Abstract The oil and gas industry relies on accurately predicting profitable clusters in subsurface formations for geophysical reservoir analysis. It is challenging to predict payable clusters in complicated geological settings like the Lower Indus Basin, Pakistan. In complex, high-dimensional heterogeneous geological settings, traditional statistical methods seldom provide correct results. Therefore, this paper introduces a robust unsupervised AI strategy designed to identify and classify profitable zones using self-organizing maps (SOM) and K-means clustering techniques. Results of SOM and K-means clustering provided the reservoir potentials of six depositional facies types (MBSD, DCSD, MBSMD, SSiCL, SMDFM, MBSh) based on cluster distributions. The depositional facies MBSD and DCSD exhibited high similarity and achieved a maximum effective porosity (PHIE) value of ≥ 15%, indicating good reservoir rock typing (RRT) features. The density-based spatial clustering of applications with noise (DBSCAN) showed minimum outliers through meta cluster attributes and confirmed the reliability of the generated cluster results. Shapley Additive Explanations (SHAP) model identified PHIE as the most significant parameter and was beneficial in identifying payable and non-payable clustering zones. Additionally, this strategy highlights the importance of unsupervised AI in managing profitable cluster distribution across various geological formations, going beyond simple reservoir characterization.
The precise characterization of reservoir parameters is vital for future development and prospect evaluation of oil and gas fields. C-sand and B-sand intervals of the Lower Goru Formation (LGF) within the Lower Indus Basin (LIB) are proven reservoirs. Conventional seismic amplitude interpretation fails to delineate the heterogeneity of the sand-shale facies distribution due to limited seismic resolution in the Sawan gas field (SGF). The high heterogeneity and low resolution make it challenging to characterize the reservoir thickness, reservoir porosity, and the factors controlling the heterogeneity. Constrained sparse spike inversion (CSSI) is employed using 3D seismic and well log data to characterize and discriminate the lithofacies, impedance, porosity, and thickness (sand-ratio) of the C- and B-sand intervals of the LGF. The achieved results disclose that the CSSI delineated the extent of lithofacies, heterogeneity, and precise characterization of reservoir parameters within the zone of interest (ZOI). The sand facies of C- and B-sand intervals are characterized by low acoustic impedance (AI) values (8 × 106 kg/m2s to 1 × 107 kg/m2s), maximum sand-ratio (0.6 to 0.9), and maximum porosity (10% to 24%). The primary reservoir (C-sand) has an excellent ability to produce the maximum yield of gas due to low AI (8 × 106 kg/m2s), maximum reservoir thickness (0.9), and porosity (24%). However, the secondary reservoir (B-sand) also has a good capacity for gas production due to low AI (1 × 107 kg/m2s), decent sand-ratio (0.6), and average porosity (14%), if properly evaluated. The time-slices of porosity and sand-ratio maps have revealed the location of low-impedance, maximum porosity, and maximum sand-ratio that can be exploited for future drillings. Rock physics analysis using AI through inverse and direct relationships successfully discriminated against the heterogeneity between the sand facies and shale facies. In the corollary, we proposed that pre-conditioning through comprehensive petrophysical, inversion, and rock physics analysis are imperative tools to calibrate the factors controlling the reservoir heterogeneity and for better reservoir quality measurement in the fluvial shallow-marine deltaic basins.
The Hangjinqi area was explored for natural gas around 40 years ago, but the efficient consideration in this area was started around a decade ago for pure gas exploration. Many wells have been drilled, yet the Hangjinqi area remains an exploration area, and the potential zones are still unclear. The Lower Shihezi Formation is a proven reservoir in the northern Ordos Basin. This study focuses on the second and third members of the Lower Shihezi Formation to understand the controlling factors of faults and sedimentary facies distribution, aimed to identify the favorable zones of gas accumulation within the Hangjinqi area. The research is conducted on a regional level by incorporating the 3D seismic grid of about 2500 km 2 , 62 well logs, and several cores using seismic stratigraphy, geological modeling, seismic attribute analysis, and well logging for the delineation of gas accumulation zones. The integrated results of structural maps, thickness maps, sand-ratio maps, and root mean square map showed that the northwestern region was uplifted compared to the southern part. The natural gas accumulated in southern zones was migrated through Porjianghaizi fault toward the northern region. Well J45 from the north zone and J77 from the south zone were chosen to compare the favorable zones of pure gas accumulation, proving that J45 lies in the pure gas zone compared to J77. Based on the faults and sedimentary facies distribution research, we suggest that the favorable zones of gas accumulation lie toward the northern region within the Hangjinqi area.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)
