STREAM

Applying digital technologies to simplify the production of farmland habitat reports through an online application. 

Environmental benchmarking of food systems is becoming an urgent requirement for farm-scale sustainability assessments and compliance with international certification schemes as it is a major contributor to the market reputation of food producers. Therefore, this Flagship Innovation Experiment (FIE) uses technology to reduce the logistical effort and cost to produce customised farmland habitat reports for environmental assessments, which traditionally require specialised ecological expertise. 

To provide a map of land uses including farmland habitats requires a smart combination of aerial imagery, existing Geographic Information System (GIS) data on biodiversity and, lastly, digitised land parcel information. The reliability of this FIE’s approach and modelled outputs is assessed by experts and on-the-ground surveys of farmland habitat, also known as ground-truthing. The team aims to develop an online application, linking photos of local wildlife features - provided by the farmer or advisor - with an information management system that can collate land use information to produce reports for individual farms and demonstrate environmental assets and actions. In these regards, the FIE also investigates the capacity of machine learning to improve habitat identification based on the visual interpretation of orthophotography.