Hybrid Physics-Constrained and Data-Driven Approach for Interwell Saturation Estimation from Well Logs

Abstract Combining physics-based models for well log analysis with artificial intelligence (AI) advanced algorithms is crucial for wellbore studies. Data-driven methods do not generalize well and lack theoretical knowledge accumulated in the field. Estimating well saturation significantly improves if predictions from physical models are used to constrain data-driven algorithms in outlined primary fluid channels and other important points of interest. Saturation propagations in the reservoirs interwell region also generalize better under using combination of models. This work addresses combined usage of theoretical and data-driven models by aggregating them into single hybrid model. Multiple physical and data-driven models are under study, their parameters are optimized using observations. Weighted sum is used to predict water saturation at every point with weights being recomputed at each step. Model outputs are compared in terms accuracy and cumulative loss. A synthesized reservoir box model encompassing volumetric interwell porosity, resistivity and saturation data is used for the validation of the algorithms. Aggregated model for estimating interwell saturation shows improved prediction accuracy compared both to physics-based or data-driven approaches separately.

Download Full-text

Using Integration of Thermal-Balance Based and Data-Driven Models to Determine Single Duct Variable Air Volume System Cooling Baseline

ASME 2013 7th International Conference on Energy Sustainability ◽

10.1115/es2013-18402 ◽

2013 ◽

Author(s):

Gyujin Shim ◽

Li Song ◽

Gang Wang

Keyword(s):

Physical Model ◽

Least Square Method ◽

Energy Performance ◽

Least Square ◽

Physical Models ◽

Data Driven ◽

Lumped Model ◽

Variable Air Volume ◽

Data Driven Approach ◽

Cooling Coil

In order to use real-time energy measurements to identify system operation faults and inefficiencies, a cooling coil energy baseline is studied in an air-handling unit (AHU) through an integration of physical models and a data driven approach in this paper. A physical model for an AHU cooling coil energy consumption is first built to understand equipment mechanism and to determine the variables impacting cooling coil energy performance, and then the physical model is simplified into a lumped model by reducing the number of independent variables needed. Regression coefficients in the lumped model are determined statistically through searching optimal fit using the least square method with short periods of measured data. Experimental results on an operational AHU (8 ton) are presented to validate the effectiveness of this approach with statistical analysis. As a result of this experiment, the proposed cooling energy baselines at the cooling coil have ±20% errors at 99.7% confidence. Six-day data for obtaining baseline is preferred since it shows similar results as 12-day.

Download Full-text

Reservoir quality evaluation of the Farewell sandstone by integrating sedimentological and well log analysis in the Kupe South Field, Taranaki Basin-New Zealand

Journal of Petroleum Exploration and Production Technology ◽

10.1007/s13202-020-01035-8 ◽

2020 ◽

Cited By ~ 1

Author(s):

S. M. Talha Qadri ◽

Md Aminul Islam ◽

Mohamed Ragab Shalaby ◽

Ahmed K. Abd El-Aal

Keyword(s):

Water Saturation ◽

Total Porosity ◽

Effective Porosity ◽

Log Analysis ◽

Reservoir Quality ◽

Well Log ◽

Shale Volume ◽

Diagenetic Processes ◽

Hydrocarbon Saturation ◽

Well Log Analysis

AbstractThe study used the sedimentological and well log-based petrophysical analysis to evaluate the Farewell sandstone, the reservoir formation within the Kupe South Field. The sedimentological analysis was based on the data sets from Kupe South-1 to 5 wells, comprising the grain size, permeability, porosity, the total cement concentrations, and imprints of diagenetic processes on the reservoir formation. Moreover, well log analysis was carried on the four wells namely Kupe South 1, 2, 5 and 7 wells for evaluating the parameters e.g., shale volume, total and effective porosity, water wetness and hydrocarbon saturation, which influence the reservoir quality. The results from the sedimentological analysis demonstrated that the Farewell sandstone is compositionally varying from feldspathic arenite to lithic arenite. The analysis also showed the presence of significant total porosity and permeability fluctuating between 10.2 and 26.2% and 0.43–1376 mD, respectively. The diagenetic processes revealed the presence of authigenic clay and carbonate obstructing the pore spaces along with the occurrence of well-connected secondary and hybrid pores which eventually improved the reservoir quality of the Farewell sandstone. The well log analysis showed the presence of low shale volume between 10.9 and 29%, very good total and effective porosity values ranging from 19 to 32.3% as well as from 17 to 27%, respectively. The water saturation ranged from 22.3 to 44.9% and a significant hydrocarbon saturation fluctuating from 55.1 to 77.7% was also observed. The well log analysis also indicated the existence of nine hydrocarbon-bearing zones. The integrated findings from sedimentological and well log analyses verified the Farewell sandstone as a good reservoir formation.

Download Full-text

Petrophysical Properties of Khasib Formation in East Baghdad Oil Field Southern Area

Iraqi Journal of Chemical and Petroleum Engineering ◽

10.31699/ijcpe.2020.4.5 ◽

2020 ◽

Vol 21 (4) ◽

pp. 41-48

Author(s):

Layth Abdulmalik Jameel ◽

Fadhil S. Kadhim ◽

Hussein Al-Sudani

Keyword(s):

Water Saturation ◽

High Water ◽

Oil Field ◽

Neutron Density ◽

Well Log ◽

Petrophysical Properties ◽

Shale Volume ◽

Southern Area ◽

Volume Porosity ◽

Well Log Analysis

Petrophysical properties evaluation from well log analysis has always been crucial for the identification and assessment of hydrocarbon bearing zones. East Baghdad field is located 10 km east of Baghdad city, where the southern area includes the two southern portions of the field, Khasib formation is the main reservoir of East Baghdad oil field. In this paper, well log data of nine wells have been environmentally corrected, where the corrected data used to determine lithology, shale volume, porosity, and water saturation. Lithology identified by two methods; neutron-density and M-N matrix plots, while the shale volume estimated by single shale indicator and dual shale indicator, The porosity is calculated from the three common porosity logs; density log, neutron log, and sonic log, the water saturation is calculated by Indonesian model and Archie equation, and the results of the two methods were compared with the available core data to check the validity of the calculation. The results show that the main lithology in the reservoir is limestone, shale volume ranged between 0.152 to 0.249, porosity between 0.147 to 0.220, and water saturation from 0.627 to 0.966, the high-water saturation indicate that the water quantity is the determining factor of the reservoir units.

Download Full-text

Application of Acoustic Impedance and Reflectivity in Reservoir Characterization

10.2118/207077-ms ◽

2021 ◽

Author(s):

Stanley Oifoghe ◽

Ikenna Obodozie ◽

Lucrecia Grigoletto

Keyword(s):

Acoustic Impedance ◽

Oil And Gas ◽

Reservoir Characterization ◽

Water Saturation ◽

Oil And Gas Industry ◽

Well Log ◽

Volume Calculation ◽

Geomechanical Properties ◽

Volume Porosity ◽

Well Log Analysis

Abstract Well log analysis is one of the methods for reservoir characterization, in the oil and gas industry. Logs are used for subsurface formation evaluation. They are useful in hydrocarbon zone identification and volume calculation. Interpretation of well log involves sequential steps, which are lithology, shale volume, porosity and saturation determination. It is unwise to analyze well log without following the logical steps, as this could introduce errors in the result. Petrophysical and Geomechanical properties are two classes of properties for reservoir characterization. The computed volume of shale in the reservoir was 10%, the average water saturation was 30%, and the average porosity was 25pu. The bulk density decreased from 2.15g/cc to 1.95g/cc and there is a considerably lower acoustic impedance in the hydrocarbon bearing sands. In challenging reservoirs, where traditional petrophysical methods do not give definitive results, the use of geomechanical methods will improve interpretation certainty and help to clear doubts in the interpreted results.

Download Full-text

Stochastic fluid modulus inversion

Geophysics ◽

10.1190/1.1527083 ◽

2002 ◽

Vol 67 (6) ◽

pp. 1835-1843 ◽

Cited By ~ 7

Author(s):

Luther White ◽

John Castagna

Keyword(s):

Elastic Wave ◽

Water Saturation ◽

Elastic Wave Velocity ◽

Log Analysis ◽

Well Log ◽

Numerical Examples ◽

Reference Information ◽

Gassmann’S Equation ◽

Well Log Analysis ◽

Stochastic Fluid

A probabilistic inversion approach is used with Gassmann's equation to determine pore fluid modulus using elastic wave velocity without reference information from a rock saturated with a second fluid of known modulus. Numerical examples show that even when uncertainties in input parameters are relatively large, useful estimates of fluid modulus can be obtained. For a well‐log data example, water saturation derived from the inverted fluid modulus compares favorably to saturations derived from well log analysis.

Download Full-text

Geological Model of the Tight Reservoir (Sadi Reservoir-Southern of Iraq)

Journal of Engineering ◽

10.31026/j.eng.2019.06.03 ◽

2019 ◽

Vol 25 (6) ◽

pp. 30-43

Author(s):

Ameer Kadhum Noori ◽

Samaher A. Lazim ◽

Ahmed A. Ramadhan

Keyword(s):

Water Saturation ◽

Oil Field ◽

Log Analysis ◽

Well Log ◽

Geological Model ◽

Tight Reservoir ◽

Petrophysical Model ◽

Well Log Analysis ◽

Log Interpretation ◽

Available Information

A3D geological model was constructed for Al-Sadi reservoir/ Halfaya Oil Field which is discovered in 1976 and located 35 km from Amara city, southern of Iraq towards the Iraqi/ Iranian borders. Petrel 2014 was used to build the geological model. This model was created depending on the available information about the reservoir under study such as 2D seismic map, top and bottom of wells, geological data & well log analysis (CPI). However, the reservoir was sub-divided into 132x117x80 grid cells in the X, Y&Z directions respectively, in order to well represent the entire Al-Sadi reservoir. Well log interpretation (CPI) and core data for the existing 6 wells were the basis of the petrophysical model (Porosity, Water saturation, & Permeability) that were distributed for all the created grids and then upscaled.

Download Full-text