About Site Language

WHDL is viewable in multiple languages. Use the pull-down menu to select a language to view the site.

I changed my language, but I’m still seeing resources in the other languages?

If a resource or text has not been translated into your selected language, it will appear in the initially added language. We are always looking for help translating these resources. If you can help, contact us!

WHDL - 00016169

Statistical Analysis of Forest Burn Extent Data

Tyler J. Shea

Resource Types

Academic (Thesis, Dissertation, Etc.)

Resource Languages

English

Institutional Repository

Description / Abstract

Submitted to the Department of Mathematics and Computer Science in partial fulfillment of the requirements for the degree of Bachelor of Science

Various machine learning algorithms have been shown to be effective methods of mapping forest fire burn extent and tree mortality. The algorithms use drone imagery to classify pixels as burned or unburned. Recent efforts used a mask region-based convolutional neural network (MR-CNN) and support vector machine (SVM) to label pixels in a post-fire forest as being within the fire’s extent. These algorithms reclassified the pixels using the Unburned Tree Noise and Sub-Crown Burn Reclassifications. The objective was that these reclassifications would produce more accurate results than the previously computed Surface Burn Classification. The purpose of this project was to use analysis methods to determine statistical significance in the results, and decide whether the reclassifications gave significantly better results than the original classification. The primary tools used in the analysis were the one- and two-tailed paired Student’s t-tests. These tests were conducted on the sensitivity results given by the algorithms, because sensitivity was considered the metric of most importance due to precedence being placed on minimizing the false negative percentage. Results calculated from the t-tests demonstrated that the new reclassifications produced a statistically significant increase in sensitivity over relying solely on the Surface Burn Classification for burn extent mapping.

Download this Resource

Download Free from WHDL

Download as a PDF: Statistical Analysis of Forest Burn
File Size Small - 582 KB

Go to Download Information

Subject Index

Copyright Notes

This material is used by permission of the rightsholder in accordance with the terms of the relevant content release. As a user, you have permission to use this content and download a copy for non-commercial use only. Downloading multiple quantities of this resource is expressly forbidden.

KeywordsStatistical analysis, Paired student's t-test, Forest burn extent

Degree AwardedBachelor of Science

Awarding InstitutionNorthwest Nazarene University

Committee MembersStephen Riley, Barry L. Myers

Supervisor or ChairDale A. Hamilton

Peer Reviewed?No

Keep Browsing