Aug 2026· SPE/IADC Asia Pacific Drilling Technology Conference and Exhibition· 0 citations· 73 references
TL;DR
A model is identified that not only reproduces historical data accurately but also yields correct responses under a diverse range of varying input parameters, and the proposed methodology establishes a reproducible basis for developing more reliable ROP forecasting tools for complex well trajectories.
Abstract
Reliable forecasting of drilling rate of penetration (ROP) remains a technical challenge due to its complex dependence on several operational, geological, and directional conditions that are highly nonlinear and well-specific. These difficulties are amplified in deviated wells, where traditional empirical relations often fail to capture the combined effects of lithological variability and directional changes. This study develops a machine learning (ML) model for ROP prediction using multi-well field data and evaluates candidate ML algorithms/models not only on numerical accuracy but also on their ability to reproduce reasonable trend responses to changes in key drilling parameters. The objective is to establish a validation approach that integrates statistical performance, cross-well generalization, and sensitivity behavior consistent with drilling mechanics.
Field data from 18 wells were used to develop the model, while two additional wells were reserved for independent validation. A total of 91,140 drilling datasets, comprising 24 parameters/features, were collected. After preprocessing and selective outlier screening, 85,695 records were retained for model training and testing. Feature selection resulted in nine highly influential parameters: True Vertical Depth (TVD), Weight on Bit (WOB), rotational speed (Rotation), mud flow rates (FLOW), mud density, shale content (Shale), Sandstone content (Sandstone), inclination (Inc), and dogleg severity (DLS). Eleven supervised ML algorithms were evaluated, representing instance-based, tree-based, boosting-based, neural-network, and stacking-ensemble model families. Model performance was assessed using feature-importance ratings and statistical metrics, including train/test R2, MSE, RMSE, and MAE, which were used to select the best-performing model. Finally, sensitivity analysis was conducted to evaluate the selected model's ability to reproduce physically meaningful ROP responses.
Model comparison across the training and testing splits demonstrated strong overall predictive performance, with training R2 values ranging from 0.91 to 0.99 and testing R2 values ranging from 0.88 to 0.94. Among the evaluated models, the Gradient Boosting (GB) model provided the best overall performance, with training R2 = 0.9940, testing R2 = 0.9399, RMSE = 36.88, and MAE = 21.52. The GB model also showed strong agreement with the averaged feature-importance ranking and reproduced physically meaningful ROP sensitivity trends for the dominantly influential drilling parameters. SHAP and feature-importance analyses confirmed that TVD, FLOW, WOB, shale content, and rotation were the most influential variables controlling ROP. External validation on two unseen wells further demonstrated strong generalization, with R2 = 0.9694 for Well-19 and R2 = 0.96 for Well-20.
This study presents a physically informed framework for evaluating and selecting data-driven ML models for deviated wells. The approach combines conventional accuracy metrics with feature-importance consistency, reasonable trend prediction in sensitivity analysis, and strong agreement between model predictions and unseen-well data. Through this integrated evaluation, a model is identified that not only reproduces historical data accurately but also yields correct responses under a diverse range of varying input parameters. The proposed methodology establishes a reproducible basis for developing more reliable ROP forecasting tools for complex well trajectories.
Accurate prediction of the rate of Penetration (ROP) is critical for optimizing drilling efficiency and reducing well construction costs in unconventional resource development. A significant gap exists in the overwhelming majority of machine learning (ML) ROP models, which have been trained exclusively on vertical well data. This systematically neglects the physical influence of wellbore geometry in deviated and horizontal wells that dominate modern unconventional drilling. However, this study addresses this gap by developing and rigorously comparing three ML algorithms: Artificial Neural Network (ANN), Gradient Boosting Machine (GBM), and Random Forest (RF), for real-time ROP prediction in a non-vertical unconventional shale well. A preprocessed dataset of 22,486 data points from the daily drilling records from a United States (U.S.) shale well was used. Eleven input features spanning four categories were employed: wellbore trajectory, depth-related, mechanical/operational parameters, and hydraulic parameters. Models were trained on a 70:15:15 train-validation-test split and evaluated using the coefficient of determination (R2), root mean square error (RMSE), and mean absolute error (MAE). All three models achieved strong predictive accuracy: ANN (R2 = 0.8780, RMSE = 0.06924), GBM (R2 = 0.9134, RMSE = 0.05833), and RF (R2 = 0.9961, RMSE = 0.01237). The RF model was superior and selected for feature importance analysis. An explicit ANN Equation was derived from extracted weights and biases, enabling model transparency and software-independent computation of ROP. Feature importance analysis on a categorical basis showed that mechanical/operational parameters were the most influential predictors, followed by depth-related, then trajectory parameters. A systematic literature review showed that in vertical conventional wells, WOB and bit speed consistently dominate as the primary ROP drivers. However, in the directional unconventional context of this study, azimuth ranked fifth and inclination seventh, together contributing 14.5%, which exceeds all hydraulic parameters. This result underscores the previously neglected role of wellbore geometry in ROP prediction for deviated wells. However, the findings in this study are limited to a single-well dataset from one U.S. shale formation, an inclination range of 0.18°–55.92° without a full horizontal lateral, and the absence of formation evaluation logs.
A. Iorkyaa, E. E. Udoh, K. S. Onwuguzo et al.· SPE Nigeria Annual Internati...· 0 citations
Against the backdrop of continuously growing global energy demand, the rate of penetration (ROP) serves as a key indicator for measuring drilling efficiency. Accurate ROP prediction is significant for optimizing drilling parameters and reducing project costs. In recent years, machine learning (ML) has been widely applied in ROP prediction research due to its advantages in handling high-dimensional data and nonlinear modeling. This paper systematically reviews and comparatively analyses the research progress of machine learning in ROP prediction. Existing studies are classified into three categories: purely data-driven models, hybrid models integrating physical mechanisms, and intelligent optimisation and decision-support methods. Cross-study comparisons reveal that pure data-driven models generally achieve high prediction accuracy when sufficient data is available. However, multiple studies note their limitations in generalization capability and physical consistency under complex geological conditions. Hybrid models integrating physical mechanisms demonstrate better robustness and interpretability, but their higher computational complexity constrains potential for real-time applications. Intelligent optimization and decision support methods show promise in multi-objective collaborative optimization, though challenges in stability and real-time performance remain. Based on this review, four main research directions are summarized: deep integration of physical constraints and intelligent optimization algorithms, development of decision support systems for real-time drilling, advancement of interdisciplinary hybrid modeling methods, and application of efficient computing and edge intelligence technologies. These directions stem from recurring technical bottlenecks and research trends in recent literature, providing guidance for future research and engineering practice.
Yulin Ma, T. Cao, Zhou Du· Journal of Petroleum Explora...· 0 citations
Understanding permeability is essential for evaluating reservoir quality and field development planning. Reliable permeability estimation can reduce the uncertainty in reservoir characterization, particularly in intervals where core data are limited. As the industry relies on log-based interpretations and empirical correlations, the limitations of these approaches become apparent. Data-driven approaches offer a promising alternative to conventional empirical methods. The data set in this study comprises 252 samples with seven features derived from conventional well logs. Data preprocessing includes handling missing values, smoothing logs, feature engineering to add an extra input, and transformation with the Yeo-Johnson technique. A center moving average filter was used to reduce variance and improve data consistency. Ensemble machine-learning (ML) and baseline models were developed and evaluated using a 75-25 train-test split, four-fold cross validation, and model complexity assessment. Ensemble methods outperformed baseline models, with extremely randomized trees (ET) and random forest (RF) emerging as the most stable, achieving a mean R² of 0.93 and 0.89 and a low R² standard deviation (0.3). Multilinear regression (MLR) and artificial neural networks (ANNs) show limited accuracy, while gradient boosting (GB) and extreme gradient boosting (XGBoost) methods exhibit overfitting despite perfect training scores. Predicted kh values were compared with core data. Both linear and nonlinear empirical equations were derived using MLR, polynomial regression, and a power-law model. The power-law model (empirical equation) achieved an R² value of 0.79 and can therefore be used to estimate permeability. Additionally, a Gaussian mixture model (GMM) was used for unsupervised classification of hydraulic flow units (HFU) using the flow zone indicator (FZI), computed from the continuous permeability curve obtained from the best ML model. Thus, ML-based permeability prediction is an indispensable component of HFU modeling. The model identified three distinct flow zones, enabling HFU clustering and defining their corresponding petrophysical properties and depositional environments.
Vikram Kumar, Sayantan Ghosh, S. Maiti· Petrophysics· 0 citations
Improving drilling efficiency remains a central objective in petroleum operations due to its direct impact on time and cost. This study develops a predictive framework for estimating the Rate of Penetration (ROP) using supervised machine learning techniques combined with systematic data conditioning. The analysis is based on more than 11,000 measurements obtained from four horizontal wells. A rigorous preprocessing strategy was implemented to enhance data reliability, including removal of invalid entries and statistical outliers using the interquartile range method. This procedure reduced the dataset to 7,297 high-quality observations. In addition, target stabilization was introduced through Exponential Moving Average smoothing (spans of 5 and 10), which reduced short-term fluctuations and improved the learnability of the ROP signal. Three tree-based regression models—Decision Tree, Random Forest, and Gradient Boosting—were evaluated under both default configurations and optimized settings. Results show that model performance is strongly influenced by data conditioning. The Random Forest model achieved the highest accuracy, with a coefficient of determination (R2) of 0.96 and a mean squared error (MSE) of 26 when trained on the EMA-10 dataset. Gradient Boosting exhibited the largest improvement from hyperparameter tuning, with R2 increasing from 0.86 to 0.95. To bridge the gap between model development and practical use, the trained models were implemented in interactive applications for real-time prediction and parameter optimization. The outcomes demonstrate that careful preprocessing and noise-aware modeling significantly enhance predictive capability.
B. Elahifar, Thomas Philip Fagerli· Journal of Energy Resources...· 0 citations
Optimizing drilling efficiency requires understanding not only which parameters influence the rate of penetration (ROP), but also the relative contribution of different drilling measurement domains to predictive capability. Most machine-learning studies emphasize prediction accuracy while providing limited insight into the engineering value of operational, hydraulic, formation, and drill string dynamic measurements. This study presents a hierarchical explainable machine-learning framework to quantify the incremental contribution of these measurement domains using real-time drilling data from the 15/9-F-5 well in the Norwegian Continental Shelf. Following quality control, a dataset comprising 606 complete observations and 24 predictor variables was analyzed. Random Forest (RF), extreme gradient boosting (XGBoost), and CatBoost were evaluated using a depth-blocked GroupKFold cross-validation strategy with hyperparameter optimization, after which the best-performing model was employed for hierarchical feature-domain analysis. Within the baseline hierarchy, the addition of hydraulic measurements produced a 29.87% increase in validation R2. Alternative formation-first and hydraulic-first hierarchies, together with pairwise feature-domain analyses, confirmed that incremental contributions depended on the sequence of feature integration. The robustness of these findings was independently verified using RF feature importance, permutation importance, SHapley Additive exPlanations (SHAP) analysis, and aggregated domain-level SHAP attribution. Aggregated SHAP analysis revealed that formation variables accounted for 48.1% of the aggregated feature attribution, whereas controllable operational and hydraulic parameters collectively accounted for 45.0%. This demonstrates that although formation-related variables exhibited the strongest predictive association, nearly half of the predictive information originates from drilling parameters that may support real-time operational decision-making. Overall, this work advances explainable machine learning in drilling engineering by providing a transparent framework for quantifying both the incremental predictive contribution and the overall feature attribution of drilling measurement domains.
Muhammad Hammad Rasool· Engineering Research Express· 0 citations
With the continuous development of drilling technology, accurately predicting mechanical penetration rates is particularly important for improving operational efficiency and reducing costs. Existing methods often struggle to provide reliable predictions when faced with complex geological conditions and variable drilling environments because they primarily rely on traditional models and fail to adequately consider various influencing factors and their nonlinear relationships. To ad-dress these issues, this paper proposes a mechanical penetration rate prediction model based on committee machines. This model effectively captures the variability characteristics of mechanical penetration rates by integrating multiple expert models while employing wavelet filtering methods to denoise the data to enhance data quality. In the application case, this paper collects relevant drilling parameter data based on a vertical well in a specific block. The evaluation of the model shows that it performs excellently in key indicators such as mean square error, coefficient of determination, root mean square error, and mean absolute error, particularly demonstrating a high predictive capability and stability by explaining 97.19% of data variability. The advantage of the constructed model lies in its strong ensemble learning ability, which not only enhances the prediction accuracy of mechanical penetration rates but also helps to deepen the understanding of the dynamic changes in the drilling process, providing effective support for subsequent drilling optimization and resource development.
Tao Cai, Huai-Yan Qi, Xue-Wu Yang et al.· Journal of Physics, Conferen...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
