Multispectral, Aerial Disease Detection for Myrtle Rust (Austropuccinia psidii) on a Lemon Myrtle Plantation

Abstract

Disease management in agriculture often assumes that pathogens are spread homogeneously across crops. In practice, pathogens can manifest in patches. Currently, disease detection is predominantly carried out by human assessors, which can be slow and expensive. A remote sensing approach holds promise. Current satellite sensors are not suitable to spatially resolve individual plants or lack temporal resolution to monitor pathogenesis. Here, we used multispectral imaging and unmanned aerial systems (UAS) to explore whether myrtle rust (Austropuccinia psidii) could be detected on a lemon myrtle (Backhousia citriodora) plantation. Multispectral aerial imagery was collected from fungicide treated and untreated tree canopies, the fungicide being used to control myrtle rust. Spectral vegetation indices and single spectral bands were used to train a random forest classifier. Treated and untreated trees could be classified with high accuracy (95%). Important predictors for the classifier were the near-infrared (NIR) and red edge (RE) spectral band. Taking some limitations into account, that are discussedherein, our work suggests potential for mapping myrtle rust-related symptoms from aerial multispectral images. Similar studies could focus on pinpointing disease hotspots to adjust management strategies and to feed epidemiological models.

Spatial Patterns of ‘Ōhi‘a Mortality Associated with Rapid ‘Ōhi‘a Death and Ungulate Presence

“…It highlights the difficulty in determining the cause of 'ōhi'a mortality from remotely sensed imagery alone, even when using multispectral or hyperspectral data [23,24], especially since symptoms of ROD can be confused with symptoms of drought [21]. Other fungal pathogens affecting forests worldwide, including ash dieback, myrtle rust, and oak wilt, were successfully detected via multispectral and hyperspectral imagery, though misclassification with drought can occur, and early detection remains a challenge [41][42][43][44].…”

Review on unmanned aerial vehicles, remote sensors, imagery processing, and their applications in agriculture

“…Machine learning is also playing an integral role in addressing the UAV data processing bottleneck in pathogen detection. Machine‐assisted pathogen stress detection has been utilized for a multitude of applications such as detection of yellow rust ( Puccinia striiformis ; Su et al., 2018), grapevine bacterial disease ( Flavescence dorée ; Albetis et al., 2017), myrtle rust ( Austropuccinia psidii ; Heim et al., 2019), and citrus greening ( Candidatus Liberibacter ; Garcia‐Ruiz et al., 2013) which achieved classification accuracies ranging from 67 to 95% and further validates the usefulness of machine‐assisted classification technologies.…”

Plant pest surveillance: from satellites to molecules

“…Commercial satellites, such as Planet Labs and Maxar, for example, now enable frequent, precise returns with high spatial and temporal resolution with growing spectral resolution and have been recently established to be capable of disease monitoring [26,27]. Unmanned aerial vehicles (UAV, or 'drones') and low-altitude aircraft are well established to be capable of disease detection and monitoring, though reliable differentiation and diagnosis remains challenging [28][29][30][31][32]. Access to these sorts of imagery is now widely available to growers due to the growing number of service providers offering weekly to sub-weekly imagery satellite, aerial and/or UAV imagery.…”