Machine learning to extract maximum value from soil and crop variability

The yields of major crops in Australia are often below their water-limited potential. A reason for this is the complexity of Genotype x Environment x Management (GxExM) interaction, which results in crop growth with high variability. This project aims to use machine learning to undertake a more detailed analysis of data already generated as part of previous research with a focus on soil factors that impact on grain yield variability. It will combine multi-layer paddock and field trial datasets with machine learning (ML) analytics with simulated cropping scenarios generated in Agricultural Production Systems sIMulator (APSIM). The model will be trained on paddock data and tested on research plots to see whether the machine learning algorithms can detect patterns from the research that traditional approaches were unable to identify by accounting for more variable across the whole GxExM interaction. The APSIM model will also be used to generate additional scenarios for testing with the machine learning algorithm.