Knowledge-guided machine-learning optimisation of soil constraint management

[Photo by UniSQ Senior Photographer David Martinelli]

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.

Funded by

CRC for High Performance Soils Ltd. Australia

Yunru (Chloe) Lai
Yunru (Chloe) Lai
Research Fellow - Soil and Crop Modelling

My research interests include pedometrics, empirical and mechanistic soil and crop modelling.