机器学习与超参数优化应用在碳酸盐油库中面积支持的透性建模中
Watheq J Al-Mudhafar1, Alqassim A Hasan2, Mohammed A Abbas3
1Basrah Oil Company, Basra, Iraq. watheq.almudhafar@utexas.edu.
Scientific reports
|April 15, 2025
概括
在碳酸盐储中准确地预测透性对于石油流动至关重要. 机器学习模型,特别是XGBoost,使用井日志有效预测透性,改进水库开发计划.
科学领域:
- 石油地质科学 石油地质科学
- 机器学习应用 机器学习应用
- 储水库工程 储水库工程
背景情况:
- 碳酸盐储具有异质的孔分布,其低矩阵透性阻碍了油流.
- 高透性断裂是关键管道,但透性测量 (核心,井测试) 很昂贵,许多井都无法使用.
- 准确的透性预测对于3D石质物质物质分布和高效的现场开发至关重要.
研究的目的:
- 评估六个机器学习算法的性能,用于使用传统井日志预测核心透性.
- 为了比较数据预处理技术和超参数调方法,以优化机器学习模型.
- 确定表现最好的机器学习算法和配置,用于在未孔井中进行透性预测.
主要方法:
- 使用了高质量的数据集,具有多个井日志输入 (马射线,多孔性,电阻性等). 和核心测量.
- 应用数据预处理:缺失数据的归算,尺度的校正,规范化 (日志,Box-Cox,NST) 和异常值的检测.
- 对比随机搜索和贝叶斯优化超参数调整;使用RMSE,MAE,R2和调整R2.2评估性能.
主要成果:
- 配置随机搜索,Box-Cox正常化,Z-score异常值检测的XGBoost算法,没有调整尺度,表现出卓越的性能.
- 实现了最低的预测误差:6.9 md (训练) 和9.78 md (测试) 根平均平方误差 (RMSE).
- 这种配置突显了特定预处理和调策略对于准确的透性预测的重要性.
结论:
- XGBoost是一个高效的机器学习算法,用于从井日志中预测碳酸盐水库的透性.
- 优化数据预处理和超参数调整对于提高预测准确性至关重要.
- 开发的模型提供了一个具有成本效益的解决方案,用于预测无井的透性,有助于水库管理.
相关概念视频
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving
29
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
29
Typical Model Studies
159
Fluid mechanics model studies often utilize scaled-down systems to predict fluid behavior in full-scale environments, such as river flows, dam spillways, and structures interacting with open surfaces. Maintaining Froude number similarity in river models is crucial, as it replicates surface flow features like wave patterns and velocities.
159
Modeling and Similitude
128
Scaled modeling is a fundamental technique in engineering, enabling the study of large and complex systems by creating smaller, manageable replicas that recreate critical characteristics of the original. In hydrology and civil infrastructure, for example, scaled models of dams help analyze water flow, turbulence, and pressure. This method allows for accurate predictions of real-world behavior within a controlled environment, significantly reducing the cost and time involved in full-scale...
128


