Status: Completed
Start date: 1 April 2020
Completion date: 30 June 2023
Project code: A-021
Species/Threats: Weeds
Current weed identification relies on expert knowledge, interpreting taxonomic or morphological identification keys, trying to match a weed with an image in a weed guide or app, or sending a weed image or specimen to herbariums for identification. This often leads to delayed or incorrect identification that impedes timely action, particularly on emerging weeds, and requires State herbaria to allocate scarce resources to respond to community identification requests for well-known established weeds.
This project developed, trialed and implemented Australia’s first real-time, artificial intelligence-based, automated identification of national, state and regional priority weeds: WeedScan.
The objective of this project was:
Schmidt-Lebuhn AN, Bell M, Eckelmann C, Evans D, Glanznig A, Rongxin L, Mitchell A, Mitchell-Storey T, Newton M and O’Duibhir L (2024) WeedScan, a weed reporting system for Australia using an image classification model for identification Invasive Plant Science and Management https://doi.org/10.1017/inp.2024.19
