CropPhen: Remote mapping of grain crop type and phenology

Page last updated: Friday, 7 July 2023 - 9:00am

Please note: This content may be out of date and is currently under review.

This project aims to develop a software-based tool to remotely map crop type (wheat, barley, chickpea, lentils, sorghum and mungbean) and development stage at the sub-paddock scale. It will combine remote sensing, crop simulation modelling, machine learning and field validation datasets to develop an approach that captures data on crop type and developmental stage every five days at a 10-metre spatial resolution using satellite imagery. This will provide growers and advisers with information that will assist them to optimise management decisions.

Start date: 01/03/2020
Finish date: 01/06/2023

Description:

The CropPhen tool will provide near real-time information for field crop species discrimination and crop-specific phenology mapping. The aim of the project is to determine reliable, accurate and spatially referenced crop species classification and phenological estimates in Australian grain production systems for wheat, barley, chickpea, lentils, sorghum and mungbeans.

The prediction of crop type and phenology at the sub-paddock scale every five days or less will help enable the provision of a key, foundational data layer that can be used to develop new on and off-farm analytics products that support the enduring profitability of Australian grain growers. Development of the CropPhen tool will include the integration of climate, crop modelling and earth observation technologies.

The project will also combine the enhanced spatial, spectral and temporal characteristics of the Sentinel-2 satellite platform operated by the European Space Agency with biophysical crop modelling and dynamic climate forecasting models. In addition, it will explore the potential of hyper spectral sensing data to complement imagery from Sentinel-2 to enhance the functionality of the CropPhen tool. This will enable the design, development and validation of novel algorithms and metrics for accurate crop type discrimination and phenology mapping well in advance of harvest.

The project is being led by the University of Queensland, with DPIRD’s Brenton Leske and Ghazwan Al Yaseri working alongside the South Australian Research and Development Institute (SARDI) to manage core field validation sites. Other partners include the University of Melbourne and Data Farming.

Funded by:

GRDC

Project code:

DAQ2005-004RTX

Contact information