Predicting alien herb invasion with machine learning models: biogeographical and life-history traits both matter

Chen, Leiyi; Shaolin, Peng; Yang, Bin

doi:10.1007/s10530-015-0870-y

Cited by 16 publications

(11 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We applied a 10-fold validation approach, i.e. repeating the validation in ten different calibration batches and comparing the outcome with that of the training data for each of these batches 44 . We then calculated the threshold value for presence and absence of Prosopis 31,39 .…”

Section: Methodsmentioning

confidence: 99%

Modelling the current fractional cover of an invasive alien plant and drivers of its invasion in a dryland ecosystem

Shiferaw

Schaffner

Bewket

et al. 2019

Sci Rep

View full text Add to dashboard Cite

The development of spatially differentiated management strategies against invasive alien plant species requires a detailed understanding of their current distribution and of the level of invasion across the invaded range. The objectives of this study were to estimate the current fractional cover gradient of invasive trees of the genus Prosopis in the Afar Region, Ethiopia, and to identify drivers of its invasion. We used seventeen explanatory variables describing Landsat 8 image reflectance, topography, climate and landscape structures to model the current cover of Prosopis across the invaded range using the random forest (RF) algorithm. Validation of the RF algorithm confirmed high model performance with an accuracy of 92% and a Kappa-coefficient of 0.8. We found that, within 35 years after its introduction, Prosopis has invaded approximately 1.17 million ha at different cover levels in the Afar Region (12.3% of the surface). Normalized difference vegetation index (NDVI) and elevation showed the highest explanatory power among the 17 variables, in terms of both the invader’s overall distribution as well as areas with high cover. Villages and linear landscape structures (rivers and roads) were found to be more important drivers of future Prosopis invasion than environmental variables, such as climate and topography, suggesting that Prosopis is likely to continue spreading and increasing in abundance in the case study area if left uncontrolled. We discuss how information on the fractional cover and the drivers of invasion can help in developing spatially-explicit management recommendations against a target invasive plant species.

show abstract

Section: Methodsmentioning

confidence: 99%

Modelling the current fractional cover of an invasive alien plant and drivers of its invasion in a dryland ecosystem

Shiferaw

Schaffner

Bewket

et al. 2019

Sci Rep

View full text Add to dashboard Cite

show abstract

“…These five performance measures have the same range (0–1), and we gave each measure equal weight in evaluating the model performance in accordance with Chen, Peng & Yang (2015). The higher the values of these five performance measures are, the better the model performs; therefore, we summed up the five values (from hereupon called the “total score”) and chose the model with the highest sum as our final optimal model.…”

Section: Methodsmentioning

confidence: 99%

Contrasting determinants for the introduction and establishment success of exotic birds in Taiwan using decision trees models

Liang

Walther

Shieh

2017

PeerJ

View full text Add to dashboard Cite

BackgroundBiological invasions have become a major threat to biodiversity, and identifying determinants underlying success at different stages of the invasion process is essential for both prevention management and testing ecological theories. To investigate variables associated with different stages of the invasion process in a local region such as Taiwan, potential problems using traditional parametric analyses include too many variables of different data types (nominal, ordinal, and interval) and a relatively small data set with too many missing values.MethodsWe therefore used five decision tree models instead and compared their performance. Our dataset contains 283 exotic bird species which were transported to Taiwan; of these 283 species, 95 species escaped to the field successfully (introduction success); of these 95 introduced species, 36 species reproduced in the field of Taiwan successfully (establishment success). For each species, we collected 22 variables associated with human selectivity and species traits which may determine success during the introduction stage and establishment stage. For each decision tree model, we performed three variable treatments: (I) including all 22 variables, (II) excluding nominal variables, and (III) excluding nominal variables and replacing ordinal values with binary ones. Five performance measures were used to compare models, namely, area under the receiver operating characteristic curve (AUROC), specificity, precision, recall, and accuracy.ResultsThe gradient boosting models performed best overall among the five decision tree models for both introduction and establishment success and across variable treatments. The most important variables for predicting introduction success were the bird family, the number of invaded countries, and variables associated with environmental adaptation, whereas the most important variables for predicting establishment success were the number of invaded countries and variables associated with reproduction.DiscussionOur final optimal models achieved relatively high performance values, and we discuss differences in performance with regard to sample size and variable treatments. Our results showed that, for both the establishment model and introduction model, the number of invaded countries was the most important or second most important determinant, respectively. Therefore, we suggest that future success for introduction and establishment of exotic birds may be gauged by simply looking at previous success in invading other countries. Finally, we found that species traits related to reproduction were more important in establishment models than in introduction models; importantly, these determinants were not averaged but either minimum or maximum values of species traits. Therefore, we suggest that in addition to averaged values, reproductive potential represented by minimum and maximum values of species traits should be considered in invasion studies.

show abstract

“…succulents with clonal fragmentation in arid ecosystems) would be fed into the model to determine their possible affiliation to this invasion syndrome. Machine learning techniques are already widely used in invasion science; for example to predict the invasion stage of alien plants using trait and biogeographical data (Chen et al 2015), to predict eradication success (Xiao et al 2018), and to identify the source of ballast water using bacterial species composition (Gerhard and Gunsch 2019).…”

Section: Figmentioning

confidence: 99%

Invasion syndromes: a systematic approach for predicting biological invasions and facilitating effective management

et al. 2020

View full text Add to dashboard Cite

Our ability to predict invasions has been hindered by the seemingly idiosyncratic contextdependency of individual invasions. However, we argue that robust and useful generalisations in invasion science can be made by considering ''invasion syndromes'' which we define as ''a combination of pathways, alien species traits, and characteristics of the recipient ecosystem which collectively result in predictable dynamics and impacts, and that can be managed effectively using specific policy and management actions''. We describe this approach and outline examples that highlight its utility, including: cacti with clonal fragmentation in arid ecosystems; small aquatic organisms introduced through ballast water in harbours; large ranid frogs with frequent secondary transfers; piscivorous freshwater fishes in connected aquatic ecosystems; plant invasions in high-elevation areas; tall-statured grasses; and tree-Electronic supplementary material The online version of this article (

show abstract

Predicting alien herb invasion with machine learning models: biogeographical and life-history traits both matter

Cited by 16 publications

References 46 publications

Modelling the current fractional cover of an invasive alien plant and drivers of its invasion in a dryland ecosystem

Modelling the current fractional cover of an invasive alien plant and drivers of its invasion in a dryland ecosystem

Contrasting determinants for the introduction and establishment success of exotic birds in Taiwan using decision trees models

Invasion syndromes: a systematic approach for predicting biological invasions and facilitating effective management

Contact Info

Product

Resources

About