The productivity of 77% of Australian soils is limited by one or more soil constraints. Accurately diagnosing soil constraints is essential to enable evidence-based optimised management to increase the efficiency of crop production. Various methods are used to diagnose soil constraints such as laboratory methods, remote and proximal sensing, but these methods have their challenges. Most of the past studies has focused on the diagnosis of a single soil constraints despite that multiple soil constraints often co-exist in the soil. The lack of appropriate understanding and methods to diagnose multiple and interacting soil constraints is thus a barrier to increasing crop yields. This project will develop a data-centric framework that integrates biophysical models, machine learning and statistical approaches to accurately diagnose and prioritise multiple and interacting soil constraints to address the shortcomings of current soil constraint diagnostics.
For more information, please contact the Graduate Research School.