Quantitative logging data clustering with hidden Markov model to assist log unit classification
Abstract Revealing subsurface structures is a fundamental task in geophysical and geological studies. Logging data are usually acquired through drilling projects, which constrain the subsurface structure, and together with the description of drill core samples, are used to distinguish geological uni...
| Үндсэн зохиолчид: | , , , , , , |
|---|---|
| Формат: | Өгүүллэг |
| Хэл сонгох: | English |
| Хэвлэсэн: |
SpringerOpen
2022-06-01
|
| Цуврал: | Earth, Planets and Space |
| Нөхцлүүд: | |
| Онлайн хандалт: | https://doi.org/10.1186/s40623-022-01651-0 |
| _version_ | 1828323826635636736 |
|---|---|
| author | Suguru Yabe Yohei Hamada Rina Fukuchi Shunichi Nomura Norio Shigematsu Tsutomu Kiguchi Kenta Ueki |
| author_facet | Suguru Yabe Yohei Hamada Rina Fukuchi Shunichi Nomura Norio Shigematsu Tsutomu Kiguchi Kenta Ueki |
| author_sort | Suguru Yabe |
| collection | DOAJ |
| description | Abstract Revealing subsurface structures is a fundamental task in geophysical and geological studies. Logging data are usually acquired through drilling projects, which constrain the subsurface structure, and together with the description of drill core samples, are used to distinguish geological units. Clustering is useful for interpreting logging data and making log unit classification and is usually performed by manual inspection of the data. However, the validity of clustering results with such subjective criteria may be questionable. This study proposed the application of a statistical clustering method, the hidden Markov model, to conduct unsupervised clustering of logging data. As logging data are aligned along the drilled hole, they and the geological structure hidden behind such sequential datasets can be regarded as observables and hidden states in the hidden Markov model. When log unit classification is manually conducted, depth dependency of logging data is usually focused. Therefore, we included depth information as observables to explicitly represent depth dependency of logging data. The model was applied to the following geological settings: the accretionary prism at the Nankai Trough, the onshore fault zone at the Kii Peninsula (southwest Japan), and the forearc basin at the Japan Trench. The optimum number of clusters were searched using a quantitative index. The clustering results using the hidden Markov model were consistent with previously reported classifications or lithological descriptions; however, our method allowed a more detailed division of logging data, which is useful to interpret geological structures, such as a fault or a fault zone. Therefore, the use of the hidden Markov model enabled us to clarify assumptions quantitatively and conduct clustering consistently for the entire depth range, even for different geological sites. The proposed method is expected to have wider applicability and extensibility for other types of data, including geochemical and structural geological data. Graphical Abstract |
| first_indexed | 2024-04-13T18:57:25Z |
| format | Article |
| id | doaj.art-a2d1a80e54aa49eaa9e5d9adb51e2544 |
| institution | Directory Open Access Journal |
| issn | 1880-5981 |
| language | English |
| last_indexed | 2024-04-13T18:57:25Z |
| publishDate | 2022-06-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Earth, Planets and Space |
| spelling | doaj.art-a2d1a80e54aa49eaa9e5d9adb51e25442022-12-22T02:34:11ZengSpringerOpenEarth, Planets and Space1880-59812022-06-0174112110.1186/s40623-022-01651-0Quantitative logging data clustering with hidden Markov model to assist log unit classificationSuguru Yabe0Yohei Hamada1Rina Fukuchi2Shunichi Nomura3Norio Shigematsu4Tsutomu Kiguchi5Kenta Ueki6Geological Survey of Japan, National Institute of Advanced Industrial Science and TechnologyInstitute for Extra-Cutting-Edge Science and Technology Avant-Garde Research, Kochi Institute for Core Sample Research, Japan Agency for Marine-Earth Science and TechnologyNaruto University of EducationGraduate School of Accountancy, Waseda UniversityGeological Survey of Japan, National Institute of Advanced Industrial Science and TechnologyGeological Survey of Japan, National Institute of Advanced Industrial Science and TechnologyResearch Institute for Marine Geodynamics, Japan Agency for Marine-Earth Science and TechnologyAbstract Revealing subsurface structures is a fundamental task in geophysical and geological studies. Logging data are usually acquired through drilling projects, which constrain the subsurface structure, and together with the description of drill core samples, are used to distinguish geological units. Clustering is useful for interpreting logging data and making log unit classification and is usually performed by manual inspection of the data. However, the validity of clustering results with such subjective criteria may be questionable. This study proposed the application of a statistical clustering method, the hidden Markov model, to conduct unsupervised clustering of logging data. As logging data are aligned along the drilled hole, they and the geological structure hidden behind such sequential datasets can be regarded as observables and hidden states in the hidden Markov model. When log unit classification is manually conducted, depth dependency of logging data is usually focused. Therefore, we included depth information as observables to explicitly represent depth dependency of logging data. The model was applied to the following geological settings: the accretionary prism at the Nankai Trough, the onshore fault zone at the Kii Peninsula (southwest Japan), and the forearc basin at the Japan Trench. The optimum number of clusters were searched using a quantitative index. The clustering results using the hidden Markov model were consistent with previously reported classifications or lithological descriptions; however, our method allowed a more detailed division of logging data, which is useful to interpret geological structures, such as a fault or a fault zone. Therefore, the use of the hidden Markov model enabled us to clarify assumptions quantitatively and conduct clustering consistently for the entire depth range, even for different geological sites. The proposed method is expected to have wider applicability and extensibility for other types of data, including geochemical and structural geological data. Graphical Abstracthttps://doi.org/10.1186/s40623-022-01651-0Hidden Markov modelLogging dataClusteringUnit classification |
| spellingShingle | Suguru Yabe Yohei Hamada Rina Fukuchi Shunichi Nomura Norio Shigematsu Tsutomu Kiguchi Kenta Ueki Quantitative logging data clustering with hidden Markov model to assist log unit classification Earth, Planets and Space Hidden Markov model Logging data Clustering Unit classification |
| title | Quantitative logging data clustering with hidden Markov model to assist log unit classification |
| title_full | Quantitative logging data clustering with hidden Markov model to assist log unit classification |
| title_fullStr | Quantitative logging data clustering with hidden Markov model to assist log unit classification |
| title_full_unstemmed | Quantitative logging data clustering with hidden Markov model to assist log unit classification |
| title_short | Quantitative logging data clustering with hidden Markov model to assist log unit classification |
| title_sort | quantitative logging data clustering with hidden markov model to assist log unit classification |
| topic | Hidden Markov model Logging data Clustering Unit classification |
| url | https://doi.org/10.1186/s40623-022-01651-0 |
| work_keys_str_mv | AT suguruyabe quantitativeloggingdataclusteringwithhiddenmarkovmodeltoassistlogunitclassification AT yoheihamada quantitativeloggingdataclusteringwithhiddenmarkovmodeltoassistlogunitclassification AT rinafukuchi quantitativeloggingdataclusteringwithhiddenmarkovmodeltoassistlogunitclassification AT shunichinomura quantitativeloggingdataclusteringwithhiddenmarkovmodeltoassistlogunitclassification AT norioshigematsu quantitativeloggingdataclusteringwithhiddenmarkovmodeltoassistlogunitclassification AT tsutomukiguchi quantitativeloggingdataclusteringwithhiddenmarkovmodeltoassistlogunitclassification AT kentaueki quantitativeloggingdataclusteringwithhiddenmarkovmodeltoassistlogunitclassification |