Saudi Arabian Oil Company

Yunsheng Li

Weihua Wang

Maan A Hawi

Roger R Sung

Ibrahim A Makrami

Chuanyu Stephen Sun

Systems and methods for generating synthetic borehole image logs include logging rate of penetration (ROP) data, resistivity data, and gamma ray data while drilling a borehole in a subsurface formation to generate logged data. The generating includes determining an effective dip angle of the subsurface formation along the borehole and generating a depth shift table based on the effective dip angle and a well deviation angle, the well deviation angle being between the borehole and a vertical reference. Datasets are generated based on the ROP data, resistivity data, and gamma ray data, the generated datasets having higher sampling rates than the logged data. Synthetic borehole images are generated based on the generated datasets and the depth shift table, and the synthetic borehole images are oriented with respect to a reference point of the borehole.

Generating synthetic borehole image logs

Systems and methods include a computer-implemented method for creating artificial real-time gamma ray (GR) images for well placement. Real-time azimuthal density data is determined from drilling of a well. An azimuthal density data set is generated using the real-time azimuthal density data. The azimuthal density data set is generated with a greater sampling rate than a real-time sampling rate of the real-time azimuthal density data. An azimuthal density curve depth match is performed using the azimuthal density data set. Performing the azimuthal density curve depth match includes creating a depth shift match table. A high-resolution sector near-bit gamma ray (GR) image is generated using the azimuthal density curve depth match and the depth shift match table. The high-resolution sector near-bit GR image is oriented to a top of a wellbore for the well.

Creation of near bit gamma ray image from a gamma ray curve

A computer-implemented method that enables lithofacies guided core description using unsupervised machine learning is described herein. The method includes obtaining well log curves for a wells in a zone. The method also includes predicting lithofacies for the wells using a machine learning model. The machine learning model is trained with input data comprising additional well log curves and well cores. The method includes grouping the wells based on the predicted lithofacies, and updating core descriptions of the wells based on the grouped wells.

Lithofacies guided core description using unsupervised machine learning

Systems and methods include a computer-implemented method: Total clay, effective porosity (PHIE) values, and gas volume are determined for a tight gas sandstone reservoir characterization using petrophysical evaluation results. Regions of the tight gas sandstone reservoir are characterized, including performing diagenetic rock typing for the regions using the total clay and PHIE values, where the diagenetic rock typing reflects porosity/permeability and clay content change. Sweet spots are determined based on the diagenetic rock typing and gas volume variation. Ranked sweet spots are determined by indexing and ranking the sweet spots by category. Optimized infill drilling locations and target zones are determined, and well placements in the tight gas sandstone reservoir are assisted using the diagenetic rock typing and the ranked sweet spots.

Log based diagenetic rock typing and sweet spot identification for tight gas sandstone reservoirs

A horizontal or deviated core sample is received from a wellbore. A presence of geologic indicators within the horizontal or deviated core sample is determined. The horizontal or deviated core sample is rotated to a position based on the presence and orientation of the geologic indicators. A top of the horizontal or deviated core sample is marked after the core has been rotated.

Orienting geologic core samples

The present disclosure describes methods and systems, including computer-implemented methods, computer-program products, and computer systems, for providing 360-degree well core sample photo image integration, calibration, and interpretation for modeling of reservoir formations and lithofacies distribution. One computer-implemented method includes receiving a 360-degree well core sample photo image, geospatially anchoring, by a computer, the received 360-degree well core sample photo image, decomposing, by a computer, the geospatially-anchored 360-degree well core sample photo image into a color numerical array, transforming, by a computer, the color numerical array into a formation image log, calibrating, by a computer, the formation image log for consistency with additionally available data, and generating, by a computer, 3D lithofacies interpretation and prediction data using the formation image log.

Growing community of inventors

Dhahran, Saudi Arabia

Yunsheng Li