Industry applications

AARSC is currently involved in collaborative projects that include a cross-section of industry bodies, government agencies and university partners. These multidisciplinary projects help industries navigate the various technologies available as well as develop new fit-for-purpose applications.

These capabilities provide data that is sufficiently granular and calibrated to be used for both farm and region-wide analysis, including:

  • Yield and quality forecasting and mapping.
  • Crop identification production area and extent.
  • Optimal planting and harvesting dates.
  • Biosecurity, plant health and stress detection.
  • Water use efficiency.
  • Nutrient use deficiency.

AARSC provides support for interpreting results agronomically, and ensuring their adoption on farm.

R&D projects

Industry Applications and Maps

Industry newsletters

Case studies

"It is very high on the priority list for us to commercialise it [remote sensing technologies] and for the benefit of our growers too because there are so many positives for the industry."

Dr. Graeme Wright, Peanut Company of Australia (Manager of Breeding & Innovation)

"We have got very good data for the last four years and three out of the last four years provided an accuracy of 97 per cent or better."

Gavin Lerch, Bundaberg Sugar Grower Services

Farming applications and analytics

LiDAR Map
LiDAR Map

LiDAR map of each individual tree and fruit (by University of Sydney).

Classified Tree Vigour Map
Classified Tree Vigour Map

High resolution satellite imagery is extremely accurate in mapping the spatial distributing of tree vigour. By using these maps, soil and plant samples that better represent high, medium and low growth trees can be easily identified and collected - reducing the number of samples to just three.

Derived Yield Map of Mango farm
Derived Yield Map

Derived yield map (kg/tree)

Fruit Yield Map
Fruit Yield Map

Mango fruit yield map derived from each sensing platform (by CQUniversity). The ‘hotter’ the colour the higher the fruit yield per tree.

Machine Vision
Machine Vision

Individual fruit identified by machine vision (by CQUniversity & University of Sydney).

NDVI Image
NDVI Image

NDVI image showing variation in tree vigor across a mango orchard. The higher the NDVI the more healthy the tree

Sample locations
Sample locations satellite image

Sample locations of 18 tree overlaid on to a false colour satellite image

Tree Crow Area
Tree Crown Area

Extraction of tree crown area.

Yield and Canopy Reflectance
Yield and Canopy Reflectance

Relationship between mango yield per tree versus measured TCA x RDVI2 (a measure of canopy reflectance)

LiDAR map of each individual tree and fruit (by University of Sydney).
High resolution satellite imagery is extremely accurate in mapping the spatial distributing of tree vigour. By using these maps, soil and plant samples that better represent high, medium and low growth trees can be easily identified and collected - reducing the number of samples to just three.
Derived yield map (kg/tree)
Mango fruit yield map derived from each sensing platform (by CQUniversity). The ‘hotter’ the colour the higher the fruit yield per tree.
Individual fruit identified by machine vision (by CQUniversity & University of Sydney).
NDVI image showing variation in tree vigor across a mango orchard. The higher the NDVI the more healthy the tree
Sample locations of 18 tree overlaid on to a false colour satellite image
Extraction of tree crown area.
Relationship between mango yield per tree versus measured TCA x RDVI2 (a measure of canopy reflectance)