Machine learning to map soil constraint variability and predict crop yield

This project will use a variety of Machine Learning techniques to bring together previously underutilised on-farm, satellite, and weather data and better predict expected crop outcomes. Tools to map fine-scale 3D-variability of agronomically important soil properties (such as depth to chemical/physical barriers and plant-available water-content) and to forecast crop yield variability in-season will be developed, improving management and profitability.