Evaluation of machine learning methods for predicting eradication of aquatic invasive species
- Yanyu Xiao
- Russ Greiner, Dept of Computing Science; PI of AICML
- Mark A Lewis
In the work, we evaluate the performance of machine learning approaches for predicting successful eradication of aquatic invasive species (AIS) and assess the extent to which eradication of an invasive species depends on the various specific ecological features of the target ecosystem and/or features that characterize the planned intervention.We studied the outcomes of 143 planned eradication attempts for eradicating AIS. Each attempt was described using ecological and eradication strategy related features of the target ecosystem. We considered various machine learning approaches to determine if any could produce a model that would accurately predict whether an invasive species will be successfully eradicated. To assess learner's performance, we examined the 10-fold cross-validation prediction accuracy as well as false positive rate, F-measure and the Area Under the Curve for each model. We also used Kaplan-Meier survival analysis to determine which features are relevant to predicting the time required for each type of eradication program. Across ve typical machine learning approaches, our analysis suggests that learners trained by the decision tree approach work well and have the best performance in predicting eradication of AIS. In particular, by examining the trained decision tree model, we found that if an occupied area was not large and/or the intervention strategy employed the containment of AIS dispersal, the eradication of AIS was likely to be successful. We also trained decision tree models over only the ecological features and found that their performance was comparable with that of models trained using both ecological and eradication strategy related features. As our trained decision tree models are very accurate, decision makers can use them to estimate the result of the proposed actions before they commit to which specific strategy should be applied.
Citation
Y. Xiao, R. Greiner, M. Lewis. "Evaluation of machine learning methods for predicting eradication of aquatic invasive species". Biological Invasions, 20(9), pp 2485-2503, March 2018.Keywords: | Aquatic species, machine learning, survival analysis, ecological features, planned intervention |
Category: | In Journal |
Web Links: | DOI |
Journal URL |
BibTeX
@article{Xiao+al:18, author = {Yanyu Xiao and Russ Greiner and Mark A Lewis}, title = {Evaluation of machine learning methods for predicting eradication of aquatic invasive species}, Volume = "20", Number = "9", Pages = {2485-2503}, journal = {Biological Invasions}, year = 2018, }Last Updated: February 07, 2020
Submitted by Sabina P