The Graincast™ suite of tools was developed to monitor crop productivity in near real-time across the Australian landscape. Four separate tools were created: the C-Crop model, which monitors crop yields with satellite; CropID, which monitors the crop species and areas of production; the Graincast™ app, which provides field-scale estimates of crop production and soil-water use; and Field Boundaries (ePaddocks), which identifies every cropped field across the landscape. The paper describes the design process, including data acquisition, machine learning, testing, validation, human-centred design and the delivery of outputs to end-users.

Digital agriculture in Australia is considered immature and its adoption ad hoc, despite a relatively advanced technology innovation sector. Increasing digital maturity and adoption in Australian agriculture will require working with end users to better design and integrate technology, improvements to supporting legislation and education, better knowledge brokering and exchange, better conversion of data to decisions, and further improvement to enabling technologies. Agronomists and early adopter farmers will play a significant role in closing the technology-end user gap.

The complex adoption pathways of digital technology in Australian livestock supply chains systems are discussed in this paper. We argue that – since quality appears to be the major basis on which Australian red meat producers will compete in global markets – the broad adoption of digital technology will prove increasingly essential to future growth of this supply chain. We discuss how value is created and how digital transformation involves organisations, people, learning and processes.

The status of digital agriculture (DA) in South America (SA) is unknown. This article quantified adoption of existing DA technologies, identified limitations for DA adoption, implementing a literature review and case studies. Sustainable metrics were summarised to benchmark DA impact. GPS guidance systems, mapping tools, mobile apps and remote sensing were the most adopted DA technologies in SA. The most reported limitations to adoption were technology cost, lack of training, limited number of companies providing services, and unclear benefits from DA. The proposed metrics to benchmark DA benefits will allow stakeholders to design targeted initiatives to promote DA towards sustainability of food production in the region.

This paper introduces an insect detection framework based on an improved YOLOv3 network to detect tiny insects on an agricultural pest dataset (Pest24). We applied data augmentation techniques to regularise the dataset, the adaptive feature fusion module is then integrated to reuse features at different level. The resulting features are then fed into the YOLOv3 object detector network for detection (localisation and classification of insects). The dataset was evaluated on different state-of-the-art detectors for comparison.

Deep machine learning-based weed detection techniques can offer automatic and practical solutions for large cropping areas. In this work, we construct a benchmark dataset by combining several small datasets and thoroughly evaluate five state-of-the-art deep learning models to classify crop and weed datasets and thoroughly evaluate five state-of-the-art deep learning models to classify crop and weed.