Advancing the delivery of national mapping applications and tools (AV21006)

What was it all about?

This investment ensured the Australian avocado industry has access to new technologies and innovations that offer direct benefits to on farm production as well as industry-wide data collation and management. 

Challenge

The previous levy-funded project Implementing precision agriculture solutions in Australian avocado production systems (AV18002) saw the implementation of a precision agriculture solution in Australian avocado production systems and the creation of a multi-scale monitoring tool for managing Australian avocado tree crops.

To maintain the currency of these outputs, further investment was needed to maintain data, improve accuracy and extend these resources to industry. 

Response

This project has worked to deliver avocado growers with commercial tools to improve yield forecasting and mapping from the orchard block to the national scale, by:

• Maintaining and updating the web mapping applications with improved accuracy (as well as currency of the national map of avocado orchards) and usefulness to the avocado industry.
  
  
• Yield forecasting modelling to support other benchmarking projects and crop forecasting, and to allow investigation in the relationship between climate and yield to inform the remote sensing climate-based yield prediction model.
  
  
• Expanding the testing and structured feedback process to allow for improved decision-making and orchard management by producers using the CropCount app as a means of improving productivity. The CropCount app will also support avocado growers who have new plantings or have no historic data (that would be used in the time series analysis). 

Benefits

• The ‘time series’ model was developed for 128 orchard blocks in QLD, SA and WA regions. The project combined freely available satellite data, historical orchard yield and management data and advanced machine learning approaches to enhance the accuracy of yield prediction models initially built in project AV18002. The accuracy of machine learning time series has been well received by the growers with a significant increase in engagement in the project period. Historic production data and associated farm maps have been provided by six major Australian growers in WA, SA, QLD. The project team has received direct requests from many of Australia’s growers to be involved in the yield forecasting component of the project, providing sensitive historic yield data sets and tree management information.
  
  
• Further validating the ‘CropCount’ methodology over seven orchard blocks in WA. The relationship of canopy reflectance, measured by remote sensing technologies, to yield parameters and tree health, under Queensland growing conditions. The continued effort to better extend the project objectives to the wider avocado industry has been well received with a significant increase in grower engagement in the project period.
  
  
• Both ‘CropCount’ and ‘time series’ yield prediction models were developed and tested in QLD, SA and WA region. During the project, 10 large growers from QLD, SA, and WA participated to test and validate both the ‘CropCount’ and ‘time series’ methodologies with crops of varying ages, varieties, and historical yield and management information.
  
  
• Increased access and awareness of the ‘Australian Tree Crop Map Dashboard' which has now been viewed 18,579 times at the time of writing.