A Nondestructive Alternative for Kerogen Type Determination in Potential Hydrocarbon Source Rocks Using Hyperspectral Data and Machine Learning
In petroleum geology, to assess the hydrocarbon generation potential in source rocks involves the determination of the kerogen type by some destructive method. The usage of such methods is a bottleneck in the process because it is time-consuming, requires specialized tools and personnel, and ends up...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9844790/ |
| _version_ | 1828424797797744640 |
|---|---|
| author | Taina T. Guimaraes Lucas S. Kupssinsku Milena B. Cardoso Leonardo Bachi Alysson S. Aires Emilie C. Koste Andre L. D. Spigolon Luiz Gonzaga Mauricio R. Veronez |
| author_facet | Taina T. Guimaraes Lucas S. Kupssinsku Milena B. Cardoso Leonardo Bachi Alysson S. Aires Emilie C. Koste Andre L. D. Spigolon Luiz Gonzaga Mauricio R. Veronez |
| author_sort | Taina T. Guimaraes |
| collection | DOAJ |
| description | In petroleum geology, to assess the hydrocarbon generation potential in source rocks involves the determination of the kerogen type by some destructive method. The usage of such methods is a bottleneck in the process because it is time-consuming, requires specialized tools and personnel, and ends up destroying the rock sample, so it is not possible to do any posterior analysis. This study presents an alternative method for determination of the kerogen type that is fast and nondestructive using hyperspectral data and machine learning techniques. The method is validated using five distinct supervised learning algorithms that were applied to spectral data collected in rock samples from Taubaté Basin, Brazil, of an outcrop whose rocks have a wide range of hydrocarbon generation potential. Cores and samples were collected from the outcrop and had their kerogen type determined by geochemical analyses performed in the laboratory. The robustness of the method is evaluated in two distinct experiments. In the first one, the hyperspectral dataset was collected using a nonimaging spectroradiometer; in the second one, the method uses nonimaging hyperspectral data as training and is tested in hyperspectral images collected. In both experiments, the method was able to establish a relationship between selected spectral features and the kerogen type of the source rocks sampled. The results obtained in this article are prospective for nondestructive classification of kerogen type (and, consequently, the hydrocarbon generation potential) since most of the models generated achieved accuracy above 0.8 in the validation step and 0.75 in the test step. |
| first_indexed | 2024-12-10T16:23:01Z |
| format | Article |
| id | doaj.art-ac90f13435704a4fb1ea83135aed9d45 |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-12-10T16:23:01Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-ac90f13435704a4fb1ea83135aed9d452022-12-22T01:41:46ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352022-01-01156418643110.1109/JSTARS.2022.31950889844790A Nondestructive Alternative for Kerogen Type Determination in Potential Hydrocarbon Source Rocks Using Hyperspectral Data and Machine LearningTaina T. Guimaraes0https://orcid.org/0000-0002-6362-6591Lucas S. Kupssinsku1https://orcid.org/0000-0003-2580-3996Milena B. Cardoso2https://orcid.org/0000-0001-8652-884XLeonardo Bachi3https://orcid.org/0000-0002-0744-9594Alysson S. Aires4https://orcid.org/0000-0001-6370-226XEmilie C. Koste5Andre L. D. Spigolon6https://orcid.org/0000-0002-0545-1244Luiz Gonzaga7https://orcid.org/0000-0002-7661-2447Mauricio R. Veronez8https://orcid.org/0000-0002-5914-3546Graduate Program in Applied Computing and the Vizlab—X-Reality and Geoinformatics Lab, Vale do Rio dos Sinos University, São Leopoldo, CEP, BrazilGraduate Program in Applied Computing and the Vizlab—X-Reality and Geoinformatics Lab, Vale do Rio dos Sinos University, São Leopoldo, CEP, BrazilGraduate Program in Applied Computing and the Vizlab—X-Reality and Geoinformatics Lab, Vale do Rio dos Sinos University, São Leopoldo, CEP, BrazilGraduate Program in Applied Computing and the Vizlab—X-Reality and Geoinformatics Lab, Vale do Rio dos Sinos University, São Leopoldo, CEP, BrazilGraduate Program in Applied Computing and the Vizlab—X-Reality and Geoinformatics Lab, Vale do Rio dos Sinos University, São Leopoldo, CEP, BrazilGraduate Program in Applied Computing and the Vizlab—X-Reality and Geoinformatics Lab, Vale do Rio dos Sinos University, São Leopoldo, CEP, BrazilResearch and Development Center of Petrobras, Rio de Janeiro, CEP, BrazilGraduate Program in Applied Computing and the Vizlab—X-Reality and Geoinformatics Lab, Vale do Rio dos Sinos University, São Leopoldo, CEP, BrazilGraduate Program in Applied Computing and the Vizlab—X-Reality and Geoinformatics Lab, Vale do Rio dos Sinos University, São Leopoldo, CEP, BrazilIn petroleum geology, to assess the hydrocarbon generation potential in source rocks involves the determination of the kerogen type by some destructive method. The usage of such methods is a bottleneck in the process because it is time-consuming, requires specialized tools and personnel, and ends up destroying the rock sample, so it is not possible to do any posterior analysis. This study presents an alternative method for determination of the kerogen type that is fast and nondestructive using hyperspectral data and machine learning techniques. The method is validated using five distinct supervised learning algorithms that were applied to spectral data collected in rock samples from Taubaté Basin, Brazil, of an outcrop whose rocks have a wide range of hydrocarbon generation potential. Cores and samples were collected from the outcrop and had their kerogen type determined by geochemical analyses performed in the laboratory. The robustness of the method is evaluated in two distinct experiments. In the first one, the hyperspectral dataset was collected using a nonimaging spectroradiometer; in the second one, the method uses nonimaging hyperspectral data as training and is tested in hyperspectral images collected. In both experiments, the method was able to establish a relationship between selected spectral features and the kerogen type of the source rocks sampled. The results obtained in this article are prospective for nondestructive classification of kerogen type (and, consequently, the hydrocarbon generation potential) since most of the models generated achieved accuracy above 0.8 in the validation step and 0.75 in the test step.https://ieeexplore.ieee.org/document/9844790/Classificationhydrocarbon source rockhyperspectralkerogen typemachine learning (ML) |
| spellingShingle | Taina T. Guimaraes Lucas S. Kupssinsku Milena B. Cardoso Leonardo Bachi Alysson S. Aires Emilie C. Koste Andre L. D. Spigolon Luiz Gonzaga Mauricio R. Veronez A Nondestructive Alternative for Kerogen Type Determination in Potential Hydrocarbon Source Rocks Using Hyperspectral Data and Machine Learning IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Classification hydrocarbon source rock hyperspectral kerogen type machine learning (ML) |
| title | A Nondestructive Alternative for Kerogen Type Determination in Potential Hydrocarbon Source Rocks Using Hyperspectral Data and Machine Learning |
| title_full | A Nondestructive Alternative for Kerogen Type Determination in Potential Hydrocarbon Source Rocks Using Hyperspectral Data and Machine Learning |
| title_fullStr | A Nondestructive Alternative for Kerogen Type Determination in Potential Hydrocarbon Source Rocks Using Hyperspectral Data and Machine Learning |
| title_full_unstemmed | A Nondestructive Alternative for Kerogen Type Determination in Potential Hydrocarbon Source Rocks Using Hyperspectral Data and Machine Learning |
| title_short | A Nondestructive Alternative for Kerogen Type Determination in Potential Hydrocarbon Source Rocks Using Hyperspectral Data and Machine Learning |
| title_sort | nondestructive alternative for kerogen type determination in potential hydrocarbon source rocks using hyperspectral data and machine learning |
| topic | Classification hydrocarbon source rock hyperspectral kerogen type machine learning (ML) |
| url | https://ieeexplore.ieee.org/document/9844790/ |
| work_keys_str_mv | AT tainatguimaraes anondestructivealternativeforkerogentypedeterminationinpotentialhydrocarbonsourcerocksusinghyperspectraldataandmachinelearning AT lucasskupssinsku anondestructivealternativeforkerogentypedeterminationinpotentialhydrocarbonsourcerocksusinghyperspectraldataandmachinelearning AT milenabcardoso anondestructivealternativeforkerogentypedeterminationinpotentialhydrocarbonsourcerocksusinghyperspectraldataandmachinelearning AT leonardobachi anondestructivealternativeforkerogentypedeterminationinpotentialhydrocarbonsourcerocksusinghyperspectraldataandmachinelearning AT alyssonsaires anondestructivealternativeforkerogentypedeterminationinpotentialhydrocarbonsourcerocksusinghyperspectraldataandmachinelearning AT emilieckoste anondestructivealternativeforkerogentypedeterminationinpotentialhydrocarbonsourcerocksusinghyperspectraldataandmachinelearning AT andreldspigolon anondestructivealternativeforkerogentypedeterminationinpotentialhydrocarbonsourcerocksusinghyperspectraldataandmachinelearning AT luizgonzaga anondestructivealternativeforkerogentypedeterminationinpotentialhydrocarbonsourcerocksusinghyperspectraldataandmachinelearning AT mauriciorveronez anondestructivealternativeforkerogentypedeterminationinpotentialhydrocarbonsourcerocksusinghyperspectraldataandmachinelearning AT tainatguimaraes nondestructivealternativeforkerogentypedeterminationinpotentialhydrocarbonsourcerocksusinghyperspectraldataandmachinelearning AT lucasskupssinsku nondestructivealternativeforkerogentypedeterminationinpotentialhydrocarbonsourcerocksusinghyperspectraldataandmachinelearning AT milenabcardoso nondestructivealternativeforkerogentypedeterminationinpotentialhydrocarbonsourcerocksusinghyperspectraldataandmachinelearning AT leonardobachi nondestructivealternativeforkerogentypedeterminationinpotentialhydrocarbonsourcerocksusinghyperspectraldataandmachinelearning AT alyssonsaires nondestructivealternativeforkerogentypedeterminationinpotentialhydrocarbonsourcerocksusinghyperspectraldataandmachinelearning AT emilieckoste nondestructivealternativeforkerogentypedeterminationinpotentialhydrocarbonsourcerocksusinghyperspectraldataandmachinelearning AT andreldspigolon nondestructivealternativeforkerogentypedeterminationinpotentialhydrocarbonsourcerocksusinghyperspectraldataandmachinelearning AT luizgonzaga nondestructivealternativeforkerogentypedeterminationinpotentialhydrocarbonsourcerocksusinghyperspectraldataandmachinelearning AT mauriciorveronez nondestructivealternativeforkerogentypedeterminationinpotentialhydrocarbonsourcerocksusinghyperspectraldataandmachinelearning |