EPPO Global Database

EPPO Reporting Service no. 11 - 2006 Num. article: 2006/242

The use of artificial neural network in biological invasions: modelling global insect pest species assemblages to determine risk of invasion

Species assemblages are groupings of species that co-occur in the same place and at the same time. Pest species assemblages are non-random species groupings that contain hidden predictive information that can be analysed using ecological community analysis techniques. Currently, there is no objective scientific approach for prioritizing and identifying species that should be subject to more detailed risk assessments. In this study, information available on the geographical distribution of a wide range of insect pest species was meant to assist the identification and prioritization of species that have the potential to pose an invasive threat in regions where they are not normally found. Data comprising the presence and absence of 844 insect pest species recorded over 459 geographical regions world-wide were analysed using self-organizing map (SOM), a well known artificial neural network algorithm.
The SOM analysis allowed each species to be ranked in term of its risk of invasion in each area based on the strength of its association with the assemblage that was characteristic for each geographical region. A risk map for several example species was produced to illustrate how such a map can be compared with the species’ actual distribution and used with other information, such as the species’ biotic characteristics and interactions with the abiotic environment, to improve pest risk assessment further. For example, in 2002, the melon thrip Thrips palmi (EPPO A1 List) attracted attention as a possible invasive species to New Zealand and significant resources were invested in assessing the risk of establishment. However, in the analysis recorded here this species is not strongly associated with the New Zealand assemblage and to date, it has not established in New Zealand. Furthermore, the analysis predicted New Zealand’s most recent invasive insect pest Chrysomphalus aonidum. Such an analysis can then be used to support additional risk assessment of potential invasive species, giving invasive species researchers, conservation managers, quarantine and biosecurity scientists a mean for prioritizing species as candidates for further research.


Worner SP, Gevrey M (2006) Modelling global insect pest species assemblages to determine risk of invasion. Journal of Applied Ecology 43, 858-867.