Waters, Ethan, Chen, C., Di Bella, L.P., Nielson, R., Harragon, R., and Azghadi, M.R. (2024) Detection of ratoon stunting disease with freely available satellite-based multispectral imaging and machine learning. In: Proceedings of the 45th Conference of the Australian Society of Sugar Cane Technologists. pp. 52-55. From: ASSCT 2024: 45th Annual Conference of the Australian Society of Sugar Cane Technologists, 16-19 April 2024, Townsville, QLD, Australia.

	PDF (Published Version) - Published Version Restricted to Repository staff only
	PDF (Call for papers) - Updated Version Restricted to Repository staff only

Abstract

Ratoon Stunting Disease (RSD) poses a significant challenge in sugarcane cultivation. The causal agent of RSD is the bacterium Leifsonia xyli subsp. Xyli (Lxx), highly contagious and primarily propagated through contaminated cutting implements (Davis et al, 1984). The infection can lead to yield losses of up to 60%, depending on variety and water availability (Bailey & Bechet, 1986). Investigating the economic impact of RSD (Magarey et al, 2021) revealed an annual economic loss of $25 million across the 87,000 hectares monitored for RSD infection (Magarey et al, 2021). Although this significant impact promotes a desire to implement hygiene and disease management protocols (Chakraborty et al), the lack of external symptoms in RSD complicates its identification and management. This necessitates laboratory diagnostic techniques such as PCR, qPCR, LAMP, or LSB-qPCR (Carvalho et al, 2016; Fegan et al, 1998; Ghai et al, 2014; Young et al, 2016). The diagnostic techniques mentioned require the collection of field samples, which, given the size and density of plantations, can be time-consuming and inefficient. This motived us to develop an accurate and efficient method for large scale RSD detection.

Actions (Repository Staff Only)

Item Control Page