The three-horned bedstraw (Galium tricornutum) eradication program in Western Australia

Document Type

Conference Proceeding

Publication Date

8-2024

Conference Title

23rd Australasian Weeds Conference - Breaking the Cycle: Towards Sustainable Weed Mangement

Place of Publication

Brisbane

ISBN

978-0-646-70156-1

Keywords

Artificial intelligence, control, compensation, image analysis, economics, eradication, Galium tricornutum, GrainCam, GSHIFS, surveillance, seed image recognition, three-horned bedstraw.

Disciplines

Artificial Intelligence and Robotics | Weed Science

Abstract

There is an increasing shift toward obtaining greater agronomic oversight through automative agricultural farming technologies that provide economic and sustainable advantages. One area of improvement lies in the temporal and spatial detection of weeds and subsequent application of site-specific herbicide technologies in cropping systems. Targeted weed technologies provide significant advantages to the cropping system. Current machine sensing technologies rely on heavy capital investment outlay which has been a barrier for adoption for many growers. Drones are also being used in this capacity; however they have limitations such as flight duration which means for large fields it lacks scalability. New satellites are being launched with increasing frequency, all with greater resolution capabilities than previously offered. This proliferation of satellites presents a new opportunity for accessing higher-resolution data, potentially reaching levels where innovative weed detection technologies can be developed. These technologies could empower growers to identify and target individual and smaller patches of weeds with precision, facilitating the 115 application of targeted herbicide spraying. One of the significant benefits of utilising satellites to provide a 'spot spray’ application map, is the lack of capital outlay required, and the ability to integrate with current machinery capabilities and the worldwide scalability of such technology. Such targeted weed management significantly reduces operational costs but also addresses sustainability concerns by minimizing herbicide usage. Growers will have more weed management options for handling hard to control weeds, utilising more expensive herbicide options on stubborn weed populations, or using alternative weed control technology, which enhances effectiveness while mitigating the development of herbicide resistance. Ultimately, WeedSAT, a new weed detection method developed by DataFarming in partnership with GRDC and the University of Sydney, has the potential to provide significant savings for growers while integrating sustainable agricultural practices.

Link to Full Text

Share

COinS