Environmental harshness drives spatial heterogeneity in biotic resistance

Spatial prediction of plant invasion using a hybrid of machine learning and geostatistical method

Modeling ecological patterns and processes often involve large-scale and complex high-dimensional spatial data. Due to the nonlinearity and multicollinearity of ecological data, traditional geostatistical methods have faced great challenges in model accuracy. As machine learning has increased our ability to construct models on big data, the main focus of the study is to propose the use of statistical models that hybridize machine learning and spatial interpolation methods to cope with increasingly large-scale and complex ecological data. Here, two machine learning algorithms, boosted regression tree (BRT) and least absolute shrinkage and selection operator (LASSO), were combined with ordinary kriging (OK) to model plant invasions across the eastern United States. The accuracies of the hybrid models and conventional models were evaluated by 10-fold cross-validation. Based on an invasive plants dataset of 15 ecoregions across the eastern United States, the results showed that the hybrid algorithms were significantly better at predicting plant invasion when compared to commonly used algorithms in terms of RMSE and paired-samples t-test (with the p-value < .0001). Besides, the additional aspect of the combined algorithms is to have the ability to select influential variables associated with the establishment of invasive cover, which cannot be achieved by conventional geostatistics. Higher accuracy in the prediction of large-scale biological invasions improves our understanding of the ecological conditions that lead to the establishment and spread of plants into novel habitats across spatial scales. The results demonstrate the effectiveness and robustness of the hybrid BRTOK and LASOK that can be used to analyze large-scale and high-dimensional spatial datasets, and it has offered an optional source of models for spatial interpolation of ecology properties. It will also provide a better basis for management decisions in early-detection modeling of invasive species.

Competitive Interactions of Flowering Rush (Butomus umbellatus L.) Cytotypes in Submersed and Emergent Experimental Aquatic Plant Communities

The ability to invade communities in a variety of habitats (e.g., along a depth gradient) may facilitate establishment and spread of invasive plants, but how multiple lineages of a species perform under varying conditions is understudied. A series of greenhouse common garden experiments were conducted in which six diploid and four triploid populations of the aquatic invasive plant Butomus umbellatus L. (Butomaceae) were grown in submersed or emergent conditions, in monoculture or in a multispecies community, to compare establishment and productivity of cytotypes under competition. Diploid biomass overall was 12 times higher than triploids in the submersed experiment and three times higher in the emergent experiment. Diploid shoot:root ratio was double that of triploid plants in submersed conditions overall, and double in emergent conditions in monoculture. Relative interaction intensities (RII) indicated that triploid plants were sixteen times more negatively impacted by competition under submersed conditions but diploid plants were twice as impacted under emergent conditions. Recipient communities were similarly negatively impacted by B. umbellatus cytotypes. This study supports the idea that diploid and triploid B. umbellatus plants are equally capable of invading emergent communities, but that diploid plants may be better adapted for invading in submersed habitats. However, consistently lower shoot:root ratios in both monoculture and in communities suggests that triploid plants may be better-adapted competitors in the long term due to increased resource allocation to roots. This represents the first examination into the role of cytotype and habitat on competitive interactions of B. umbellatus.