Predict Geomechanical Parameters with Machine Learning Combining Drilling Data and Gamma Ray

The aim of this work is the development of a fast and reliable method for geomechanical parameters evaluation while drilling using surface logging data. Geomechanical parameters are usually evaluated from cores or sonic logs, which are typically expensive and sometimes difficult to obtain. A novel approach is here proposed, where machine learning algorithms are used to calculate the Young's Modulus from drilling parameters and the gamma ray log. The proposed method combines typical mud logging drilling data (ROP, RPM, Torque, Flow measurements, WOB and SPP), XRF data and well log data (Sonic logs, Bulk Density, Gamma Ray) with several machine learning techniques. The models were trained and tested on data coming from three wells drilled in the same basin in Kuwait, in the same geological units but in different reservoirs. Sonic logs and bulk density are used to evaluate the geomechanical parameters (e.g. Young's Modulus) and to train the model. The training phase and the hyperparameter tuning were performed using data coming from a single well. The model was then tested against previously unseen data coming from the other two wells. The trained model is able to predict the Young's modulus in the test wells with a root mean squared error around 12 GPa. The example here provided demonstrates that a model trained with drilling parameters and gamma ray coming from one well is able to predict the Young Modulus of different wells in the same basin. These outcomes highlight the potentiality of this procedure and point out several implications for the reservoir characterization. Indeed, once the model has been trained, it is possible to predict the Young's Modulus in different wells of the same basin using only surface logging data.

Determination of the mud weight window, optimum drilling trajectory, and wellbore stability using geomechanical parameters in one of the Iranian hydrocarbon reservoirs

The challenges behind this research were encountered while drilling into the Ilam, Mauddud, Gurpi, and Mishrif Formations, where severe drilling instability-related issues were observed across the weaker formations above the reservoir intervals. In this paper, geomechanical parameters were carried out to determine optimum mud weight windows and safe drilling deviation trajectories using the geomechanical parameters. We propose a workflow to determine the equivalent mud window (EMW) that resulted in 11.18–12.61 ppg which is suitable for Gurpi formation and 9.36–13.13 ppg for Ilam and Mishrif Formations, respectively. To estimate safe drilling trajectories, the Poisson’s ratio, Young’s modulus, and unconfined compressive strength (UCS) parameters were determined. These parameters illustrate an optimum drilling trajectory angle of 45° (Azimuth 277°) for the Ilam to Mauddud Formations and less than 35° for the Gurpi Formation. Our analysis reveals that maximum horizontal stress and Poisson’s ratio have the most impact on determining the optimum drilling mud weight windows and safe drilling deviation trajectories. On the contrary, vertical stress and Young’s modulus have minimum impact on drilling mud weight windows and safe drilling deviation trajectories. This study can be used as a reference for the optimal mud weight window to overcome drilling instability issues in future wellbore planning in the study.

Stress field analysis and its effect on selection of optimal well trajectory in directional drilling (case study: southwest of Iran)

Given the complexities of reservoir exploration and development, it is vital to understand the geomechanical properties of the reservoir and well in the drilling operation. In constructing a mechanical model of the earth, a combination of environmental geomechanical parameters, as well as the magnitude and direction of stresses, is used. In this study, stress analysis and its effect on azimuth well in deviated drilling in an oil field located in southwestern Iran are investigated. Necessary geomechanical parameters are estimated using density and slowness logs of sonic waves (shear and compression). The Mohr–Coulomb failure criterion is followed to determine a safe mud weight window. A mechanical model of the earth is designed using laboratory data and well logging, and it is validated by the results obtained from laboratory rock mechanics using the calibrated core samples. The results show that drilling in the azimuth at about 135° with an angle of about 15° is the most stable path for the well in the carbonate reservoir formation in the studied oil field.

Time-dependent reliability analysis of unsaturated slopes under rapid drawdown with intelligent surrogate models

Slope stability in reservoirs depends on time-dependent triggering factors such as fluctuations of the groundwater level and precipitation. This paper assesses the stability of reservoir slopes over time, accounting for the uncertainty of the shear strength and hydraulic parameters. An intelligent surrogate model has been developed to reduce the computational effort. The capability of two machine learning algorithms, namely Support Vector Regression and Extreme Gradient Boosting, is considered to obtain the relationship between geomechanical parameters and the factor of safety. The probability of failure of a hypothetical reservoir slope is estimated employing Monte Carlo simulations for different scenarios of drawdown velocity. A sensitivity analysis is conducted to investigate the influence of the geomechanical parameters, regarded as random variables, on the probability of failure. The results revealed that the coefficient of variation in the effective friction angle and the correlation between effective cohesion and friction angle have the highest impact on the probability of failure. The intelligent surrogate model can predict the factor of safety of reservoir slopes under rapid drawdown with high accuracy and enhanced computational efficiency.

A case study on establishing the state of decomposition of municipal solid waste in a bioreactor landfill in India

Estimation of temporal changes undergone by municipal solid waste (MSW) in its physico–chemico–geomechanical properties in a bioreactor landfill (BLF) is essential for: (i) efficient landfilling, (ii) establishing the state of decomposition of MSW with time and (iii) deciding upon the appropriate time to initiate landfill mining. To achieve this, a series of destructive (DTs) and non-destructive tests (NDTs) can be conducted on the MSW samples in the BLF. With this in view, several DTs were conducted on these samples retrieved from different depths of the two cells of a fully operational BLF in Mumbai, India. Subsequently, the physical and chemical properties of these samples such as composition, moisture content, volatile solids (VS), elemental content, lignocellulosic content (i.e. cellulose, hemicellulose and lignin content) and bio-methanation potential, were determined by following the laboratory testing, as a function of time. Also, NDTs such as cone penetration test and multichannel analysis of surface waves were conducted on these cells of BLF to obtain geomechanical parameters (viz. cone resistance, sleeve resistance, friction ratio and shear wave velocity) of the MSW. Based on the data obtained from these tests, and reported in the literature, it has been observed that the VS, elemental content, lignocellulosic content and bio-methanation potential of MSW exhibits very well-defined trends, as compared to the geomechanical parameters, with time. Furthermore, it has been observed that the VS, hydrogen-, carbon- and nitrogen-content reduce significantly (≈62%, 70%, 50% and 30%, respectively), following an exponential decay, until the critical time ( tcr) (≈4 years) has been achieved. As, beyond tcr these parameters remain practically unchanged, which corresponds to the ‘stabilized MSW’, mining of the BLF can be initiated without further delay.

Geomechanical characterization of a heterogenous rock mass using geological and laboratory test results: a case study of the Niobec Mine, Quebec (Canada)

To conduct a successful geomechanical characterization of rock masses, an appropriate interpretation of lithological heterogeneity should be attained by considering both the geological and geomechanical data. In order to clarify the reliability and applicability of geological surveys for rock mechanics purposes, a geomechanical characterization study is conducted on the heterogeneous rock mass of Niobec Mine (Quebec, Canada), by considering the characteristics of its various identified lithological units. The results of previous field and laboratory test campaigns were used to quantify the variability associated to intact rock geomechanical parameters for the different present lithological units. The interpretation of geomechanical similarities between the lithological units resulted in determination of three main rock units (carbonatite, syenite, and carbonatite-syenite units). Geomechanical parameters of these rock units and their associated variabilities are utilized for stochastic estimation of geomechanical parameters of the heterogeneous rock mass using the Monte Carlo Simulation method. A comparison is also made between the results of probabilistic and deterministic analyses to highlight the presence of intrinsic variability associated with the heterogeneous rock mass properties. The results indicated that, for the case of Niobec Mine, the carbonatite-syenite rock unit could be considered as a valid representative of the entire rock mass geology since it offers an appropriate geomechanical approximation of all the present lithological units at the mine site, in terms of both the magnitude and dispersion of the strength and deformability parameters. Article Highlights Evaluating the reliability and applicability of geological survey outcomes for rock mechanics purposes. A geomechanical characterization study is conducted on the heterogeneous rock mass by considering the various identified rock lithotypes. The geomechanical parameters of intact units and their associated variabilities are used to stochastically estimate the geomechanical parameters of the heterogeneous rock mass by employing the Monte Carlo Simulation. A comparison is also made between the results of probabilistic and deterministic geomechanical analyses. The results indicate that, in the case of Niobec Mine, the combined syenite-carbonatite rock unit could be considered as a valid representative of the entire rock mass.