Learning from the past to predict the future: an historical analysis of grass invasions in northern Australia

An important focus of biosecurity is anticipating future risks, but time lags between introduction, naturalisation, and (ultimately) impact mean that future risks can be strongly influenced by history. We conduct a comprehensive historical analysis of tropical grasses (n = 155) that have naturalised in Australia since European settlement (1788) to determine what factors shaped historical patterns of naturalisation and future risks, including for the 21 species that cause serious negative impacts. Most naturalised species were from the Old World (78 %), were introduced for use in pasture (64.5 %), were first recorded prior to 1940 (84.5 %) and naturalised before 1980 (90.3 %). Patterns for high-impact species were similar, with all being first recorded in Australia by 1940, and only seven naturalised since then-five intentionally introduced as pasture species. Counter to expectations, we found no evidence for increased naturalisation with increasing trade, including for species introduced unintentionally for which the link was expected to be strongest. New pathways have not emerged since the 1930s despite substantial shifts in trading patterns. Furthermore, introduction and naturalisation rates are now at or approaching historically low levels. Three reasons were identified: (1) the often long lag phase between introduction and reported naturalisation means naturalisation rates reflect historical trends in introduction rates; (2) important introduction pathways are not directly related to trade volume and globalisation; and (3) that species pools may become depleted. The last of these appears to be the case for the most important pathway for tropical grasses, i.e. the intentional introduction of useful pasture species. Assuming that new pathways don't arise that might result in increased naturalisation rates, and that current at-border biosecurity practices remain in place, we conclude that most future high-impact tropical grass species are already present in Australia. Our results highlight the need to continually test underlying assumptions regarding future naturalisation rates of high-impact invasive species, as conclusions have important implications for how best to manage future biosecurity risks.

Automating Crop Damage Assessments with Unmanned Aerial Systems and Machine Learning

Agricultural pests are responsible for millions of dollars in crop losses and management costs every year. In order to implement optimal site-specific treatments and reduce control costs, new methods to accurately monitor and assess pest damage need to be investigated. In this paper we explore the combination of unmanned aerial vehicles (UAV), remote sensing and machine learning techniques as a promising methodology to address this challenge. The deployment of UAVs as a sensor platform is a rapidly growing field of study for biosecurity and precision agriculture applications. In this experiment, a data collection campaign is performed over a sorghum crop severely damaged by white grubs (Coleoptera: Scarabaeidae). The larvae of these scarab beetles feed on the roots of plants, which in turn impairs root exploration of the soil profile. In the field, crop health status could be classified according to three levels: bare soil where plants were decimated, transition zones of reduced plant density and healthy canopy areas. In this study, we describe the UAV platform deployed to collect high-resolution RGB imagery as well as the image processing pipeline implemented to create an orthoimage. An unsupervised machine learning approach is formulated in order to create a meaningful partition of the image into each of the crop levels. The aim of this approach is to simplify the image analysis step by minimizing user input requirements and avoiding the manual data labelling necessary in supervised learning approaches. The implemented algorithm is based on the K-means clustering algorithm. In order to control high-frequency components present in the feature space, a neighbourhood-oriented parameter is introduced by applying Gaussian convolution kernels prior to K-means clustering. The results show the algorithm delivers consistent decision boundaries that classify the field into three clusters, one for each crop health level as shown in Figure 1. The methodology presented in this paper represents a venue for further esearch towards automated crop damage assessments and biosecurity surveillance.