Application of LF-NMR measurements and supervised learning regression methods for improved characterization of heavy oils and bitumens
This work studies the physicochemical properties of unconventional hydrocarbon resources such as heavy oils and bitumens. The principal methods used in the research consisted of LF-NMR experiments, hypothesis testing, and statistical and data-driven modeling. The research output consists of several...
| Main Author: | |
|---|---|
| Format: | Thesis |
| Published: |
Curtin University
2022
|
| Online Access: | http://hdl.handle.net/20.500.11937/89363 |
| _version_ | 1848765207648665600 |
|---|---|
| author | Markovic, Strahinja |
| author_facet | Markovic, Strahinja |
| author_sort | Markovic, Strahinja |
| building | Curtin Institutional Repository |
| collection | Online Access |
| description | This work studies the physicochemical properties of unconventional hydrocarbon resources such as heavy oils and bitumens. The principal methods used in the research consisted of LF-NMR experiments, hypothesis testing, and statistical and data-driven modeling. The research output consists of several machine learning and analytical models capable of predicting heavy oil and bitumen viscosity and core sample water saturation with high accuracy. These results provide a strong case for in-situ LF-NMR applications in well logging. |
| first_indexed | 2025-11-14T11:31:35Z |
| format | Thesis |
| id | curtin-20.500.11937-89363 |
| institution | Curtin University Malaysia |
| institution_category | Local University |
| last_indexed | 2025-11-14T11:31:35Z |
| publishDate | 2022 |
| publisher | Curtin University |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | curtin-20.500.11937-893632022-09-27T01:57:19Z Application of LF-NMR measurements and supervised learning regression methods for improved characterization of heavy oils and bitumens Markovic, Strahinja This work studies the physicochemical properties of unconventional hydrocarbon resources such as heavy oils and bitumens. The principal methods used in the research consisted of LF-NMR experiments, hypothesis testing, and statistical and data-driven modeling. The research output consists of several machine learning and analytical models capable of predicting heavy oil and bitumen viscosity and core sample water saturation with high accuracy. These results provide a strong case for in-situ LF-NMR applications in well logging. 2022 Thesis http://hdl.handle.net/20.500.11937/89363 Curtin University fulltext |
| spellingShingle | Markovic, Strahinja Application of LF-NMR measurements and supervised learning regression methods for improved characterization of heavy oils and bitumens |
| title | Application of LF-NMR measurements and supervised learning regression methods for improved characterization of heavy oils and bitumens |
| title_full | Application of LF-NMR measurements and supervised learning regression methods for improved characterization of heavy oils and bitumens |
| title_fullStr | Application of LF-NMR measurements and supervised learning regression methods for improved characterization of heavy oils and bitumens |
| title_full_unstemmed | Application of LF-NMR measurements and supervised learning regression methods for improved characterization of heavy oils and bitumens |
| title_short | Application of LF-NMR measurements and supervised learning regression methods for improved characterization of heavy oils and bitumens |
| title_sort | application of lf-nmr measurements and supervised learning regression methods for improved characterization of heavy oils and bitumens |
| url | http://hdl.handle.net/20.500.11937/89363 |