A COMPARATIVE ANALYSIS OF RANDOM FOREST AND LOGISTIC REGRESSION FOR WEED RISK ASSESSMENT

Simple item page
dc.contributor.advisorPeer, Wendyen_US
dc.contributor.authorHarris, Chinchuen_US
dc.contributor.departmentPlant Science and Landscape Architecture (PSLA)en_US
dc.contributor.publisherDigital Repository at the University of Marylanden_US
dc.contributor.publisherUniversity of Maryland (College Park, Md.)en_US
dc.date.accessioned2019-02-01T06:31:10Z
dc.date.available2019-02-01T06:31:10Z
dc.date.issued2018en_US
dc.description.abstractInvasive species have largely negative impacts on the environment and the economy. The management and regulation of invasive plants are facilitated using screening tools, such as weed risk assessments (WRAs) to predict the invasive potential of non-native plants. The identification of these species and their subsequent regulation on importation helps to reduce the risk of future ecosystem and economic costs. Globally, there are many different types of highly useful WRAs already available. However, in this day of big data and powerful predictive analytics, there is an increasing demand for the development of new and more robust screening tools. In this thesis, I use the machine learning algorithm, Random forests, to develop a new WRA. I show that random forest model has greater predictive accuracies than an existing logistic regression model and that random forest is a better learner. In addition, variable importance analysis was performed to identify factors associated with invasive status classification of non-native plants. The study suggests that random forests make powerful weed risk screening tools and should be utilized for assessing invasive risk potential along with other WRAs. An integrative approach for evaluating weed risk can greatly serve to facilitate the WRA process.en_US
dc.identifierhttps://doi.org/10.13016/vyxv-9moe
dc.identifier.urihttp://hdl.handle.net/1903/21592
dc.language.isoenen_US
dc.subject.pqcontrolledPlant sciencesen_US
dc.subject.pqcontrolledStatisticsen_US
dc.subject.pqcontrolledEcologyen_US
dc.subject.pquncontrolledInvasive plantsen_US
dc.subject.pquncontrolledLogistic regressionen_US
dc.subject.pquncontrolledMachine learningen_US
dc.subject.pquncontrolledRandom forestsen_US
dc.subject.pquncontrolledWeed risk assessmenten_US
dc.titleA COMPARATIVE ANALYSIS OF RANDOM FOREST AND LOGISTIC REGRESSION FOR WEED RISK ASSESSMENTen_US
dc.typeThesisen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Harris_umd_0117N_19218.pdf
Size:
1.73 MB
Format:
Adobe Portable Document Format
Download

Collections

UMD Theses and Dissertations
Plant Science & Landscape Architecture Theses and Dissertations