why?
 Pasture utilisation
 Help make objective decisions on stocking rates
 Estimate biomass compared to benchmarks
 Calibrate other methods (e.g. pastures from space)
Why?
 Pasture utilisation
 Help make objective decisions on stocking rates
 Estimate biomass compared to
benchmarks
 Calibrate other methods
Correlating sensors to GDM…
 >200 samples taken from across Australia
 Each sample consists of 8-12 individual cuts
 Each site is scanned with a Greenseeker Handheld
 Height measured by plate meter
 Digital image (before and after cut)
 Quadrat is harvested using clippers or knives – cut
to ground
Preliminary results…
• The ok, more
common
• Tablelands Fescue
• The good,
• Tasmanian
Ryegrass
Preliminary results…
• The problems…
• Poor calibrations • NDVI Saturation
Effect of plant mix
Season State Species Input variable Model type Model R2
1 Winter NSW Fescue NDVI*Height LM -204 + 368.8 x 0.95
2 Winter Vic Ryegrass NDVI*Height GLM exp^(6.1 + 0.21 x) 0.79
3 Winter Vic Phalaris_Ryegrass NDVI*Height LM -189 + 244.7 x 0.68
4 Winter Vic Phalaris NDVIxLHt LM -62 + 862.3 x 0.67
5 Winter Vic Mixed LNDVI LM -22 -811.5 x 0.33
6 Winter NSW Fescue NDVI GLM exp^(4.2 + 5.75 x) 0.91
7 Winter NSW Lucerne NDVI LM -571 + 2464.7 x 0.92
8 Winter Vic Mixed NDVI LM -75157 + 104337.6 x 0.6
9 Winter Vic Phalaris_Clover NDVIxLHt LM -167 + 945.8 x 0.93
10 Winter Vic Phalaris LHt LM -1378 + 1731.9 x 0.75
11 Winter Vic Phalaris_Ryegrass_Clove
r
LHt LM -835 + 1509.6 x 0.53
12 Winter Vic Phalaris_Clover NDVIxLHt GLM exp^(4.9 + 1.35 x) 0.86
14 Winter NSW Fescue LNDVI GLM exp^(9.2 + 2.61 x) 0.95
15 Winter Vic Phalaris_Clover NDVIxLHt QLM -30 + 456.1 x + 178.8 x^2 0.92
16 Winter Vic Phalaris LNDVI GLM exp^(9.1 + 10.2 x) 0.73
17 Winter Vic Ryegrass NDVI*Height GLM exp^(4.4 + 0.41 x) 0.71
18 Winter Vic Phalaris_Clover NDVIxLHt LM -347 + 1613.8 x 0.81
19 Winter Vic Phalaris_Ryegrass_Clove
r
Height GLM exp^(6.7 + 0.15 x) 0.84
20 Spring Vic Ryegrass NDVI*Height LM 925 + 256.1 x 0.87
23 Spring Vic Phalaris_Clover NDVI*Height GLM exp^(8.1 + 0.14 x) 0.47
24 Spring NSW Fescue NDVIxLHt LM -592 + 2141.8 x 0.87
25 Spring NSW Lucerne NDVI GLM exp^(2.2 + 6.79 x) 0.76
26 Spring NSW Phalaris LHt LM -93 + 1113.7 x 0.96
27 Spring Vic Mixed LHt GLM exp^(3.3 + 1.72 x) 0.72
28 Spring Vic Mixed NDVI*Height LM 1333 + 443.3 x 0.51
29 Spring Vic Ryegrass NDVI GLM exp^(-5.9 + 16.2 x) 0.68
30 Spring Vic Phalaris NDVIxLHt GLM exp^(4.6 + 1.64 x) 0.89
31 Spring Vic Phalaris_Clover Height LM 242 + 191.2 x 0.92
32 Spring NSW Cocksfoot_Fescue NDVIxLHt LM -348 + 2069.1 x 0.7
33 Spring NSW Cocksfoot_Fescue_Clove
r
LNDVI GLM exp^(8.4 + 1.88 x) 0.71
34 Spring Vic Ryegrass_Clover NDVI*Height GLM exp^(6.5 + 0.12 x) 0.86
35 Spring Vic Phalaris_Clover NDVIxLHt LM -75 + 1418.4 x 0.91
36 Spring NSW Fescue_Clover NDVIxLHt LM -60 + 1145.7 x 0.65
37 Spring NSW Ryegrass NDVI LM -578 + 5083.8 x 0.63
38 Spring NSW Fescue NDVIxLHt LM 174 + 1641.4 x 0.74
39 Spring NSW Mixed NDVIxLHt LM -633 + 2381.6 x 0.9
40 Spring Vic Mixed LNDVI LM 8218 + 7283.1 x 0.82
41 Spring Vic Ryegrass NDVIxLHt LM -1112 + 2783.3 x 0.9
42 Spring Vic Phalaris_Ryegrass_Clove
r
LNDVI LM 3410 + 2241.5 x 0.83
43 Spring Vic Phalaris Clover NDVIxLHt LM 91 + 2256 8 x 0 95
Solutions?
 We examined
other reflectance
bands
 Excellent
correlation but
not consistent
 The best co-
variate turns out
to be plate
height.
Question % of possible 
sites 
Proportion of sites where ACS470 bands are better than GS NDVI?  97%
Proportion of these sites where there is a substantive improvement (increase of 
more than r2
 0.10)? 
71%
Proportion of sites where ACS470 bands are better than GS NDVI, Height or a 
combination? 
78%
Proportion of these sites where there is a substantive improvement (increase of 
more than r2
 0.10)? 
29%
Date  State 
Locatio
n 
Species/past
ure type 
Best 2 band 
sensor model  r2
 
Best 3 band sensor 
model  r2
 
   
4/06/2014 NSW UNE 
Fescue 
Fescue Ln GDM = Ln 
NDVI ((760‐
700)/760+700) 
0.83 Ln GDM = Band 590, 
Ln Band 730 
0.86 
23/06/2014 NSW Sundow
n 
Lucerne  GDM = Ln SR 
(590/730) 
0.91 GDM = SR 
(590/730), SR 
(730/760) 
0.95 
23/06/2014 NSW Sundow
n 
Fescue GDM = SR 
(590/670) 
0.93 GDM = SR(730/670), 
SR(760/590) 
0.95 
25/07/2014 NSW Sundow
n 
Fescue Ln GDM = 
SR(530/760) 
0.96 Ln GDM = Band 730, 
Ln NDVI ((760‐
530)/760+530)) 
0.98 
18/09/2015 NSW Sundow
n 
Lucerne  GDM = Ln((760‐
530)/760+530)) 
0.93 Ln GDM = 
SR(760/730), Ln 
Band 700 
0.98 
18/09/2014 NSW Sundow
n 
Fescue Ln GDM = Band  
530 
0.85 Ln GDM = Ln Band 
760, NDVI ((760‐
530)/760+530)) 
0.90 
23/09/2014 NSW Kirby Phalaris  GDM = NDVI 
((760‐
730)/(760+730)) 
0.88 GDM = Ln 
SR(670/760), Ln 
SR(700/730) 
0.98 
 
a) b) c)
Region    
Combined 
Winter+Spring
All cuts
Northern 
Tablelands 
r2
  0.70 0.45
n  289 545
Mean 2191 2616
RMSE  982 1312
Central 
Victoria 
r2
  0.77   
n  66
Mean  1373
RMSE  541   
Southern 
Victoria 
r2
  0.62   
n  82
Mean  1743
RMSE 375
Western 
Victoria 
r2
  0.77   
n  326
Mean  1206
RMSE  469   
Tasmania 
r2
  0.66 0.68
n  82 153
Mean  1189 1120
RMSE  403 380
WA and SA pastures
0 units
21 units
42 units
63 units
0.51 0.55
0.65 0.78
DIY calibration
Where to from here?
 Integrate with weather and satellite data
 Integrate with LiDAR
 Integration with feed budgeting/stocking rate software
 Quality and pasture growth rates
Calibration shifts
Dealing with calibration shifts…
NDVI profiling
Soil moisture
LiDAR data
Lidar data
Take home messages
 NDVI from affordable AOS have the potential to provide pastures
biomass estimates
 In many pastures, the inclusion of height measures improved the
correlation with GDM, and was a better universal covariate than other
AOS bands
 Work is still to be done to validate estimates, and provide seasonal,
regional, species and calibrations
 LiDAR may provide convenient height measures, though further
development is required

More Related Content

Viewers also liked

Presentasi settingulang
Presentasi settingulangPresentasi settingulang
Presentasi settingulang
lani adiningsih
 
David rogers ingles_bloque_5_y_6
David rogers ingles_bloque_5_y_6David rogers ingles_bloque_5_y_6
David rogers ingles_bloque_5_y_6
UPN Universidad Privada del Norte
 
Almanak BIG 2015
Almanak BIG 2015Almanak BIG 2015
Almanak BIG 2015
Kunto Adji
 
Electrical measurements
Electrical measurementsElectrical measurements
Electrical measurements
Mohammed Waris Senan
 
Pembacaan dan pemahaman gambar teknik
Pembacaan dan pemahaman gambar teknikPembacaan dan pemahaman gambar teknik
Pembacaan dan pemahaman gambar teknik
Zainal Abidin
 
Kabel bawah tanah dan sambungan kabel-Syamsir abduh
Kabel bawah tanah dan sambungan kabel-Syamsir abduhKabel bawah tanah dan sambungan kabel-Syamsir abduh
Kabel bawah tanah dan sambungan kabel-Syamsir abduh
Trisakti University
 
RPP SMK Gambar Teknik Kelas XI
RPP SMK Gambar Teknik Kelas XIRPP SMK Gambar Teknik Kelas XI
RPP SMK Gambar Teknik Kelas XI
Diva Pendidikan
 
Dianelvaguzman.doc
Dianelvaguzman.docDianelvaguzman.doc
Dianelvaguzman.doc
Dianelva Guzman
 

Viewers also liked (9)

Presentasi settingulang
Presentasi settingulangPresentasi settingulang
Presentasi settingulang
 
David rogers ingles_bloque_5_y_6
David rogers ingles_bloque_5_y_6David rogers ingles_bloque_5_y_6
David rogers ingles_bloque_5_y_6
 
Almanak BIG 2015
Almanak BIG 2015Almanak BIG 2015
Almanak BIG 2015
 
Electrical measurements
Electrical measurementsElectrical measurements
Electrical measurements
 
Todd Bittner Resume ver2
Todd Bittner Resume ver2Todd Bittner Resume ver2
Todd Bittner Resume ver2
 
Pembacaan dan pemahaman gambar teknik
Pembacaan dan pemahaman gambar teknikPembacaan dan pemahaman gambar teknik
Pembacaan dan pemahaman gambar teknik
 
Kabel bawah tanah dan sambungan kabel-Syamsir abduh
Kabel bawah tanah dan sambungan kabel-Syamsir abduhKabel bawah tanah dan sambungan kabel-Syamsir abduh
Kabel bawah tanah dan sambungan kabel-Syamsir abduh
 
RPP SMK Gambar Teknik Kelas XI
RPP SMK Gambar Teknik Kelas XIRPP SMK Gambar Teknik Kelas XI
RPP SMK Gambar Teknik Kelas XI
 
Dianelvaguzman.doc
Dianelvaguzman.docDianelvaguzman.doc
Dianelvaguzman.doc
 

Similar to Real-time pasture biomass estimation by Karl Andersson

Network Tools in FME
Network Tools in FMENetwork Tools in FME
Network Tools in FMESafe Software
 
Kano GIS Day 2014 - The Application of Multivariate Geostatistical analyses i...
Kano GIS Day 2014 - The Application of Multivariate Geostatistical analyses i...Kano GIS Day 2014 - The Application of Multivariate Geostatistical analyses i...
Kano GIS Day 2014 - The Application of Multivariate Geostatistical analyses i...
eHealth Africa
 
Optimization of VNIRS for field determination oftopsoil chemical properties J...
Optimization of VNIRS for field determination oftopsoil chemical properties J...Optimization of VNIRS for field determination oftopsoil chemical properties J...
Optimization of VNIRS for field determination oftopsoil chemical properties J...
FAO
 
Development of marker-assisted selection (MAS) technology in crop improvement...
Development of marker-assisted selection (MAS) technology in crop improvement...Development of marker-assisted selection (MAS) technology in crop improvement...
Development of marker-assisted selection (MAS) technology in crop improvement...
International Institute of Tropical Agriculture
 
Carlos Rivero Predictive Analytics Presentation
Carlos Rivero Predictive Analytics PresentationCarlos Rivero Predictive Analytics Presentation
Carlos Rivero Predictive Analytics PresentationCarlos Rivero
 
Cost of Living, Linear Regression, Multiple Linear Regression
Cost of Living, Linear Regression, Multiple Linear RegressionCost of Living, Linear Regression, Multiple Linear Regression
Cost of Living, Linear Regression, Multiple Linear Regression
Faisal Akbar
 
DigitalGlobe Overview
DigitalGlobe OverviewDigitalGlobe Overview
DigitalGlobe Overview
CIMMYT
 
Validation
ValidationValidation
Validation
COGS Presentations
 
Extreme Computing for Extreme Adaptive Optics: The Key to Finding Life Outsid...
Extreme Computing for Extreme Adaptive Optics: The Key to Finding Life Outsid...Extreme Computing for Extreme Adaptive Optics: The Key to Finding Life Outsid...
Extreme Computing for Extreme Adaptive Optics: The Key to Finding Life Outsid...
inside-BigData.com
 
Non-Uniform Random Feature Selection and Kernel Density Scoring With SVM Base...
Non-Uniform Random Feature Selection and Kernel Density Scoring With SVM Base...Non-Uniform Random Feature Selection and Kernel Density Scoring With SVM Base...
Non-Uniform Random Feature Selection and Kernel Density Scoring With SVM Base...
Sathishkumar Samiappan
 
doe in other industries
doe in other industriesdoe in other industries
doe in other industries
gautam makeshbabu
 
High throughput assessment of plant canopy in progress
High throughput assessment of plant canopy in progressHigh throughput assessment of plant canopy in progress
High throughput assessment of plant canopy in progress
ICRISAT
 
BATHYMETRIC LIDAR
BATHYMETRIC LIDARBATHYMETRIC LIDAR
DSD-INT - SWAN Advanced Course - 02 - Setting up a SWAN computation
DSD-INT - SWAN Advanced Course - 02 - Setting up a SWAN computationDSD-INT - SWAN Advanced Course - 02 - Setting up a SWAN computation
DSD-INT - SWAN Advanced Course - 02 - Setting up a SWAN computation
Deltares
 

Similar to Real-time pasture biomass estimation by Karl Andersson (15)

Network Tools in FME
Network Tools in FMENetwork Tools in FME
Network Tools in FME
 
Kano GIS Day 2014 - The Application of Multivariate Geostatistical analyses i...
Kano GIS Day 2014 - The Application of Multivariate Geostatistical analyses i...Kano GIS Day 2014 - The Application of Multivariate Geostatistical analyses i...
Kano GIS Day 2014 - The Application of Multivariate Geostatistical analyses i...
 
Optimization of VNIRS for field determination oftopsoil chemical properties J...
Optimization of VNIRS for field determination oftopsoil chemical properties J...Optimization of VNIRS for field determination oftopsoil chemical properties J...
Optimization of VNIRS for field determination oftopsoil chemical properties J...
 
Development of marker-assisted selection (MAS) technology in crop improvement...
Development of marker-assisted selection (MAS) technology in crop improvement...Development of marker-assisted selection (MAS) technology in crop improvement...
Development of marker-assisted selection (MAS) technology in crop improvement...
 
Carlos Rivero Predictive Analytics Presentation
Carlos Rivero Predictive Analytics PresentationCarlos Rivero Predictive Analytics Presentation
Carlos Rivero Predictive Analytics Presentation
 
Cost of Living, Linear Regression, Multiple Linear Regression
Cost of Living, Linear Regression, Multiple Linear RegressionCost of Living, Linear Regression, Multiple Linear Regression
Cost of Living, Linear Regression, Multiple Linear Regression
 
DigitalGlobe Overview
DigitalGlobe OverviewDigitalGlobe Overview
DigitalGlobe Overview
 
Validation
ValidationValidation
Validation
 
Extreme Computing for Extreme Adaptive Optics: The Key to Finding Life Outsid...
Extreme Computing for Extreme Adaptive Optics: The Key to Finding Life Outsid...Extreme Computing for Extreme Adaptive Optics: The Key to Finding Life Outsid...
Extreme Computing for Extreme Adaptive Optics: The Key to Finding Life Outsid...
 
Non-Uniform Random Feature Selection and Kernel Density Scoring With SVM Base...
Non-Uniform Random Feature Selection and Kernel Density Scoring With SVM Base...Non-Uniform Random Feature Selection and Kernel Density Scoring With SVM Base...
Non-Uniform Random Feature Selection and Kernel Density Scoring With SVM Base...
 
doe in other industries
doe in other industriesdoe in other industries
doe in other industries
 
RegressionProjectReport
RegressionProjectReportRegressionProjectReport
RegressionProjectReport
 
High throughput assessment of plant canopy in progress
High throughput assessment of plant canopy in progressHigh throughput assessment of plant canopy in progress
High throughput assessment of plant canopy in progress
 
BATHYMETRIC LIDAR
BATHYMETRIC LIDARBATHYMETRIC LIDAR
BATHYMETRIC LIDAR
 
DSD-INT - SWAN Advanced Course - 02 - Setting up a SWAN computation
DSD-INT - SWAN Advanced Course - 02 - Setting up a SWAN computationDSD-INT - SWAN Advanced Course - 02 - Setting up a SWAN computation
DSD-INT - SWAN Advanced Course - 02 - Setting up a SWAN computation
 

More from Amanda Woods

Hire for Baby Australia Franchise Business model slide
Hire for Baby Australia Franchise Business model slideHire for Baby Australia Franchise Business model slide
Hire for Baby Australia Franchise Business model slide
Amanda Woods
 
SPAA Precision Ag News magazine Vol 12 Issue 3 Winter 2016
SPAA Precision Ag News magazine Vol 12 Issue 3 Winter 2016SPAA Precision Ag News magazine Vol 12 Issue 3 Winter 2016
SPAA Precision Ag News magazine Vol 12 Issue 3 Winter 2016
Amanda Woods
 
SPAA Precision Agriculture in Practise II Book in Case Studies
SPAA Precision Agriculture in Practise II Book in Case StudiesSPAA Precision Agriculture in Practise II Book in Case Studies
SPAA Precision Agriculture in Practise II Book in Case Studies
Amanda Woods
 
Weed Sensing SPAA Precision Agriculture Factsheet 2016
Weed Sensing SPAA Precision Agriculture Factsheet 2016Weed Sensing SPAA Precision Agriculture Factsheet 2016
Weed Sensing SPAA Precision Agriculture Factsheet 2016
Amanda Woods
 
Airborne Imagery SPAA Precision Agriculture factsheet 2016
Airborne Imagery SPAA Precision Agriculture factsheet 2016Airborne Imagery SPAA Precision Agriculture factsheet 2016
Airborne Imagery SPAA Precision Agriculture factsheet 2016
Amanda Woods
 
Controlled Traffic Farming Precision SPAA Agriculture Factsheet
Controlled Traffic Farming Precision SPAA Agriculture FactsheetControlled Traffic Farming Precision SPAA Agriculture Factsheet
Controlled Traffic Farming Precision SPAA Agriculture Factsheet
Amanda Woods
 
A Guide to Using Precision Viticulture Case Studies from the Grampians and Ya...
A Guide to Using Precision Viticulture Case Studies from the Grampians and Ya...A Guide to Using Precision Viticulture Case Studies from the Grampians and Ya...
A Guide to Using Precision Viticulture Case Studies from the Grampians and Ya...
Amanda Woods
 
Precision Viticulture FactSheet by SPAA Australia 2015
Precision Viticulture FactSheet by SPAA Australia 2015Precision Viticulture FactSheet by SPAA Australia 2015
Precision Viticulture FactSheet by SPAA Australia 2015
Amanda Woods
 
UAV Drone Mapping of Rhizoctonia bare patch for targeted treatment by Andrea ...
UAV Drone Mapping of Rhizoctonia bare patch for targeted treatment by Andrea ...UAV Drone Mapping of Rhizoctonia bare patch for targeted treatment by Andrea ...
UAV Drone Mapping of Rhizoctonia bare patch for targeted treatment by Andrea ...
Amanda Woods
 
Does Optimum Surface Landforming offer Precision Agriculture's Highest ROI? D...
Does Optimum Surface Landforming offer Precision Agriculture's Highest ROI? D...Does Optimum Surface Landforming offer Precision Agriculture's Highest ROI? D...
Does Optimum Surface Landforming offer Precision Agriculture's Highest ROI? D...
Amanda Woods
 
PPMS: Cattle and Pasture Production without the sweat by Sally Leigo
PPMS: Cattle and Pasture Production without the sweat by Sally LeigoPPMS: Cattle and Pasture Production without the sweat by Sally Leigo
PPMS: Cattle and Pasture Production without the sweat by Sally Leigo
Amanda Woods
 
Knowledge Management, sensing and control tools for irrigated broadacre cropping
Knowledge Management, sensing and control tools for irrigated broadacre croppingKnowledge Management, sensing and control tools for irrigated broadacre cropping
Knowledge Management, sensing and control tools for irrigated broadacre cropping
Amanda Woods
 
Big ideas for using data by Brett Whelan University of Sydney
Big ideas for using data by Brett Whelan University of SydneyBig ideas for using data by Brett Whelan University of Sydney
Big ideas for using data by Brett Whelan University of Sydney
Amanda Woods
 
101 ways to make precision agriculture work in Qld vegetables Sarah Limpus, I...
101 ways to make precision agriculture work in Qld vegetables Sarah Limpus, I...101 ways to make precision agriculture work in Qld vegetables Sarah Limpus, I...
101 ways to make precision agriculture work in Qld vegetables Sarah Limpus, I...
Amanda Woods
 
Pest & Disease Survelliance & New Technologies by Rohan Kimber
Pest & Disease Survelliance & New Technologies by Rohan KimberPest & Disease Survelliance & New Technologies by Rohan Kimber
Pest & Disease Survelliance & New Technologies by Rohan Kimber
Amanda Woods
 
Big Data for Informed Decisions by Lisa Prassack, Prassack Advisors
Big Data for Informed Decisions by Lisa Prassack, Prassack AdvisorsBig Data for Informed Decisions by Lisa Prassack, Prassack Advisors
Big Data for Informed Decisions by Lisa Prassack, Prassack Advisors
Amanda Woods
 
Evaluating satellite remote sensing as a method for measuring yield variabili...
Evaluating satellite remote sensing as a method for measuring yield variabili...Evaluating satellite remote sensing as a method for measuring yield variabili...
Evaluating satellite remote sensing as a method for measuring yield variabili...
Amanda Woods
 
AgDNA maximising field level profitability using IoT and data automation
AgDNA maximising field level profitability using IoT and data automationAgDNA maximising field level profitability using IoT and data automation
AgDNA maximising field level profitability using IoT and data automation
Amanda Woods
 
Precision Agriculture Apps and Mapping
Precision Agriculture Apps and MappingPrecision Agriculture Apps and Mapping
Precision Agriculture Apps and Mapping
Amanda Woods
 
Weed Mapping by Andrew Newall, SPAA Expo 16
Weed Mapping by Andrew Newall, SPAA Expo 16 Weed Mapping by Andrew Newall, SPAA Expo 16
Weed Mapping by Andrew Newall, SPAA Expo 16
Amanda Woods
 

More from Amanda Woods (20)

Hire for Baby Australia Franchise Business model slide
Hire for Baby Australia Franchise Business model slideHire for Baby Australia Franchise Business model slide
Hire for Baby Australia Franchise Business model slide
 
SPAA Precision Ag News magazine Vol 12 Issue 3 Winter 2016
SPAA Precision Ag News magazine Vol 12 Issue 3 Winter 2016SPAA Precision Ag News magazine Vol 12 Issue 3 Winter 2016
SPAA Precision Ag News magazine Vol 12 Issue 3 Winter 2016
 
SPAA Precision Agriculture in Practise II Book in Case Studies
SPAA Precision Agriculture in Practise II Book in Case StudiesSPAA Precision Agriculture in Practise II Book in Case Studies
SPAA Precision Agriculture in Practise II Book in Case Studies
 
Weed Sensing SPAA Precision Agriculture Factsheet 2016
Weed Sensing SPAA Precision Agriculture Factsheet 2016Weed Sensing SPAA Precision Agriculture Factsheet 2016
Weed Sensing SPAA Precision Agriculture Factsheet 2016
 
Airborne Imagery SPAA Precision Agriculture factsheet 2016
Airborne Imagery SPAA Precision Agriculture factsheet 2016Airborne Imagery SPAA Precision Agriculture factsheet 2016
Airborne Imagery SPAA Precision Agriculture factsheet 2016
 
Controlled Traffic Farming Precision SPAA Agriculture Factsheet
Controlled Traffic Farming Precision SPAA Agriculture FactsheetControlled Traffic Farming Precision SPAA Agriculture Factsheet
Controlled Traffic Farming Precision SPAA Agriculture Factsheet
 
A Guide to Using Precision Viticulture Case Studies from the Grampians and Ya...
A Guide to Using Precision Viticulture Case Studies from the Grampians and Ya...A Guide to Using Precision Viticulture Case Studies from the Grampians and Ya...
A Guide to Using Precision Viticulture Case Studies from the Grampians and Ya...
 
Precision Viticulture FactSheet by SPAA Australia 2015
Precision Viticulture FactSheet by SPAA Australia 2015Precision Viticulture FactSheet by SPAA Australia 2015
Precision Viticulture FactSheet by SPAA Australia 2015
 
UAV Drone Mapping of Rhizoctonia bare patch for targeted treatment by Andrea ...
UAV Drone Mapping of Rhizoctonia bare patch for targeted treatment by Andrea ...UAV Drone Mapping of Rhizoctonia bare patch for targeted treatment by Andrea ...
UAV Drone Mapping of Rhizoctonia bare patch for targeted treatment by Andrea ...
 
Does Optimum Surface Landforming offer Precision Agriculture's Highest ROI? D...
Does Optimum Surface Landforming offer Precision Agriculture's Highest ROI? D...Does Optimum Surface Landforming offer Precision Agriculture's Highest ROI? D...
Does Optimum Surface Landforming offer Precision Agriculture's Highest ROI? D...
 
PPMS: Cattle and Pasture Production without the sweat by Sally Leigo
PPMS: Cattle and Pasture Production without the sweat by Sally LeigoPPMS: Cattle and Pasture Production without the sweat by Sally Leigo
PPMS: Cattle and Pasture Production without the sweat by Sally Leigo
 
Knowledge Management, sensing and control tools for irrigated broadacre cropping
Knowledge Management, sensing and control tools for irrigated broadacre croppingKnowledge Management, sensing and control tools for irrigated broadacre cropping
Knowledge Management, sensing and control tools for irrigated broadacre cropping
 
Big ideas for using data by Brett Whelan University of Sydney
Big ideas for using data by Brett Whelan University of SydneyBig ideas for using data by Brett Whelan University of Sydney
Big ideas for using data by Brett Whelan University of Sydney
 
101 ways to make precision agriculture work in Qld vegetables Sarah Limpus, I...
101 ways to make precision agriculture work in Qld vegetables Sarah Limpus, I...101 ways to make precision agriculture work in Qld vegetables Sarah Limpus, I...
101 ways to make precision agriculture work in Qld vegetables Sarah Limpus, I...
 
Pest & Disease Survelliance & New Technologies by Rohan Kimber
Pest & Disease Survelliance & New Technologies by Rohan KimberPest & Disease Survelliance & New Technologies by Rohan Kimber
Pest & Disease Survelliance & New Technologies by Rohan Kimber
 
Big Data for Informed Decisions by Lisa Prassack, Prassack Advisors
Big Data for Informed Decisions by Lisa Prassack, Prassack AdvisorsBig Data for Informed Decisions by Lisa Prassack, Prassack Advisors
Big Data for Informed Decisions by Lisa Prassack, Prassack Advisors
 
Evaluating satellite remote sensing as a method for measuring yield variabili...
Evaluating satellite remote sensing as a method for measuring yield variabili...Evaluating satellite remote sensing as a method for measuring yield variabili...
Evaluating satellite remote sensing as a method for measuring yield variabili...
 
AgDNA maximising field level profitability using IoT and data automation
AgDNA maximising field level profitability using IoT and data automationAgDNA maximising field level profitability using IoT and data automation
AgDNA maximising field level profitability using IoT and data automation
 
Precision Agriculture Apps and Mapping
Precision Agriculture Apps and MappingPrecision Agriculture Apps and Mapping
Precision Agriculture Apps and Mapping
 
Weed Mapping by Andrew Newall, SPAA Expo 16
Weed Mapping by Andrew Newall, SPAA Expo 16 Weed Mapping by Andrew Newall, SPAA Expo 16
Weed Mapping by Andrew Newall, SPAA Expo 16
 

Recently uploaded

SAP Sapphire 2024 - ASUG301 building better apps with SAP Fiori.pdf
SAP Sapphire 2024 - ASUG301 building better apps with SAP Fiori.pdfSAP Sapphire 2024 - ASUG301 building better apps with SAP Fiori.pdf
SAP Sapphire 2024 - ASUG301 building better apps with SAP Fiori.pdf
Peter Spielvogel
 
Epistemic Interaction - tuning interfaces to provide information for AI support
Epistemic Interaction - tuning interfaces to provide information for AI supportEpistemic Interaction - tuning interfaces to provide information for AI support
Epistemic Interaction - tuning interfaces to provide information for AI support
Alan Dix
 
Assure Contact Center Experiences for Your Customers With ThousandEyes
Assure Contact Center Experiences for Your Customers With ThousandEyesAssure Contact Center Experiences for Your Customers With ThousandEyes
Assure Contact Center Experiences for Your Customers With ThousandEyes
ThousandEyes
 
Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...
Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...
Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...
James Anderson
 
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 previewState of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
Prayukth K V
 
Free Complete Python - A step towards Data Science
Free Complete Python - A step towards Data ScienceFree Complete Python - A step towards Data Science
Free Complete Python - A step towards Data Science
RinaMondal9
 
Quantum Computing: Current Landscape and the Future Role of APIs
Quantum Computing: Current Landscape and the Future Role of APIsQuantum Computing: Current Landscape and the Future Role of APIs
Quantum Computing: Current Landscape and the Future Role of APIs
Vlad Stirbu
 
PCI PIN Basics Webinar from the Controlcase Team
PCI PIN Basics Webinar from the Controlcase TeamPCI PIN Basics Webinar from the Controlcase Team
PCI PIN Basics Webinar from the Controlcase Team
ControlCase
 
FIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdfFIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance
 
Pushing the limits of ePRTC: 100ns holdover for 100 days
Pushing the limits of ePRTC: 100ns holdover for 100 daysPushing the limits of ePRTC: 100ns holdover for 100 days
Pushing the limits of ePRTC: 100ns holdover for 100 days
Adtran
 
GraphRAG is All You need? LLM & Knowledge Graph
GraphRAG is All You need? LLM & Knowledge GraphGraphRAG is All You need? LLM & Knowledge Graph
GraphRAG is All You need? LLM & Knowledge Graph
Guy Korland
 
Climate Impact of Software Testing at Nordic Testing Days
Climate Impact of Software Testing at Nordic Testing DaysClimate Impact of Software Testing at Nordic Testing Days
Climate Impact of Software Testing at Nordic Testing Days
Kari Kakkonen
 
GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...
GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...
GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...
Sri Ambati
 
Elevating Tactical DDD Patterns Through Object Calisthenics
Elevating Tactical DDD Patterns Through Object CalisthenicsElevating Tactical DDD Patterns Through Object Calisthenics
Elevating Tactical DDD Patterns Through Object Calisthenics
Dorra BARTAGUIZ
 
The Future of Platform Engineering
The Future of Platform EngineeringThe Future of Platform Engineering
The Future of Platform Engineering
Jemma Hussein Allen
 
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdfFIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance
 
RESUME BUILDER APPLICATION Project for students
RESUME BUILDER APPLICATION Project for studentsRESUME BUILDER APPLICATION Project for students
RESUME BUILDER APPLICATION Project for students
KAMESHS29
 
Accelerate your Kubernetes clusters with Varnish Caching
Accelerate your Kubernetes clusters with Varnish CachingAccelerate your Kubernetes clusters with Varnish Caching
Accelerate your Kubernetes clusters with Varnish Caching
Thijs Feryn
 
Secstrike : Reverse Engineering & Pwnable tools for CTF.pptx
Secstrike : Reverse Engineering & Pwnable tools for CTF.pptxSecstrike : Reverse Engineering & Pwnable tools for CTF.pptx
Secstrike : Reverse Engineering & Pwnable tools for CTF.pptx
nkrafacyberclub
 
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdfObservability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
Paige Cruz
 

Recently uploaded (20)

SAP Sapphire 2024 - ASUG301 building better apps with SAP Fiori.pdf
SAP Sapphire 2024 - ASUG301 building better apps with SAP Fiori.pdfSAP Sapphire 2024 - ASUG301 building better apps with SAP Fiori.pdf
SAP Sapphire 2024 - ASUG301 building better apps with SAP Fiori.pdf
 
Epistemic Interaction - tuning interfaces to provide information for AI support
Epistemic Interaction - tuning interfaces to provide information for AI supportEpistemic Interaction - tuning interfaces to provide information for AI support
Epistemic Interaction - tuning interfaces to provide information for AI support
 
Assure Contact Center Experiences for Your Customers With ThousandEyes
Assure Contact Center Experiences for Your Customers With ThousandEyesAssure Contact Center Experiences for Your Customers With ThousandEyes
Assure Contact Center Experiences for Your Customers With ThousandEyes
 
Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...
Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...
Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...
 
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 previewState of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
 
Free Complete Python - A step towards Data Science
Free Complete Python - A step towards Data ScienceFree Complete Python - A step towards Data Science
Free Complete Python - A step towards Data Science
 
Quantum Computing: Current Landscape and the Future Role of APIs
Quantum Computing: Current Landscape and the Future Role of APIsQuantum Computing: Current Landscape and the Future Role of APIs
Quantum Computing: Current Landscape and the Future Role of APIs
 
PCI PIN Basics Webinar from the Controlcase Team
PCI PIN Basics Webinar from the Controlcase TeamPCI PIN Basics Webinar from the Controlcase Team
PCI PIN Basics Webinar from the Controlcase Team
 
FIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdfFIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdf
 
Pushing the limits of ePRTC: 100ns holdover for 100 days
Pushing the limits of ePRTC: 100ns holdover for 100 daysPushing the limits of ePRTC: 100ns holdover for 100 days
Pushing the limits of ePRTC: 100ns holdover for 100 days
 
GraphRAG is All You need? LLM & Knowledge Graph
GraphRAG is All You need? LLM & Knowledge GraphGraphRAG is All You need? LLM & Knowledge Graph
GraphRAG is All You need? LLM & Knowledge Graph
 
Climate Impact of Software Testing at Nordic Testing Days
Climate Impact of Software Testing at Nordic Testing DaysClimate Impact of Software Testing at Nordic Testing Days
Climate Impact of Software Testing at Nordic Testing Days
 
GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...
GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...
GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...
 
Elevating Tactical DDD Patterns Through Object Calisthenics
Elevating Tactical DDD Patterns Through Object CalisthenicsElevating Tactical DDD Patterns Through Object Calisthenics
Elevating Tactical DDD Patterns Through Object Calisthenics
 
The Future of Platform Engineering
The Future of Platform EngineeringThe Future of Platform Engineering
The Future of Platform Engineering
 
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdfFIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
 
RESUME BUILDER APPLICATION Project for students
RESUME BUILDER APPLICATION Project for studentsRESUME BUILDER APPLICATION Project for students
RESUME BUILDER APPLICATION Project for students
 
Accelerate your Kubernetes clusters with Varnish Caching
Accelerate your Kubernetes clusters with Varnish CachingAccelerate your Kubernetes clusters with Varnish Caching
Accelerate your Kubernetes clusters with Varnish Caching
 
Secstrike : Reverse Engineering & Pwnable tools for CTF.pptx
Secstrike : Reverse Engineering & Pwnable tools for CTF.pptxSecstrike : Reverse Engineering & Pwnable tools for CTF.pptx
Secstrike : Reverse Engineering & Pwnable tools for CTF.pptx
 
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdfObservability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
 

Real-time pasture biomass estimation by Karl Andersson

  • 1. Real-time pasture biomass estimation Mark Trotter, Karl Andersson, Andrew Robson, Derek Schneider, Ashley Saint, Lucy Frizell Participant teams: Lewis Kahn, Paul Reynolds, Tony Butler, Brad Wooldridge, Chris Blore, Peter Schroder, Jim Shovelton, Ian Gamble
  • 2. B.GSM.0010, P4.18 Real Time Pasture Biomass Estimation
  • 3.
  • 4. Aims and why What we’re doing Some results Mobile app Future directions
  • 5. Aims 1. Evaluate the potential for Active Optical Sensors (AOS) 2. Develop a series calibrations for use by producers 3. Develop a Mobile Device Application (MDA) to support AOS
  • 6. Aims: Current biomass Growth rate Paddock 963 23 Black leg 750 21 Plumb tree 894 25 Parkers 675 11 Parkers west 762 18 Gumtree 1 1256 31 Gumtree 2 1766 34 500 1000 1500 Export data
  • 7. Why? Pasture utilisation Estimate biomass compared to benchmarks Help make objective decisions on stocking rates Calibrate other methods (e.g. pastures from space)
  • 8. Why?  Pasture utilisation  Help make objective decisions on stocking rates  Estimate biomass compared to benchmarks  Calibrate other methods (e.g. pastures from space)
  • 9. Why?  Pasture utilisation  Help make objective decisions on stocking rates  Estimate biomass compared to benchmarks  Calibrate other methods (e.g. pastures from space)
  • 10. Why?  Pasture utilisation  Help make objective decisions on stocking rates  Estimate biomass compared to benchmarks  Calibrate other methods
  • 11. Correlating sensors to GDM…  >200 samples taken from across Australia  Each sample consists of 8-12 individual cuts  Each site is scanned with a Greenseeker Handheld  Height measured by plate meter  Digital image (before and after cut)  Quadrat is harvested using clippers or knives – cut to ground
  • 12. Preliminary results… • The ok, more common • Tablelands Fescue • The good, • Tasmanian Ryegrass
  • 13. Preliminary results… • The problems… • Poor calibrations • NDVI Saturation
  • 14.
  • 16. Season State Species Input variable Model type Model R2 1 Winter NSW Fescue NDVI*Height LM -204 + 368.8 x 0.95 2 Winter Vic Ryegrass NDVI*Height GLM exp^(6.1 + 0.21 x) 0.79 3 Winter Vic Phalaris_Ryegrass NDVI*Height LM -189 + 244.7 x 0.68 4 Winter Vic Phalaris NDVIxLHt LM -62 + 862.3 x 0.67 5 Winter Vic Mixed LNDVI LM -22 -811.5 x 0.33 6 Winter NSW Fescue NDVI GLM exp^(4.2 + 5.75 x) 0.91 7 Winter NSW Lucerne NDVI LM -571 + 2464.7 x 0.92 8 Winter Vic Mixed NDVI LM -75157 + 104337.6 x 0.6 9 Winter Vic Phalaris_Clover NDVIxLHt LM -167 + 945.8 x 0.93 10 Winter Vic Phalaris LHt LM -1378 + 1731.9 x 0.75 11 Winter Vic Phalaris_Ryegrass_Clove r LHt LM -835 + 1509.6 x 0.53 12 Winter Vic Phalaris_Clover NDVIxLHt GLM exp^(4.9 + 1.35 x) 0.86 14 Winter NSW Fescue LNDVI GLM exp^(9.2 + 2.61 x) 0.95 15 Winter Vic Phalaris_Clover NDVIxLHt QLM -30 + 456.1 x + 178.8 x^2 0.92 16 Winter Vic Phalaris LNDVI GLM exp^(9.1 + 10.2 x) 0.73 17 Winter Vic Ryegrass NDVI*Height GLM exp^(4.4 + 0.41 x) 0.71 18 Winter Vic Phalaris_Clover NDVIxLHt LM -347 + 1613.8 x 0.81 19 Winter Vic Phalaris_Ryegrass_Clove r Height GLM exp^(6.7 + 0.15 x) 0.84 20 Spring Vic Ryegrass NDVI*Height LM 925 + 256.1 x 0.87 23 Spring Vic Phalaris_Clover NDVI*Height GLM exp^(8.1 + 0.14 x) 0.47 24 Spring NSW Fescue NDVIxLHt LM -592 + 2141.8 x 0.87 25 Spring NSW Lucerne NDVI GLM exp^(2.2 + 6.79 x) 0.76 26 Spring NSW Phalaris LHt LM -93 + 1113.7 x 0.96 27 Spring Vic Mixed LHt GLM exp^(3.3 + 1.72 x) 0.72 28 Spring Vic Mixed NDVI*Height LM 1333 + 443.3 x 0.51 29 Spring Vic Ryegrass NDVI GLM exp^(-5.9 + 16.2 x) 0.68 30 Spring Vic Phalaris NDVIxLHt GLM exp^(4.6 + 1.64 x) 0.89 31 Spring Vic Phalaris_Clover Height LM 242 + 191.2 x 0.92 32 Spring NSW Cocksfoot_Fescue NDVIxLHt LM -348 + 2069.1 x 0.7 33 Spring NSW Cocksfoot_Fescue_Clove r LNDVI GLM exp^(8.4 + 1.88 x) 0.71 34 Spring Vic Ryegrass_Clover NDVI*Height GLM exp^(6.5 + 0.12 x) 0.86 35 Spring Vic Phalaris_Clover NDVIxLHt LM -75 + 1418.4 x 0.91 36 Spring NSW Fescue_Clover NDVIxLHt LM -60 + 1145.7 x 0.65 37 Spring NSW Ryegrass NDVI LM -578 + 5083.8 x 0.63 38 Spring NSW Fescue NDVIxLHt LM 174 + 1641.4 x 0.74 39 Spring NSW Mixed NDVIxLHt LM -633 + 2381.6 x 0.9 40 Spring Vic Mixed LNDVI LM 8218 + 7283.1 x 0.82 41 Spring Vic Ryegrass NDVIxLHt LM -1112 + 2783.3 x 0.9 42 Spring Vic Phalaris_Ryegrass_Clove r LNDVI LM 3410 + 2241.5 x 0.83 43 Spring Vic Phalaris Clover NDVIxLHt LM 91 + 2256 8 x 0 95
  • 17.
  • 18. Solutions?  We examined other reflectance bands  Excellent correlation but not consistent  The best co- variate turns out to be plate height. Question % of possible  sites  Proportion of sites where ACS470 bands are better than GS NDVI?  97% Proportion of these sites where there is a substantive improvement (increase of  more than r2  0.10)?  71% Proportion of sites where ACS470 bands are better than GS NDVI, Height or a  combination?  78% Proportion of these sites where there is a substantive improvement (increase of  more than r2  0.10)?  29% Date  State  Locatio n  Species/past ure type  Best 2 band  sensor model  r2   Best 3 band sensor  model  r2       4/06/2014 NSW UNE  Fescue  Fescue Ln GDM = Ln  NDVI ((760‐ 700)/760+700)  0.83 Ln GDM = Band 590,  Ln Band 730  0.86  23/06/2014 NSW Sundow n  Lucerne  GDM = Ln SR  (590/730)  0.91 GDM = SR  (590/730), SR  (730/760)  0.95  23/06/2014 NSW Sundow n  Fescue GDM = SR  (590/670)  0.93 GDM = SR(730/670),  SR(760/590)  0.95  25/07/2014 NSW Sundow n  Fescue Ln GDM =  SR(530/760)  0.96 Ln GDM = Band 730,  Ln NDVI ((760‐ 530)/760+530))  0.98  18/09/2015 NSW Sundow n  Lucerne  GDM = Ln((760‐ 530)/760+530))  0.93 Ln GDM =  SR(760/730), Ln  Band 700  0.98  18/09/2014 NSW Sundow n  Fescue Ln GDM = Band   530  0.85 Ln GDM = Ln Band  760, NDVI ((760‐ 530)/760+530))  0.90  23/09/2014 NSW Kirby Phalaris  GDM = NDVI  ((760‐ 730)/(760+730))  0.88 GDM = Ln  SR(670/760), Ln  SR(700/730)  0.98   
  • 20. Region     Combined  Winter+Spring All cuts Northern  Tablelands  r2   0.70 0.45 n  289 545 Mean 2191 2616 RMSE  982 1312 Central  Victoria  r2   0.77    n  66 Mean  1373 RMSE  541    Southern  Victoria  r2   0.62    n  82 Mean  1743 RMSE 375 Western  Victoria  r2   0.77    n  326 Mean  1206 RMSE  469    Tasmania  r2   0.66 0.68 n  82 153 Mean  1189 1120 RMSE  403 380
  • 21. WA and SA pastures
  • 22. 0 units 21 units 42 units 63 units 0.51 0.55 0.65 0.78
  • 23.
  • 24.
  • 25.
  • 27. Where to from here?  Integrate with weather and satellite data  Integrate with LiDAR  Integration with feed budgeting/stocking rate software  Quality and pasture growth rates
  • 29. Dealing with calibration shifts… NDVI profiling
  • 32. Take home messages  NDVI from affordable AOS have the potential to provide pastures biomass estimates  In many pastures, the inclusion of height measures improved the correlation with GDM, and was a better universal covariate than other AOS bands  Work is still to be done to validate estimates, and provide seasonal, regional, species and calibrations  LiDAR may provide convenient height measures, though further development is required