Graduate Thesis Or Dissertation
 

Opening Pandora’s Box: Machine learning applications for chemical forensics and non-target chemical analyses

Public Deposited

Downloadable Content

Download PDF
https://ir.library.oregonstate.edu/concern/graduate_thesis_or_dissertations/x346dc185

Descriptions

Attribute NameValues
Creator
Abstract
  • Water bodies act as chemical data loggers that contain tens of thousands of molecules that represent the sum of the biological, chemical, and physical processes occurring within a watershed. We hypothesize that unique chemical signatures present within a water sample can be informative of upstream processes. By extracting non-polar organic compounds from water samples at/near chemical sources, and then use high-resolution mass spectrometry (HRMS) data in conjunction with machine learning tools to identify the chemical signatures that are diagnostic of each source. If these diagnostic signatures, or fingerprints, are detected in environmental samples, we can confirm the presence of source-specific discharge in receiving bodies of water. Grab samples were collected in western Oregon in 2018-19 and analyzed in triplicate from different sources including headwater streams, agricultural field runoff, animal manure, municipal wastewater, and urban/suburban road runoff. Data from machine learning models indicate that each source is readily distinguishable based on its chemical composition and that as few as 10 non-target chemical compounds can be diagnostic of chemical sources. Diagnostic chemical fingerprints were detected in high probability in mixed water samples (e.g., creeks). This workflow is open source and freely available to help managers identify pollutant sources present in receiving water bodies, which will help direct limited resources to projects that maximize water quality improvements.
License
Resource Type
Date Issued
Degree Level
Degree Name
Degree Field
Degree Grantor
Commencement Year
Advisor
Committee Member
Academic Affiliation
Rights Statement
Publisher
Peer Reviewed
Language

Relationships

Parents:

This work has no parents.

In Collection:

Items

Thumbnail Title Date Uploaded Visibility Actions
file details DavilaSantiagoEmmanuel2020.pdf 2020-11-14 Public Download