Optimising soil constraint management through computer-based learning and modelling

This project aims to find the best ways to manage multiple soil constraints, such as sodicity, acidity, and salinity, to help farmers make informed soil management decisions that maximise productivity and profitability.

There are different ways to manage constraints in isolation, but deciding which method to use and when can be challenging. This is due to the high variability in the responsiveness of soils to ameliorants where multiple soil constraints exist.

To tackle this challenge, the project proposes a computer-based approach to optimising soil constraint management. Known as a knowledge-guided machine-learning modelling framework, it uses scientific understanding and learns from existing data to predict which combinations of soil management will work best for a particular soil affected by multiple constraints under specific conditions.

The project team will engage growers in this research to cultivate early adopters and ensure that the eventual universal decision-support tool will be used by the industry. Such tools will improve soil function and capacity across Australian agriculture while enhancing productivity and profitability.

The project will also standardise and use data from published studies and Soil CRC’s past and current experiments to ensure the data will be findable, accessible, interoperable, and reusable (FAIR).

This research builds on two Program 4 projects: Improving decision support systems, which improved the representation of soil constraints in various decision support tools; and Diagnosis frameworks for multiple and complex soil constraints, which developed a diagnostic framework for multiple and interacting soil constraints.