Twenty-five years of conferences on the Ecology and Management of Alien Plant invasions: the history of EMAPi 1992–2017

A novel hybrid model for species distribution prediction using neural networks and Grey Wolf Optimizer algorithm

Neural networks are frequently employed to model species distribution through backpropagation methods, known as backpropagation neural networks (BPNN). However, the complex structure of BPNN introduces parameter settings challenges, such as the determination of connection weights, which can affect the accuracy of model simulation. In this paper, we integrated the Grey Wolf Optimizer (GWO) algorithm, renowned for its excellent global search capacity and rapid convergence, to enhance the performance of BPNN. Then we obtained a novel hybrid algorithm, the Grey Wolf Optimizer algorithm optimized backpropagation neural networks algorithm (GNNA), designed for predicting species' potential distribution. We also compared the GNNA with four prevalent species distribution models (SDMs), namely the generalized boosting model (GBM), generalized linear model (GLM), maximum entropy (MaxEnt), and random forest (RF). These models were evaluated using three evaluation metrics: the area under the receiver operating characteristic curve, Cohen's kappa, and the true skill statistic, across 23 varied species. Additionally, we examined the predictive accuracy concerning spatial distribution. The results showed that the predictive performance of GNNA was significantly improved compared to BPNN, was significantly better than that of GLM and GBM, and was even comparable to that of MaxEnt and RF in predicting species distributions with small sample sizes. Furthermore, the GNNA demonstrates exceptional powers in forecasting the potential non-native distribution of invasive plant species.

Some reflections on current invasion science and perspectives for an exciting future

Species spreading beyond their native ranges are important study objects in ecology and environmental sciences and research on biological invasions is thriving. Along with an increase in the number of publications, the research field is experiencing an increase in the diversity of methods applied and questions asked. This development has facilitated an upsurge in information on invasions, but it also creates conceptual and practical challenges. To provide more transparency on which kind of research is actually done in the field, the distinction between invasion science, encompassing the full spectrum of studies on biological invasions and the sub-field of invasion biology, studying patterns and mechanisms of species invasions with a focus on biological research questions, can be useful. Although covering a smaller range of topics, invasion biology today still is the driving force in invasion science and we discuss challenges stemming from its embeddedness in the social context. Invasion biology consists of the building blocks ‘theory’, ‘case studies’ and ‘application’, where theory takes the form of conceptual frameworks, major hypotheses and statistical generalisations. Referencing recent work in philosophy of science, we argue that invasion biology, like other biological or ecological disciplines, does not rely on the development of an all-encompassing theory in order to be efficient. We suggest, however, that theory development is nonetheless necessary and propose improvements. Recent advances in data visualisation, machine learning and semantic modelling are providing opportunities for enhancing knowledge management and presentation and we suggest that invasion science should use these to transform its ways of publishing, archiving and visualising research. Along with a stronger focus on studies going beyond purely biological questions, this would facilitate the efficient prevention and management of biological invasions.

Global Actions for Managing Cactus Invasions

The family Cactaceae Juss. contains some of the most widespread and damaging invasive alien plant species in the world, with Australia (39 species), South Africa (35) and Spain (24) being the main hotspots of invasion. The Global Cactus Working Group (IOBC GCWG) was launched in 2015 to improve international collaboration and identify key actions that can be taken to limit the impacts caused by cactus invasions worldwide. Based on the results of an on-line survey, information collated from a review of the scientific and grey literature, expertise of the authors, and because invasiveness appears to vary predictably across the family, we (the IOBC GCWG): (1) recommend that invasive and potentially invasive cacti are regulated, and to assist with this, propose five risk categories; (2) recommend that cactus invasions are treated physically or chemically before they become widespread; (3) advocate the use of biological control to manage widespread invasive species; and (4) encourage the development of public awareness and engagement initiatives to integrate all available knowledge and perspectives in the development and implementation of management actions, and address conflicts of interest, especially with the agricultural and ornamental sectors. Implementing these recommendations will require global co-operation. The IOBC GCWG aims to assist with this process through the dissemination of information and experience.