Digital agriculture is exciting attention because of an expectation that food systems will be disrupted by new digital technologies through improvements in precision, efficiency, volume, speed of process or identity of product. This is against the background of the drive for sustainability in food systems. A diversity of technology applications is unilaterally emerging in all food chains with benefits realized through human acceptance and adoption in business processes. This paper focuses on Australia but the lessons apply to digital agriculture globally. We propose that sustainable food systems frameworks identify the relation of individual changes to broader systemic change, to relate individual changes to one another and to understand how multiple changes within a system can trigger major shifts in entire agri-food chains. With this rapidly-changing landscape in mind, we argue that food system frameworks cover five domains: production, market, capitals, governance and data technologies. We analyse experience from agricultural systems, compare it to digitization in non-agricultural systems and conclude that change will be both disruptive and cumulative. We consider the role of systems governance to be under-reported. Governance will prove critical in areas of IP legislation, policy harmonization and targeted investment.

On-farm experimentation (OFE) is a farmer-centric process that can enhance the adoption of digital agriculture technologies and improve farm profitability and sustainability. Farmers work with consultants or researchers to design and implement experiments using their own machinery to test management practices at the field or farm scale. Analysis of data from OFE is challenging because of the large spatial variation influenced by spatial autocorrelation that is not due to the treatment being tested and is often much larger than treatment effects. In addition, the relationship between treatment and yield response may also vary spatially. We investigate the use of geographically weighted regression (GWR) for analysis of data from large on-farm experiments. GWR estimates local regressions, where data are weighted by distance from the site using a distance-decay kernel. It is a simple approach that can be easily explained to farmers and their agronomic advisors. We use simulated data to test the ability of GWR to separate yield variation due to treatment from any underlying spatial variation in yield that is not due to treatment; show that GWR kernel bandwidth can be based on experimental design to accurately separate the underlying spatial variability from treatment effects; and demonstrate a step-wise model selection approach to determine when the response to treatment is global across the experiment or locally varying. We demonstrate our recommended approach on two large-scale experiments conducted on farms in Western Australia to investigate grain yield response to potassium fertiliser. We discuss the implications of our results for routine practical application to OFE and conclude that GWR has potential for wide application in a semi-automated manner to analyse OFE data, improve farm decision-making, and enhance the adoption of digital technologies.