Knowledge-guided machine-learning optimisation of soil constraint management
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 to maximise productivity and profitability. While there are different ways to manage constraints in isolation, it is difficult to know which method to use and when due to 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 (a knowledge-guided machine-learning framework) that incorporates 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 weather and farming conditions. In addition, this project will standardise and use data from published studies and past/current experiments conducted by the Soil CRC participants to ensure that the data will be findable, accessible, interoperable and reusable (FAIR).
University of Southern Queensland, Mallee Sustainable Farming, Burdekin Productivity Services, West Midlands Group, Riverine Plains Inc.
CRC for High Performance Soils Ltd. Australia
- A conceptual framework for the modelling of sodicity constraints to crops
- Pipeline for quantification of climate risk on crop productivity of dominant soil types in Queensland, under future climate change scenarios
- Scoping study of the requirements for the development of CaneMAPPs
- Diagnosis frameworks for multiple and complex soil constraints
- Improving the representation of soil productivity/constraints in existing DSS and modelling platforms