Improving and Developing Statistical Methods for Analyzing Air Pollution Measurements

Simple item page
dc.contributor.advisorGriffin, Roberten_US
dc.creatorActkinson, Blakeen_US
dc.date.accessioned2022-10-05T20:44:48Zen_US
dc.date.created2022-05en_US
dc.date.issued2022-04-19en_US
dc.date.submittedMay 2022en_US
dc.date.updated2022-10-05T20:44:48Zen_US
dc.description.abstractWith the advent of a big data revolution in air pollution research comes a necessity for refining existing statistical techniques and developing new ones that are robust, scalable, and informative. This work discusses the development of novel statistical methods applied to air pollution and can be broken into two parts: improving an existing method to analyze air pollution measurements taken at stationary monitors and developing new methods to analyze novel measurements taken with a mobile platform. In the first main chapter of this thesis, Dynamic Principal Component Analysis (DPCA) is discussed as an alternative to Principal Component Analysis (PCA) for analyzing time-dependent relationships between air pollutant variables measured at stationary monitors. DPCA is shown to offer several advantages over PCA, in that it generates a set of statistics which are time dependent and uncovers a wealth of information not readily apparent in a conventional static application. The second part of this work discusses development of new statistical methods to analyze a burgeoning and increasingly important method of measuring air pollution, which is through mobile monitoring. Mobile monitoring offers excellent spatial coverage at the expense of temporal coverage, making many conventional statistical techniques frequently employed by the atmospheric sciences community ill-suited for analysis of these measurements. Subsequent chapters discuss mobile monitoring as a measurement strategy, a novel algorithm to derive and quantify the background in mobile monitoring measurements, and another novel algorithm to identify and analyze detected plumes in time series. Results from these algorithms showcase the power mobile measurements have to inform stakeholders about the spatial variability of air pollution not obvious through the use of stationary monitors alone. It is hoped that through the refinement and development of these techniques and others that an important and exciting era of air pollution research can be ushered and its long-term mysteries solved.en_US
dc.embargo.lift2024-05-01en_US
dc.embargo.terms2024-05-01en_US
dc.format.mimetypeapplication/pdfen_US
dc.identifier.citationActkinson, Blake. "Improving and Developing Statistical Methods for Analyzing Air Pollution Measurements." (2022) Diss., Rice University. <a href="https://hdl.handle.net/1911/113501">https://hdl.handle.net/1911/113501</a>.en_US
dc.identifier.urihttps://hdl.handle.net/1911/113501en_US
dc.language.isoengen_US
dc.rightsCopyright is held by the author, unless otherwise indicated. Permission to reuse, publish, or reproduce the work beyond the bounds of fair use or other exemptions to copyright law must be obtained from the copyright holder.en_US
dc.subjectAir pollutionen_US
dc.subjectStatisticsen_US
dc.titleImproving and Developing Statistical Methods for Analyzing Air Pollution Measurementsen_US
dc.typeThesisen_US
dc.type.materialTexten_US
thesis.degree.departmentCivil and Environmental Engineeringen_US
thesis.degree.disciplineEngineeringen_US
thesis.degree.grantorRice Universityen_US
thesis.degree.levelDoctoralen_US
thesis.degree.nameDoctor of Philosophyen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
ACTKINSON-DOCUMENT-2022.pdf
Size:
14.3 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 2 of 2
No Thumbnail Available
Name:
PROQUEST_LICENSE.txt
Size:
5.84 KB
Format:
Plain Text
Description:
Download
No Thumbnail Available
Name:
LICENSE.txt
Size:
2.61 KB
Format:
Plain Text
Description:
Download
Collections
Rice University Theses and Dissertations