Prediction of fracture density in a gas reservoir using robust computational approaches

This study presents a pioneering machine learning approach to continuously model fracture intensity in hydrocarbon reservoirs using solely conventional well logs and mud loss data. While machine learning has previously been applied to predict discrete fracture properties, this is among the first attempts to leverage well logs for continuous fracture intensity modeling leveraging advanced ensemble techniques. A multi-level stacked ensemble methodology systematically combines the strengths of diverse algorithms like gradient boosting, random forest and XGBoost through a tiered approach, enhancing predictive performance beyond individual models. Nine base machine learning algorithms generate initial fracture intensity predictions which are combined through linear regression meta-models and further stacked using ridge regression into an integrated super-learner model. This approach achieves significant improvements over individual base models, with the super-learner attaining a mean absolute error of 0.083 and R^2 of 0.980 on test data. By quantifying the crucial fracture intensity parameter continuously as a function of depth, this data-driven methodology enables more accurate reservoir characterization compared to traditional methods. The ability to forecast fracture intensity solely from conventional well logs opens new opportunities for rapid, low-cost quantification of this parameter along new wells without requiring advanced logging tools. When incorporated into reservoir simulators, these machine learning fracture intensity models can help optimize production strategies and recovery management. This systematic stacked ensemble framework advances continuous fracture intensity modeling exclusively from well logs, overcoming limitations of prior techniques. Novel insights gained via rigorous model evaluation deepen the understanding of naturally fractured reservoirs.

Section: Introductionmentioning

confidence: 99%

Robust fracture intensity estimation from petrophysical logs and mud loss data: a multi-level ensemble modeling approach

Azadivash,

Soleymani,

Seifirad

et al. 2024

Reservoir rock typing for optimum permeability prediction of Nubia formation in October Field, Gulf of Suez, Egypt

Kassab,

Abbas,

Osman

et al. 2024

Permeability prediction and distribution is very critical for reservoir modeling process. The conventional method for obtaining permeability data is from cores, which is a very costly method. Therefore, it is usual to pay attention to logs for calculating permeability where it has massive limitations regarding this step. The aim of this study is to use unique artificial intelligence (AI) algorithms to tackle this challenge and predict permeability in the studied wells using conventional logs and routine core analysis results of the core plugs as an input to predict the permeability in non-cored intervals using extreme gradient boosting algorithm (XGB). This led to promising results as per the R2 correlation coefficient. The R2 correlation coefficient between the predicted and actual permeability was 0.73 when using the porosity measured from core plugs and 0.51 when using the porosity calculated from logs. This study presents the use of machine-learning extreme gradient boosting algorithm in permeability prediction. To our knowledge, this algorithm has not been used in this formation and field before. In addition, the machine-learning model established is uniquely simple and convenient as only four commonly available logs are required as inputs, it even provides reliable results even if one of the required logs for input is synthesized due to its unavailability.

Multiple linear regression and gene expression programming to predict fracture density from conventional well logs of basement metamorphic rocks

Hasan,

M. Tóth

2024

Fracture identification and evaluation requires data from various resources, such as image logs, core samples, seismic data, and conventional well logs for a meaningful interpretation. However, several wells have some missing data; for instance, expensive cost run for image logs, cost concern for core samples, and occasionally unsuccessful core retrieving process. Thus, a majority of the current research is focused on predicting fracture based on conventional well log data. Interpreting fractures information is very important especially to develop reservoir model and to plan for drilling and field development. This study employed statistical methods such as multiple linear regression (MLR), principal component analysis (PCA), and gene expression programming (GEP) to predict fracture density from conventional well log data. This study explored three wells from a basement metamorphic rock with ten conventional logs of gamma rays, thorium, potassium, uranium, deep resistivity, flushed zone resistivity, bulk density, neutron porosity, sonic porosity, and photoelectric effect. Four different methods were used to predict the fracture density, and the results show that predicting fracture density is possible using MLR, PCA, and GEP. However, GEP predicted the best fracture density with R2 > 0.86 for all investigated wells, although it had limited use in predicting fracture density. All methods used highlighted that flushed zone resistivity and uranium content are the two most significant well log parameters to predict fracture density. GEP was efficient for use in metamorphic rocks as it works well for conventional well log data as the data is nonlinear, and GEP uses nonlinear algorithms.