The Agricultural Data Science group applies data-driven approaches to address carbon and nitrogen challenges in agricultural systems.
Across the group, our expertise spans machine learning, global data synthesis, process-based modelling, sustainability assessment, and spatial analysis, with a strong focus on generating robust evidence for sustainable agriculture and decision-making.
Our capabilities include
Data synthesis, machine learning and integrated agroecosystem modelling
We combine big data analytics, meta-analysis, machine learning and process-based models to improve understanding and prediction of soil carbon and nitrogen dynamics, nitrogen losses, and management impacts across agricultural systems.
Sustainable nitrogen management and emissions mitigation
We evaluate fertiliser nitrogen use efficiency, greenhouse gas mitigation strategies, and management options that reduce nitrogen losses while improving agricultural productivity and environmental outcomes.
Spatial analysis, GIS and precision agriculture
We apply spatial modelling, remote sensing and precision agriculture approaches to support more targeted water and nutrient management, spatiotemporal analysis, and support more precise, data-informed decision-making.
Environmental footprint and sustainability indicators
The group develops evidence-based environmental footprint and sustainability metrics, including reactive nitrogen assessment, nitrogen footprint quantification, food credentialing, and broader green indicators for agricultural products and production systems.
