Scentific Research

Recently, there has been an increasing interest in broad-scale analysis, modeling, and prediction of the distribution and composition of plant species assemblages under climatic, environmental, and biotic filtering for plant conservation purposes. The team of Dai Junhu, a Researcher of the China-Pakistan Joint Research Center on Earth Sciences, devised a method to reliably predict the impact of climate change and biotic and environmental factors on plant communities.

The team first used multilabel algorithms in order to convert the task of explaining a large assemblage of plant communities into a classification framework that is able to capture with high cross-validated accuracy the pattern of species distributions under a composite set of biotic and abiotic factors. It applied this model to a set of plant communities in the Swiss Alps. The model explained presences/absences of 175 plant species in 608 plots with >87% cross-validated accuracy, predicted decreases in α, β, and γ diversity by 2040 under both moderate and extreme climate scenarios, and identified plant species likely to be favored/disfavored by climate change. Multi-label variables also revealed the importance of topography, soil and temperature extremes (rather than averages) in determining the distribution of plant species and their response to climate change.

The method was able to address a number of challenging research problems, such as scaling to large numbers of species, exploiting species relationships, dealing with species rarity, and overwhelming proportion of absences in the presence/absence matrix. By handling hundreds/thousands of plants and plots simultaneously over large areas, the method can help broad-scale conservation of plant species under climate change, as it allows species that require urgent conservation planning and policies (assisted migration, seed conservation, ex-situ conservation) to be detected and prioritized. It can also increase the practicality of assisted colonization of plant species, by preventing ill-advised introduction of plant species with limited future survival probability in a certain area. The relevant findings were published in the International Journal of Climatology with the title "A new method for broad-scale modeling and projection of plant assemblages under climatic, biotic, and environmental cofiltering".