본문 바로가기
KERD
논문

딥러닝기반 이미지로그의 압축파쇄대 심도 검출모델 개발

Development of Deep Learning-Based Detection Model for Borehole Breakout Depths in Image Logs

장찬동|조영욱|김하영|염주열|이경북
한국자원공학회 (The Korean Society of Mineral and Energy Resources Engineers)|2024.12|한국자원공학회지 (Journal of the Korean Society of Mineral and Energy Resources Engineers)|제61권 제6호|pp. 468-479|DOI 10.32390/ksmer.2024.61.6.468

0

조회

0

다운로드

0

인용

0

참고문헌

키워드

장단기기억confusion matrix혼동행렬압축파쇄대이미지로그익스트림 그래디언트 부스팅borehole breakoutimage loglong short-term memory (LSTM)extreme gradient boosting (XGBoost)
주제분류자원공학

초록

본 연구는 이미지로그의 압축파쇄대 심도를 검출하기 위해 장단기기억(long short-term memory, LSTM)을 적용하여 XGBoost(extreme gradient boosting) 모델의 한계를 보완하고자 한다. 경주시심도 1 km 시추공의 이미지로그를 전처리하여 얻어진 99,084개 자료로 XGBoost와 LSTM 모델을개발하였다. 단일 심도만을 고려하는 XGBoost 모델과 달리, LSTM 모델은 연속된 7개 심도자료로중앙심도의 압축파쇄대 여부를 분석한다. XGBoost 대비 LSTM 모델은 테스트자료에서 false negative가 88% 감소하였고 재현율이 29% 향상되었다. 또한 7개 심도자료를 활용한 XGBoost 모델과 비교 시에도 우수한 성능을 보였다. 이는 LSTM이 연속된 심도자료를 체계적으로 분석하여전문가의 응력분석 효율성을 향상시킬 수 있음을 시사한다.

Abstract

This study applied the long short-term memory (LSTM) algorithm to detect the depths of borehole breakouts in image logs to overcome the limitations of the extreme gradient boosting (XGBoost) model. Using 99,084 data obtained from the preprocessed image log of a 1 km deep borehole in Gyeongju-si, we developed both XGBoost and LSTM models. While the XGBoost model considers only single-depth data, the LSTM model analyzes the occurrence of borehole breakouts at the central depth using data from seven consecutive depths. The LSTM model showed an 88% reduction in false negatives and 29% improvement in recall on the test data compared to the XGBoost model. It also outperformed the XGBoost model that using the seven-depth data. These results suggest that the LSTM model can systematically analyze sequential depth data to enhance the efficiency of experts in stress analysis.

참고문헌 (36)

  1. Alom, M. Z., "A state-of-the-art survey on deep learning theory and architectures", Electronics, 8(3), pp.292~ (2019)
  2. Alzubaidi, F., "Automatic fracture detection and characterization from unwrapped drill-core images using mask R-CNN", Journal of Petroleum Science and Engineering, 208(Part C), pp.109471~ (2022)
  3. Barton, C. A., "Utilizing wellbore image data to determine the complete stress tensor : application to permeability anisotropy and wellbore stability", The Log Analyst, 38(6) (1997)
  4. Barton, C. A., "In-situ stress orientation and magnitude at the Fenton Geothermal Site, New Mexico, determined from wellbore breakouts", Geophysical Research Letters, 15(5), pp.467~470 (1988)
  5. Chang, C., "Critical pore pressure assessment for CO2geological storage in Gyeongsang Basin, Korea, from a geomechanics perspective", Geosciences Journal, 21, pp.617~630 (2017)
  6. Chen, M. Y., "Formation imaging with microelectrical scanning arrays", The Log Analyst, 28(3) (1987)
  7. Chen, T., "XGBoost: A scalable tree boosting system", Proceedings of the 22nd ACM SICKDD International Conference on Knowledge Discovery and Data Mining (2016), ACM
  8. Dias, L. O., "Automatic detection of fractures and breakouts patterns in acoustic borehole image logs using fast-region convolutional neural networks", Journal of Petroleum Science and Engineering, 191, pp.107099~ (2020)
  9. Du, L., "Automatic fracture detection from the images of electrical image logs using Mask RCNN", Fuel, 351, pp.128992~ (2023)
  10. Elman, J. L., "Finding structure in time", Cognitive Science, 14(2), pp.179~211 (1990)
  11. Friedman, J. H., "Greedy function approximation: A gradient boosting machine", The Annals of Statistics, 29(5), pp.1189~1232 (2001)
  12. Han, S., "Automatic borehole fracture detection and characterization with tailored Faster R-CNN and simplified Hough transform", Engineering Applications of Artificial Intelligence, 126(Part C), pp.107024~ (2023)
  13. Heidbach, O., "The World Stress Map database release 2016: Crustal stress pattern across scales", Tectonophysics, 744, pp.484~498 (2018)
  14. Heidbach, O., "World stress map 2016", GFZ Data Services, ~ (2016)
  15. Hochreiter, S, "Long short-term memory", Neural Computation, 9(8), pp.1735~1780 (1997)
  16. Hochreiter, S., "The vanishing gradient problem during learning recurrent neural nets and problem solutions", International Journal of Uncertainty Fuzziness and Knowledge-Based Systems, 6(2), pp.107~116 (1998)
  17. Hwang, H., "XGBoost model to identify potential factors improving and deteriorating elderly cognition", The Journal of Korean Institute of Next Generation Computing, 14(3), pp.16~24 (2018)
  18. Jo, Y., "In situ stress states at KURT, an underground research laboratory in South Korea for the study of high-level radioactive waste disposal", Engineering Geology, 259, pp.105198~ (2019)
  19. Ki, S., "Prediction of missing tubing head pressure using recurrent neural network", Journal of the Korean Society of Mineral and Energy Resources Engineers, 56(5), pp.416~426 (2019)
  20. Kim, H., "Improvement of RNN-based prediction for shale-gas production with data preprocessing in Montney shale play", Gas Science and Engineering (2024)
  21. Lagraba, J. O. P., "Borehole image tool design, value of information, and tool selection", Dipmeter and Borehole Image Log Technology, 92, pp.15~38 (2010)
  22. Lee, D. Y., "Analysis of the shale gas production prediction model based on machine learning using productivity factors", Journal of the Korean Society of Mineral and Energy Resources Engineers, 61(2), pp.111~123 (2024)
  23. Lee, K., "Prediction of shale-gas production at duvernay formation using deeplearning algorithm", SPE Journal, 24(6), pp.2423~2437 (2019)
  24. Li, X., "The geomechanics of Shenhua carbon dioxide capture and storage (CCS) demonstration project in Ordos Basin, China", Journal of Rock Mechanics and Geotechnical Engineering, 8(6), pp.948~966 (2016)
  25. Liu, G., "VirusPredictor:XGBoost-based software to predict virus-related sequences in human data", Bioinformatics, 40(4), pp.btae192~ (2024)
  26. Ma, J., "Analyzing the leading causes of traffic fatalities using XGBoost and grid-based analysis: a city management perspective", IEEE Access, 7, pp.148059~148072 (2019)
  27. Olya, B. A. M., "Toward real-time fracture detection on image logs using deep convolutional neural network YOLOv5", Interpretation, 12(2), pp.SB9~SB18 (2024)
  28. Qiao, B., "A parallel feature selection method based on NMI-XGBoost and distance correlation for typhoon trajectory prediction", The Journal of Supercomputing, 80, pp.11293~11321 (2024)
  29. Schuster, M., "Bidirectional recurrent neural networks", IEEE Transactions on Signal Processing, 45(11), pp.2673~2681 (1997)
  30. Shamir, G., "Stress orientation profile to 3.5 km depth near the San Andreas Fault at Cajon Pass, California", Journal of Geophysical Research: Solid Earth, 97(B4), pp.5059~5080 (1992)
  31. "XGBoost" (2024)[URL]
  32. Yang, J., "Automated extraction of borehole breakout properties from acoustic televiewer (ATV) data", Proceedings of the 56th U.S. Rock Mechanics, 2022, ~[DOI]
  33. Yeom, J., "Detection of borehole breakout depth in image logs using machine learning algorithms", The Korean Society of Mineral and Energy Resources Engineers, 60(4), pp.223~230 (2023)
  34. Zhang, W., "Automatic detection of fractures based on optimal path search in well logging images", Journal of Sensors, 2021(1), pp.5577084~ (2021)
  35. Zhu, J., "A review of geothermal energy resources, development, and applications in China: Current status and prospects", Energy, 93(1), pp.466~483 (2015)
  36. Zoback, M. D., "Reservoir geomechanics", pp.449~ (2010), Cambridge University Press

관련 논문AI추천

머신러닝을 이용한 이미지로그의 압축파쇄대 깊이 검출모델 개발김하영, 염주열, 이경북, 장찬동, 조영욱한국자원공학회 · 한국자원공학회지2023 · 제60권 제4호딥러닝을 이용한 화강암 X-ray CT 영상에서의 균열 검출에 관한 연구김광염, 김예진, 윤태섭, 이준성, 전성환, 현석환한국암반공학회 · 터널과 지하공간2019 · 제29권 제3호딥러닝 알고리듬을 활용한 고해상도 물리검층 자료의 생성 연구김민, 권서윤, 민배현, 박가영, 이수진, 지민수, 최수인한국자원공학회 · 한국자원공학회지2022 · 제59권 제5호가스하이드레이트 저류층 모델링을 위한 심층학습 기반 물리검층 해석의 최신 기술동향 분석권서윤, 김광현, 김성일, 민배현, 박가영, 이경북, 지민수, Nguyen Xuan Huy한국자원공학회 · 한국자원공학회지2021 · 제58권 제2호딥러닝을 활용한 암석 분류 프레임워크: 터널 안정성 모니터링 및 유지관리를 위한 데이터 기반 접근 방식김용성, 김용진, 박종설, 이승주, 지봉준한국지반신소재학회 · 한국지반신소재학회 논문집2025 · 제24권 제1호셰일가스 생산량 예측 모델의 성능개선을 위한 장단기기억 신경망 기반 생산감퇴특성 추출 및 활용 연구신효진, 이대모, 임종세한국자원공학회 · 한국자원공학회지2023 · 제60권 제6호

이 간행물의 다른 논문 (6건)

비소 및 수은 오염 농경지토양의 복원을 위한 옥살산 및 요오드화 칼륨을 이용한 토양세척공법 적용성 평가고주인, 이민현, 권요셉, 고일하, 지원현, 이시연pp. 447-454아사바스카 오일샌드 저류층에서의 toe-up SAGD 예열단계 최적화 연구김남화, 신현돈, 백진현pp. 455-467현무암 내 CO2 수용액 주입에 따른 탄소 광물화 및 암석 물성 변화에 관한 코어 규모 모델링 및 시뮬레이션 연구민배현, 권태혁, 서정규, 김호상, 안영빈, 윤소은pp. 480-499국내외 철강산업 전과정평가 표준 및 지침 비교 분석이윤모, 황용우, 김서연, 김다연, 조성진, 오창용pp. 500-509한국지질자원연구원 신규 기본사업(2025-2030) 기획 및 개발 전략: 연구성과 지식파급효과 분석을 중심으로배준희, 신재은, 이재욱pp. 510-516
원문 보기