SlideShare a Scribd company logo
The Dynamic Aerial Survey
       Algorithm




    Precision Fertiliser Applications
        Falzon GA, Lamb DW & Schneider DA
Overview
The Need for Top-dress Fertilisers.
The Advent of Active Optical Sensors.
Real-Time Aerial Crop Survey & its
Challenges.
The Solution: DAS.
Future Developments.
Top-Dress Fertilisers
Irrigated durum wheat: 2 applications of
N/season
322 kg N/ha, $A309.84/ha (July 2011).
300 ha cereal feld requires $A92,952
N/application and $A185,904 total.
Extra on-costs! Aircraft cost $A7000-
$A10000/9ight.
We need greater effciency!!!
Active-Optical Sensors
CropCircleTM ACS210 'red head' & GeoSCOUT 400 data-logger

λ 1=650nm   (red)                      λ 2=880nm   (NIR)




                                      4.00m


                           2.28m
                                             m
                                        0.44
Real-Time Aerial Survey
Fletcher FU24954 aircraft
Garmin GPS18 5Hz
On-The-Go Sensing: 80 kts = 144 km/h




Can we create an accurate prescription map after each
pass?
The DAS Algorithm: Pt I

                                    Paddock Polygons
                                     cumulative passes




                         Ragged Arrays
           geo-referenced samples: different dimensions
The DAS Algorithm: Pt II
The DAS Algorithm: Pt III

             Support Vector Machines
                        Nk
              f ( z)=∑i=1 [β −β K ( z i , z)+β0 ]
                              1
                              i
                                  2
                                  i

                         Kernels
Polynomial                   Radial                 Sigmoid
     T   n
(γ z⋅z +κ)                  −∣z−z T∣                     T
                                                tanh (γ z⋅z +κ)
                        exp(     2
                                     )
                              2σ
The DAS Algorithm: Pt IV
The DAS Algorithm: Pt V
Divide f ( z) into prescription zones
                     M P =( M 1, P ,… , M N , P )




Pre-set Levels e.g. NDVI = {0.0,0.2,0.4,0.6,0.8}
Divide into N levels e.g. n = 10
K-means clustering, e.g. cluster into three groups (low, med, high).
The DAS Algorithm: In
       Action
Future Developments

       Incorporate Prior Information
Prior survey results
Additional information such as soil surveys
and yield maps
Expert knowledge
Future Developments

           Joint Air-Ground Operations
Extension of Prior Survey Models.
Ground Validation, Small Scale Areas, Combined
Air/Ground Fertiliser Teams.
          Field Calibration & Validations
Wind shear, height, droplet size (I. Yule), servo latency.
Compare drop zone to management map.
Thank you!
M. Trotter (UNE PARG)
SUPERAIR
CRC for Spatial Information (CRCSI)
Sugar Research & Development Corporation (SRDC)
Nick Barton (Twynam Agriculture)
Andrew Smart (Precision Cropping Technologies)
Nick Gillingham (Sundown Pastoral Company)
Dr. F. Honey (SpecTerra Services)

More Related Content

What's hot

10 10-12 tf communications
10 10-12 tf  communications10 10-12 tf  communications
10 10-12 tf communications
Sean C. Casey, PhD, MBA
 
Spectral Analysis at the Limit - Applications in Radio Astronomy
Spectral Analysis at the Limit - Applications in Radio AstronomySpectral Analysis at the Limit - Applications in Radio Astronomy
Spectral Analysis at the Limit - Applications in Radio Astronomy
Hochschule für Technik FHNW
 
Applied maths for electronics engineers june 2013 (2)
Applied maths for electronics engineers june 2013 (2)Applied maths for electronics engineers june 2013 (2)
Applied maths for electronics engineers june 2013 (2)
SRI TECHNOLOGICAL SOLUTIONS
 
FOSDEM 2015: Distributed Tile Processing with GeoTrellis and Spark
FOSDEM 2015: Distributed Tile Processing with GeoTrellis and SparkFOSDEM 2015: Distributed Tile Processing with GeoTrellis and Spark
FOSDEM 2015: Distributed Tile Processing with GeoTrellis and Spark
Rob Emanuele
 
LHCb Computing Workshop 2018: PV finding with CNNs
LHCb Computing Workshop 2018: PV finding with CNNsLHCb Computing Workshop 2018: PV finding with CNNs
LHCb Computing Workshop 2018: PV finding with CNNs
Henry Schreiner
 
Parallel Wavelet Schemes for Images
Parallel Wavelet Schemes for ImagesParallel Wavelet Schemes for Images
Parallel Wavelet Schemes for Images
David Bařina
 
AIP seminar - ARCHES WP6
AIP seminar - ARCHES WP6AIP seminar - ARCHES WP6
AIP seminar - ARCHES WP6
Alexey Mints
 
Molecular Variation of Potato virus Y Isolated from Egypt
Molecular Variation of Potato virus Y Isolated from EgyptMolecular Variation of Potato virus Y Isolated from Egypt
Molecular Variation of Potato virus Y Isolated from Egypt
Medhat Helmy
 
IGARSS2011_TU1.T03.2_Zhan.ppt
IGARSS2011_TU1.T03.2_Zhan.pptIGARSS2011_TU1.T03.2_Zhan.ppt
IGARSS2011_TU1.T03.2_Zhan.ppt
grssieee
 
Q4 2016 GeoTrellis Presentation
Q4 2016 GeoTrellis PresentationQ4 2016 GeoTrellis Presentation
Q4 2016 GeoTrellis Presentation
Rob Emanuele
 
FIBRE presentation at GEC25
FIBRE presentation at GEC25FIBRE presentation at GEC25
FIBRE presentation at GEC25
FIBRE Testbed
 
hadoop introduce
hadoop introducehadoop introduce
hadoop introduce
justlooks
 
Raster Processing with Scipy.ndimage (Dev Meet Up II)
Raster Processing with Scipy.ndimage (Dev Meet Up II)Raster Processing with Scipy.ndimage (Dev Meet Up II)
Raster Processing with Scipy.ndimage (Dev Meet Up II)
JHasthorpe
 
PREDICTING THE TIME OF OBLIVIOUS PROGRAMS. Euromicro 2001
PREDICTING THE TIME OF OBLIVIOUS PROGRAMS. Euromicro 2001PREDICTING THE TIME OF OBLIVIOUS PROGRAMS. Euromicro 2001
PREDICTING THE TIME OF OBLIVIOUS PROGRAMS. Euromicro 2001
Casiano Rodriguez-leon
 
PREDICTING THE TIME OF OBLIVIOUS PROGRAMS. Euromicro 2001
PREDICTING THE TIME OF OBLIVIOUS PROGRAMS. Euromicro 2001PREDICTING THE TIME OF OBLIVIOUS PROGRAMS. Euromicro 2001
PREDICTING THE TIME OF OBLIVIOUS PROGRAMS. Euromicro 2001
Casiano Rodriguez-leon
 
G2+ worldwide positioning services
G2+ worldwide positioning servicesG2+ worldwide positioning services
G2+ worldwide positioning services
Hydrographic Society Benelux
 
LIDAR-derived DTM for archaeology and landscape history research some recent ...
LIDAR-derived DTM for archaeology and landscape history research some recent ...LIDAR-derived DTM for archaeology and landscape history research some recent ...
LIDAR-derived DTM for archaeology and landscape history research some recent ...
Shaun Lewis
 
Core B-H Curve Simulation using LTspice
Core B-H Curve Simulation using LTspiceCore B-H Curve Simulation using LTspice
Core B-H Curve Simulation using LTspice
Tsuyoshi Horigome
 
Application of HDF/HDF-EOS data to atmospheric and climate sciences at Univer...
Application of HDF/HDF-EOS data to atmospheric and climate sciences at Univer...Application of HDF/HDF-EOS data to atmospheric and climate sciences at Univer...
Application of HDF/HDF-EOS data to atmospheric and climate sciences at Univer...
The HDF-EOS Tools and Information Center
 
Core B-H Curve Simulation using LTspice
Core B-H Curve Simulation using LTspiceCore B-H Curve Simulation using LTspice
Core B-H Curve Simulation using LTspice
Tsuyoshi Horigome
 

What's hot (20)

10 10-12 tf communications
10 10-12 tf  communications10 10-12 tf  communications
10 10-12 tf communications
 
Spectral Analysis at the Limit - Applications in Radio Astronomy
Spectral Analysis at the Limit - Applications in Radio AstronomySpectral Analysis at the Limit - Applications in Radio Astronomy
Spectral Analysis at the Limit - Applications in Radio Astronomy
 
Applied maths for electronics engineers june 2013 (2)
Applied maths for electronics engineers june 2013 (2)Applied maths for electronics engineers june 2013 (2)
Applied maths for electronics engineers june 2013 (2)
 
FOSDEM 2015: Distributed Tile Processing with GeoTrellis and Spark
FOSDEM 2015: Distributed Tile Processing with GeoTrellis and SparkFOSDEM 2015: Distributed Tile Processing with GeoTrellis and Spark
FOSDEM 2015: Distributed Tile Processing with GeoTrellis and Spark
 
LHCb Computing Workshop 2018: PV finding with CNNs
LHCb Computing Workshop 2018: PV finding with CNNsLHCb Computing Workshop 2018: PV finding with CNNs
LHCb Computing Workshop 2018: PV finding with CNNs
 
Parallel Wavelet Schemes for Images
Parallel Wavelet Schemes for ImagesParallel Wavelet Schemes for Images
Parallel Wavelet Schemes for Images
 
AIP seminar - ARCHES WP6
AIP seminar - ARCHES WP6AIP seminar - ARCHES WP6
AIP seminar - ARCHES WP6
 
Molecular Variation of Potato virus Y Isolated from Egypt
Molecular Variation of Potato virus Y Isolated from EgyptMolecular Variation of Potato virus Y Isolated from Egypt
Molecular Variation of Potato virus Y Isolated from Egypt
 
IGARSS2011_TU1.T03.2_Zhan.ppt
IGARSS2011_TU1.T03.2_Zhan.pptIGARSS2011_TU1.T03.2_Zhan.ppt
IGARSS2011_TU1.T03.2_Zhan.ppt
 
Q4 2016 GeoTrellis Presentation
Q4 2016 GeoTrellis PresentationQ4 2016 GeoTrellis Presentation
Q4 2016 GeoTrellis Presentation
 
FIBRE presentation at GEC25
FIBRE presentation at GEC25FIBRE presentation at GEC25
FIBRE presentation at GEC25
 
hadoop introduce
hadoop introducehadoop introduce
hadoop introduce
 
Raster Processing with Scipy.ndimage (Dev Meet Up II)
Raster Processing with Scipy.ndimage (Dev Meet Up II)Raster Processing with Scipy.ndimage (Dev Meet Up II)
Raster Processing with Scipy.ndimage (Dev Meet Up II)
 
PREDICTING THE TIME OF OBLIVIOUS PROGRAMS. Euromicro 2001
PREDICTING THE TIME OF OBLIVIOUS PROGRAMS. Euromicro 2001PREDICTING THE TIME OF OBLIVIOUS PROGRAMS. Euromicro 2001
PREDICTING THE TIME OF OBLIVIOUS PROGRAMS. Euromicro 2001
 
PREDICTING THE TIME OF OBLIVIOUS PROGRAMS. Euromicro 2001
PREDICTING THE TIME OF OBLIVIOUS PROGRAMS. Euromicro 2001PREDICTING THE TIME OF OBLIVIOUS PROGRAMS. Euromicro 2001
PREDICTING THE TIME OF OBLIVIOUS PROGRAMS. Euromicro 2001
 
G2+ worldwide positioning services
G2+ worldwide positioning servicesG2+ worldwide positioning services
G2+ worldwide positioning services
 
LIDAR-derived DTM for archaeology and landscape history research some recent ...
LIDAR-derived DTM for archaeology and landscape history research some recent ...LIDAR-derived DTM for archaeology and landscape history research some recent ...
LIDAR-derived DTM for archaeology and landscape history research some recent ...
 
Core B-H Curve Simulation using LTspice
Core B-H Curve Simulation using LTspiceCore B-H Curve Simulation using LTspice
Core B-H Curve Simulation using LTspice
 
Application of HDF/HDF-EOS data to atmospheric and climate sciences at Univer...
Application of HDF/HDF-EOS data to atmospheric and climate sciences at Univer...Application of HDF/HDF-EOS data to atmospheric and climate sciences at Univer...
Application of HDF/HDF-EOS data to atmospheric and climate sciences at Univer...
 
Core B-H Curve Simulation using LTspice
Core B-H Curve Simulation using LTspiceCore B-H Curve Simulation using LTspice
Core B-H Curve Simulation using LTspice
 

Similar to Falzon Das Se Ag Compressed

An evaluation of gnss code and phase solutions
An evaluation of gnss code and phase solutionsAn evaluation of gnss code and phase solutions
An evaluation of gnss code and phase solutions
Alexander Decker
 
Foss4g2009tokyo Realini Go Gps
Foss4g2009tokyo Realini Go GpsFoss4g2009tokyo Realini Go Gps
Foss4g2009tokyo Realini Go Gps
OSgeo Japan
 
Signal Processing Algorithms for MIMO Radar
Signal Processing Algorithms for MIMO RadarSignal Processing Algorithms for MIMO Radar
Signal Processing Algorithms for MIMO Radar
sansam77
 
How gps works
How gps worksHow gps works
How gps works
jotugill
 
Second Order Perturbations During Inflation Beyond Slow-roll
Second Order Perturbations During Inflation Beyond Slow-rollSecond Order Perturbations During Inflation Beyond Slow-roll
Second Order Perturbations During Inflation Beyond Slow-roll
Ian Huston
 
How gps works
How gps worksHow gps works
How gps works
chintanmehta007
 
Selm Falzon Compressed
Selm Falzon CompressedSelm Falzon Compressed
Selm Falzon Compressed
gfalzon2
 
goGPS (March 2010)
goGPS (March 2010)goGPS (March 2010)
goGPS (March 2010)
Eugenio Realini
 
Chap2 ofdm basics
Chap2 ofdm basicsChap2 ofdm basics
Chap2 ofdm basics
Karuthapandi A
 
2_prats_IGARSS2011_distributed_imaging_v4.ppt
2_prats_IGARSS2011_distributed_imaging_v4.ppt2_prats_IGARSS2011_distributed_imaging_v4.ppt
2_prats_IGARSS2011_distributed_imaging_v4.ppt
grssieee
 
Real Time Spectroscopy
Real Time SpectroscopyReal Time Spectroscopy
Real Time Spectroscopy
Claudio Attaccalite
 
Bloco2 produtos gerados_pelo_inpe
Bloco2 produtos gerados_pelo_inpeBloco2 produtos gerados_pelo_inpe
Bloco2 produtos gerados_pelo_inpe
Dafmet Ufpel
 
Modal Analysis Basic Theory
Modal Analysis Basic TheoryModal Analysis Basic Theory
Modal Analysis Basic Theory
YuanCheng38
 
CELEBRATION 2000 (3rd Deployment) & ALP 2002 Generation of a 3D-Model of the ...
CELEBRATION 2000 (3rd Deployment) & ALP 2002Generation of a 3D-Model of the ...CELEBRATION 2000 (3rd Deployment) & ALP 2002Generation of a 3D-Model of the ...
CELEBRATION 2000 (3rd Deployment) & ALP 2002 Generation of a 3D-Model of the ...
gigax2
 
射頻電子 - [第六章] 低雜訊放大器設計
射頻電子 - [第六章] 低雜訊放大器設計射頻電子 - [第六章] 低雜訊放大器設計
射頻電子 - [第六章] 低雜訊放大器設計
Simen Li
 
CAPACITIVE SENSORS ELECTRICAL WAFER SORT
CAPACITIVE SENSORS ELECTRICAL WAFER SORTCAPACITIVE SENSORS ELECTRICAL WAFER SORT
CAPACITIVE SENSORS ELECTRICAL WAFER SORT
Massimo Garavaglia
 
MUMS Opening Workshop - Model Uncertainty in Data Fusion for Remote Sensing -...
MUMS Opening Workshop - Model Uncertainty in Data Fusion for Remote Sensing -...MUMS Opening Workshop - Model Uncertainty in Data Fusion for Remote Sensing -...
MUMS Opening Workshop - Model Uncertainty in Data Fusion for Remote Sensing -...
The Statistical and Applied Mathematical Sciences Institute
 
2.5 pda-capwap - gray
2.5   pda-capwap - gray2.5   pda-capwap - gray
2.5 pda-capwap - gray
cfpbolivia
 
Pda capwap - frank rausche
Pda capwap - frank rauschePda capwap - frank rausche
Pda capwap - frank rausche
cfpbolivia
 
Lb2519271931
Lb2519271931Lb2519271931
Lb2519271931
IJERA Editor
 

Similar to Falzon Das Se Ag Compressed (20)

An evaluation of gnss code and phase solutions
An evaluation of gnss code and phase solutionsAn evaluation of gnss code and phase solutions
An evaluation of gnss code and phase solutions
 
Foss4g2009tokyo Realini Go Gps
Foss4g2009tokyo Realini Go GpsFoss4g2009tokyo Realini Go Gps
Foss4g2009tokyo Realini Go Gps
 
Signal Processing Algorithms for MIMO Radar
Signal Processing Algorithms for MIMO RadarSignal Processing Algorithms for MIMO Radar
Signal Processing Algorithms for MIMO Radar
 
How gps works
How gps worksHow gps works
How gps works
 
Second Order Perturbations During Inflation Beyond Slow-roll
Second Order Perturbations During Inflation Beyond Slow-rollSecond Order Perturbations During Inflation Beyond Slow-roll
Second Order Perturbations During Inflation Beyond Slow-roll
 
How gps works
How gps worksHow gps works
How gps works
 
Selm Falzon Compressed
Selm Falzon CompressedSelm Falzon Compressed
Selm Falzon Compressed
 
goGPS (March 2010)
goGPS (March 2010)goGPS (March 2010)
goGPS (March 2010)
 
Chap2 ofdm basics
Chap2 ofdm basicsChap2 ofdm basics
Chap2 ofdm basics
 
2_prats_IGARSS2011_distributed_imaging_v4.ppt
2_prats_IGARSS2011_distributed_imaging_v4.ppt2_prats_IGARSS2011_distributed_imaging_v4.ppt
2_prats_IGARSS2011_distributed_imaging_v4.ppt
 
Real Time Spectroscopy
Real Time SpectroscopyReal Time Spectroscopy
Real Time Spectroscopy
 
Bloco2 produtos gerados_pelo_inpe
Bloco2 produtos gerados_pelo_inpeBloco2 produtos gerados_pelo_inpe
Bloco2 produtos gerados_pelo_inpe
 
Modal Analysis Basic Theory
Modal Analysis Basic TheoryModal Analysis Basic Theory
Modal Analysis Basic Theory
 
CELEBRATION 2000 (3rd Deployment) & ALP 2002 Generation of a 3D-Model of the ...
CELEBRATION 2000 (3rd Deployment) & ALP 2002Generation of a 3D-Model of the ...CELEBRATION 2000 (3rd Deployment) & ALP 2002Generation of a 3D-Model of the ...
CELEBRATION 2000 (3rd Deployment) & ALP 2002 Generation of a 3D-Model of the ...
 
射頻電子 - [第六章] 低雜訊放大器設計
射頻電子 - [第六章] 低雜訊放大器設計射頻電子 - [第六章] 低雜訊放大器設計
射頻電子 - [第六章] 低雜訊放大器設計
 
CAPACITIVE SENSORS ELECTRICAL WAFER SORT
CAPACITIVE SENSORS ELECTRICAL WAFER SORTCAPACITIVE SENSORS ELECTRICAL WAFER SORT
CAPACITIVE SENSORS ELECTRICAL WAFER SORT
 
MUMS Opening Workshop - Model Uncertainty in Data Fusion for Remote Sensing -...
MUMS Opening Workshop - Model Uncertainty in Data Fusion for Remote Sensing -...MUMS Opening Workshop - Model Uncertainty in Data Fusion for Remote Sensing -...
MUMS Opening Workshop - Model Uncertainty in Data Fusion for Remote Sensing -...
 
2.5 pda-capwap - gray
2.5   pda-capwap - gray2.5   pda-capwap - gray
2.5 pda-capwap - gray
 
Pda capwap - frank rausche
Pda capwap - frank rauschePda capwap - frank rausche
Pda capwap - frank rausche
 
Lb2519271931
Lb2519271931Lb2519271931
Lb2519271931
 

Falzon Das Se Ag Compressed

  • 1. The Dynamic Aerial Survey Algorithm Precision Fertiliser Applications Falzon GA, Lamb DW & Schneider DA
  • 2. Overview The Need for Top-dress Fertilisers. The Advent of Active Optical Sensors. Real-Time Aerial Crop Survey & its Challenges. The Solution: DAS. Future Developments.
  • 3. Top-Dress Fertilisers Irrigated durum wheat: 2 applications of N/season 322 kg N/ha, $A309.84/ha (July 2011). 300 ha cereal feld requires $A92,952 N/application and $A185,904 total. Extra on-costs! Aircraft cost $A7000- $A10000/9ight. We need greater effciency!!!
  • 4. Active-Optical Sensors CropCircleTM ACS210 'red head' & GeoSCOUT 400 data-logger λ 1=650nm (red) λ 2=880nm (NIR) 4.00m 2.28m m 0.44
  • 5. Real-Time Aerial Survey Fletcher FU24954 aircraft Garmin GPS18 5Hz On-The-Go Sensing: 80 kts = 144 km/h Can we create an accurate prescription map after each pass?
  • 6. The DAS Algorithm: Pt I Paddock Polygons cumulative passes Ragged Arrays geo-referenced samples: different dimensions
  • 8. The DAS Algorithm: Pt III Support Vector Machines Nk f ( z)=∑i=1 [β −β K ( z i , z)+β0 ] 1 i 2 i Kernels Polynomial Radial Sigmoid T n (γ z⋅z +κ) −∣z−z T∣ T tanh (γ z⋅z +κ) exp( 2 ) 2σ
  • 10. The DAS Algorithm: Pt V Divide f ( z) into prescription zones M P =( M 1, P ,… , M N , P ) Pre-set Levels e.g. NDVI = {0.0,0.2,0.4,0.6,0.8} Divide into N levels e.g. n = 10 K-means clustering, e.g. cluster into three groups (low, med, high).
  • 11. The DAS Algorithm: In Action
  • 12. Future Developments Incorporate Prior Information Prior survey results Additional information such as soil surveys and yield maps Expert knowledge
  • 13. Future Developments Joint Air-Ground Operations Extension of Prior Survey Models. Ground Validation, Small Scale Areas, Combined Air/Ground Fertiliser Teams. Field Calibration & Validations Wind shear, height, droplet size (I. Yule), servo latency. Compare drop zone to management map.
  • 14. Thank you! M. Trotter (UNE PARG) SUPERAIR CRC for Spatial Information (CRCSI) Sugar Research & Development Corporation (SRDC) Nick Barton (Twynam Agriculture) Andrew Smart (Precision Cropping Technologies) Nick Gillingham (Sundown Pastoral Company) Dr. F. Honey (SpecTerra Services)