본문 바로가기
KERD
논문

생산성 영향인자를 활용한 기계학습 기반 셰일가스 생산량 예측모델 분석

Analysis of the Shale Gas Production Prediction Model Based on Machine Learning Using Productivity Factors

신효진|임종세|이다영
한국자원공학회 (The Korean Society of Mineral and Energy Resources Engineers)|2024.04|한국자원공학회지 (Journal of the Korean Society of Mineral and Energy Resources Engineers)|제61권 제2호|pp. 111-123|DOI 10.32390/ksmer.2024.61.2.111

1

조회

0

다운로드

1

인용

0

참고문헌

키워드

기계학습machine learningfeature selection특징 선택셰일가스shale gas생산량 예측생산성 영향인자productivity factorproduction prediction
주제분류자원공학

초록

셰일가스 저류층에서의 복잡한 유동 메커니즘으로 불확실성이 존재하여 최근 기계학습을 활용한생산량 예측을 수행하고 있으나, 생산관련인자를 효율적으로 수집하고 분석하는 데는 어려움이 있다. 이 연구에서는 특징 선택을 활용하여 서로 다른 기준의 생산성 영향인자를 파악하고, 이를 다양한 기계학습 알고리즘에 적용하여 Barnett Shale의 가스 생산량을 예측하였다. 이에 Filter 기법 기반의 총 주입유체량, 측정 깊이, 하부 천공 위치 등 생산성 영향인자를 random forest 모델에 적용할 경우 오차율을 개선할 수 있음을 확인하였다. 이와 더불어 Marcellus Shale에서 제안된 특징 선택 과정및 기계학습 알고리즘의 확장 가능성을 파악하였으며, 이 연구를 통해 생산 정보 취득이 어려운 경우에도 제한된 변수를 활용하여 신뢰성 있는 생산량 예측이 가능할 것으로 사료된다.

Abstract

Owing to the uncertainties caused by complex flow mechanisms in shale gas reservoirs, production prediction using machine learning has recently been performed. However, efficiently collecting and analyzing production-related factors is difficult. In this study, the productivity factors of different criteria were identified using feature selection, and gas production was predicted using the selected factors in various machine learning models. The error rate improved when productivity factors such as total fluid, measured depth, and lower perforation based on the filter method were applied to the random forest model. In addition, the potential for extending the proposed feature selection process and machine learning algorithms in Marcellus Shale was identified, and a reliable production prediction was expected to be possible by utilizing limited variables even at the sites where production information was difficult to obtain.

참고문헌 (36)

  1. Abusamra, H., "A comparative study of feature selection and classification methods for gene expression data of glioma", Procedia Computer Science, 23, pp.5~14 (2013)
  2. Al Daoud, E., "Comparison between XGBoost, LightGBM and CatBoost using a home credit dataset", International Journal of Computer and Information Engineering, 13(1), pp.6~10 (2019)
  3. Breiman, L., "Machine learning, 24", pp.123~140 (1994), Kluwer academic publishers
  4. Chen, T., "XGBoost: A scalable tree boosting system", Proceedings of the 22nd ACM SICKDD International Conference on Knowledge Discovery and Data Mining, pp.785~794 (2016)
  5. Duong, A. N., "An unconventional rate decline approach for tight and fracture-dominated gas wells", Canadian Unconventional Resources and International Petroleum Conference, pp.15~ (2010), Canadian Society for Unconventional Gas
  6. Ekundayo, J. M., "Numerical simulation of gas production from gas Shale reservoirs-Influence of gas sorption hysteresis", Energies, 12(18), pp.12~ (2019)
  7. "Enverus" (2023)[URL]
  8. "Federal Reserve Bank of Dallas" (2023)[URL]
  9. Fonti, V., "Feature selection using LASSO", Amsterdam Research Paper in Business Analytics, 30, pp.1~25 (2017)
  10. Geng, L., "A fractal production prediction model for Shale gas reservoirs", Journal of Natural Gas Science and Engineering, 55, pp.354~367 (2018)
  11. Guo, C., "Improved numerical simulation for Shale gas reservoirs", Offshore Technology Conference-Asia, pp.17~ (2014)
  12. Guyon, I., "An introduction to variable and feature selection", Journal of Machine Learning Research, 3, pp.1157~1182 (2003)
  13. Hall, M. A., "Correlation-based Feature Selection for Machine Learning", PhD, pp.1999
  14. Jain, A., "Feature selection: evaluation, application, and small sample performance", IEEE Transactions on Pattern Analysis and Machine Intelligence, 19(2), pp.153~158 (1997)
  15. Jo, J. H., "Lasso regression of RNA-Seq data based on bootstrapping for robust feature selection", KIISE Transactions on Computing Practice, 23(9), pp.557~563 (2017)
  16. Ke, G., "LightGBM: A highly efficient gradient boosting decision tree", 31st Conference on Neural Information Processing Systems, Neural Information Processing Systems, pp.9~ (2017)
  17. Kim, J. S., "Probabilistic decline curve analysis for forecasting estimated ultimate recovery in Shale gas play", Journal of The Korean Society of Mineral and Energy Resources Engineers, 51(6), pp.808~819 (2014)
  18. Luo, G., "Production-strategy insights using machine learning:Application for Bakken Shale", SPE Reservoir Evaluation &Engineering, 22(3), pp.17~ (2019)
  19. New Mexico Bureau of Geology and Mineral Resources, "The Barnett Shale in southeastern New Mexico: distribution, thickness, and source rock characterization, 502", New Mexico tech socorro, 57~ (2007)
  20. Niu, W., "A production prediction method for Shale gas wells based on multiple regression", Energies, 14(5), pp.11~ (2021)
  21. Niu, W., "Development of Shale gas production prediction models based on machine learning using early data", Energy Reports, 8, pp.1229~1237 (2022)
  22. Oh, H. T., "Analysis of uncertainty trend for estimated ultimate recovery prediction of Shale gas with various production periods based on machine learning", Journal of The Korean Society of Mineral and Energy Resources Engineers, 58(5), pp.475~490 (2021)
  23. Panja, P., "Application of artificial intelligence to forecast hydrocarbon production from Shales", Petroleum, 4(1), pp.75~89 (2018)
  24. Peng, H., "Feature selection based on mutual information criteria of max-dependency, maxrelevance, and min-redundancy", IEEE Transactions on Pattern Analysis and Machine Intelligence, 27(8), pp.1226~1238 (2005)
  25. "PHYS" (2023)[URL]
  26. Pudjihartono, N., "A review of feature selection methods for machine learing-based disease risk prediction", Frontiers in Bioinformatics, 2, pp.17~ (2022)
  27. Shin, H. S., "Development of production-forecasting model based on the characteristics of production decline analysis using the reservoir and hydraulic fracture parameters in Montney Shale Gas reservoir", Canada, Geofluids, 2021, pp.12~ (2021)
  28. Syed, F. I., "Smart Shale gas production performance analysis using machine learning applications", Petroleum Research, 7(1), pp.21~31 (2022)
  29. Tan, L., "Methods of decline curve analysis for Shale Gas reservoirs", Energies, 11(3), pp.18~ (2018)
  30. "U.S. Energy Information Administration (EIA)" (2023)[URL]
  31. Wang, K., "Predicting production and estimated ultimate recoveries for Shale gas wells: A new methodology approach", Applied Energy, 206, pp.1416~1431 (2017)
  32. Won, J. H., "A survey on hyperparameter optimization in machine learning", Journal of Korean Institute of Communications and Information Sciences, 48(6), pp.15~ (2023)
  33. Yeom, J. Y., "Detection of borehole breakout depth in image logs using machine learning algorithms", Journal of The Korean Society of Mineral and Energy Resources Engineers, 60(4), pp.223~230 (2023)
  34. Zhai, S., "Prediction of gas production potential based on machine learning in Shale gas field: a case study", Energy Sources, Part A: Recovery, Utilization, and Environmental Effects, 44(3), pp.6581~6601 (2022)
  35. Zhang, H., "Extended exponential decline curve analysis", Journal of Natural Gas Science and Engineering, 36, pp.402~413 (2016)
  36. Zhang, Y., "A gradient boosting method to improve travel time prediction", Transportation Research Part C: Emerging Technologies, 58, pp.308~324 (2015)

관련 논문AI추천

머신러닝 기반 생산기간에 따른 셰일가스 궁극가채량 예측의 불확실성 추이 분석기세일, 박창협, 오현택, 장일식한국자원공학회 · 한국자원공학회지2021 · 제58권 제5호셰일가스 생산량 예측 시 생산관련인자를 활용한 장단기기억 신경망 적용 연구신효진, 이대모, 임종세한국자원공학회 · 한국자원공학회지2022 · 제59권 제6호셰일가스 생산량 예측 모델의 성능개선을 위한 장단기기억 신경망 기반 생산감퇴특성 추출 및 활용 연구신효진, 이대모, 임종세한국자원공학회 · 한국자원공학회지2023 · 제60권 제6호거리기반 후보군 선정과 인공신경망을 결합한 가스생산량 히스토리매칭강주명, 김재준, 민배현, 박창협, 안성인한국자원공학회 · 한국자원공학회지2017 · 제54권 제4호랜덤 포레스트 기반 분위수 회귀와 신뢰구간 보정을 통한 셰일저류층 궁극가채량 예측의 불확실성 정량화기세일, 심재헌, 장일식한국자원공학회 · 한국자원공학회지2025 · 제62권 제4호셰일 저류층 물성 및 수압파쇄 조건에 따른 생산감퇴곡선 인자 영향 분석강판상, 신효진, 임종세한국자원공학회 · 한국자원공학회지2017 · 제54권 제3호

이 간행물의 다른 논문 (7건)

채석, 파쇄, 출하 공정을 함께 고려한 석재 생산시스템 시뮬레이터 개발정다희, 최요순, 박세범pp. 89-99지하광산의 수갱운반용 권양시스템 설계 소프트웨어 개발이동길pp. 100-110이산화탄소 주입 시나리오에 따른 이산화탄소 지중저장의 트랩 메커니즘 분석임수경, 장일식pp. 124-135적색, 녹색, 청색광에서 생장한 Paenibacillus hunanensis 의 지구화학적 특성 연구박주영, 이지인, 임찬우, 황의정, 최예진, 이종운, 김희연pp. 136-142광해방지사업 분야 정보통신 기술의 실무 수요 및 증강현실 기술의 기초 타당성에 관한 연구김수로, 이진수, 박제현pp. 143-152
원문 보기