Centimeter-Scale Lithology and Facies Prediction in Cored Wells Using Machine Learning
نویسندگان
چکیده
Machine-learning algorithms have been used by geoscientists to infer geologic and physical properties from hydrocarbon exploration development wells for more than 40 years. These techniques historically utilize digital well-log information, which, like any remotely sensed measurement, resolution limitations. Core is the only subsurface data that true scale heterogeneity. However, core description analysis are time-intensive, therefore most not utilized their full potential. Quadrant 204 on United Kingdom Continental Shelf has publicly available open-source well log data. This study utilizes this dataset machine-learning models predict lithology facies at centimeter scale. We selected 12 Q204 region with Schiehallion, Foinaven, Loyal, Alligin fields. interpreted training 659 m of sub-centimeter scale, utilizing a lithology-based labeling scheme (five classes) depositional-process-based (six classes). Utilizing “color-channel-log” (CCL) summarizes image each depth interval, our best performing trained model predicts correct 69% accuracy (i.e., predicted output same as lithology) individual classes sandstone mudstone over 80% accuracy. The CCL require less compute power generate accurate results. While process-based labels better characterize turbidites hybrid-event-bed stratigraphy, based predictions were compared lithology. In all cases, standard cannot accurately or level. workflow developed can unlock warehouses high-resolution in multitude geological settings. be applied other geographic areas deposit types where large quantities photographed material available. research establishes an open-source, python-based analyze scalable, reproducible way. anticipate will serve baseline future borehole
منابع مشابه
Stock Price Prediction using Machine Learning and Swarm Intelligence
Background and Objectives: Stock price prediction has become one of the interesting and also challenging topics for researchers in the past few years. Due to the non-linear nature of the time-series data of the stock prices, mathematical modeling approaches usually fail to yield acceptable results. Therefore, machine learning methods can be a promising solution to this problem. Methods: In this...
متن کاملsimulation and experimental studies for prediction mineral scale formation in oil field during mixing of injection and formation water
abstract: mineral scaling in oil and gas production equipment is one of the most important problem that occurs while water injection and it has been recognized to be a major operational problem. the incompatibility between injected and formation waters may result in inorganic scale precipitation in the equipment and reservoir and then reduction of oil production rate and water injection rate. ...
Hypertension Prediction in Primary School Students Using an Ensemble Machine Learning Method
Introduction: The prevalence of hypertension in children is increasing, and this complication is considered the most important risk factor for cardiovascular diseases in older age. Early detection and control of hypertension can prevent its progress and reduce its consequences. Machine learning methods can help predict this complication promptly and reduce cost and time. This study aimed to pro...
متن کاملThermal conductivity of Water-based nanofluids: Prediction and comparison of models using machine learning
Statistical methods, and especially machine learning, have been increasingly used in nanofluid modeling. This paper presents some of the interesting and applicable methods for thermal conductivity prediction and compares them with each other according to results and errors that are defined. The thermal conductivity of nanofluids increases with the volume fraction and temperature. Machine learni...
متن کاملThermal conductivity of Water-based nanofluids: Prediction and comparison of models using machine learning
Statistical methods, and especially machine learning, have been increasingly used in nanofluid modeling. This paper presents some of the interesting and applicable methods for thermal conductivity prediction and compares them with each other according to results and errors that are defined. The thermal conductivity of nanofluids increases with the volume fraction and temperature. Machine learni...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Frontiers in Earth Science
سال: 2021
ISSN: ['2296-6463']
DOI: https://doi.org/10.3389/feart.2021.659611