Digital elevation models (DEMs) play a key role in extracting morphometric factors like fill sink, flow accumulation, profile, flow width, slope, plan curvature, aspect, and total catchment to estimate the Topographic Wetness Index (TWI) that provides key information for modelling and predicting hazards related to mass movement or landsliding. The range and accuracy of information, including the topographic feature, can influence the quality of results, significantly impacting the severity and likelihood of occurrence of mass movement. Therefore, it plays a crucial role, especially in mountainous regions. This research aims to investigate, evaluate, and identify the optimal downscaling methodology for DEMs and assess its impact on DEMs at different spatial resolutions. Morphometric factors derived from the DEM were examined using six distinct methodologies: kriging, nearest neighbor, majority, bilinear, bi-cubic, and the Hopfield Neural Network (HNN). Three geospatial databases containing a 20 m, 12.50 m, and 1.50 m resolution DEM were used for analysis. Six downscaled topographic maps were generated: kriging, nearest neighbor, majority, bilinear, bi-cubic, and the HNN. Results validated from field elevation survey points have an accuracy of 1.50 m from total stations and the Global Positioning System (GPS). By predicted actual values at corresponding locations, field survey points named GPS, and total station data having vertical accuracy of 1.50 m, were used as a standalone reference source to validate the downscaled results. Consequently, we strongly endorse downscaling DEM employing the HNN technique to obtain the most precise morphometric parameters for fill sink, flow accumulation, profile, flow width slope, plan curvature, aspect, and total catchment to assess TWI maps. The result shows RMSE accuracy improved accuracy approximately 25% to 75% and 93%, respectively, when progressing from low to medium resolution (30, 20, and 12.50 m) DEMs. It is concluded that all the mentioned techniques, Bi-cubic, HNN, Nearest Neighbor, Majority, Bilinear, and Kriging, can improve the overall accuracy of DEM. However, Bi-cubic and HNN methods demonstrate superior accuracy relative to the Bilinear, Nearest Neighbor, Majority, and Kriging methods. This study attempts to address a gap in past research by evaluating and selecting the most effective downscaling approaches for DEMs and testing their accuracy to enhance topographical features at various spatial resolutions in mountainous regions.

Seismic reservoir characterization in data-limited settings is often hindered by sparse wells, limited resolution, and ambiguous facies delineation. This study develops a convolutional neural network seismic (CNNS) workflow that combines rock-physics-driven synthetic data and transfer learning to improve prediction of elastic properties and lithofacies. Pseudo-wells generated from rock physics models and nearby wells are used to simulate AVO gathers and multi-attribute seismic volumes, which are first used to pre-train the CNNS; the fully connected layers are then fine-tuned with real seismic and well-log data. Elastic property prediction (P-impedance, porosity, and density) is systematically benchmarked against conventional pre-stack seismic inversion (PSSI), a Fully Connected deep neural network (DNN), and a DNN trained with synthetic data (DNNS). Quantitative comparison shows that CNNS yields the most reliable elastic property volumes, with overall R2 values of 0.9655 for Pimpedance (0.9749 at a blind well), 0.9644 for density, and 0.9695 for porosity. Variogram and spatial autocorrelation analyses demonstrate that CNNS best preserves vertical resolution and anisotropic lateral continuity, whereas DNNS tends to over-smooth and PSSI/DNN exhibit higher short-wavelength noise. Based on these CNNS-derived P-impedance, porosity, and density volumes selected because they provide the most geologically consistent elastic fields lithofacies prediction is performed exclusively with CNNS, without direct facies comparison to PSSI, DNN, or DNNS. Facies are classified into four categories: non-reservoir mudstone and low, medium, and high porosity sandstone. The CNNS-based facies model shows excellent agreement with well-log interpretations and channel architecture, achieving classification accuracies of 91.02 % (mudstone), 97.05 % (low-porosity sand), 100 % (medium-porosity sand), and 98.80 % (high-porosity sand. The resulting 3D facies distribution delineates laterally continuous high-quality sandstone bodies and discontinuous injectites, providing a robust basis for targeting sweet spots and optimizing drilling strategies in complex reservoirs.

The Sembar Formation is a key petroliferous unit in the Lower Indus Basin of Pakistan; however, its resource potential remains uncertain due to limited and discontinuous Total Organic Carbon (TOC) and Rock-Eval pyrolysis data. Accurate assessment of TOC, volatile hydrocarbons (S1), remaining hydrocarbons (S2), carbon dioxide yield (S3), maximum pyrolysis temperature (Tmax), and Vitrinite Reflectance (

Carbon dioxide (CO2) emissions pose a major environmental concern, and various methods are used for CO2 sequestration. CO2-water activating gas (CO2-WAG) injection is a technique used to increase production of oil and sequester CO2 in subsurface formations. However, the performance of the CO2-WAG project depends on various parameters, such as injection rates, cycle size, and ratio, that traditionally require numerous computationally expensive simulations. The study introduces a robust machine learning workflow for CO2-WAG performance prediction and optimization by using a model calibrated using Bell Creek formation properties. Machine learning models are based on algorithms like extreme gradient boosting (XGBoost), linear regression (LR), random forest (RF), k-nearest neighbor (KNN), support vector regression (SVR), artificial neural network (ANN), convolutional neural network (CNN), and hybrid models such as ANN and CNN coupled with XGBoost (ANN-XGBoost, and CNN-XGBoost) to predict CO2-WAG performance. A dataset of 2,400 samples was generated using the CMG-GEM numerical simulator, incorporating seven input parameters (e.g., injection rate, CO2-WAG cycle size, and WAG ratio) and three output parameters, with 80% of the dataset allocated for training and 20% for validation and testing. Among the proposed models, the hybrid model ANN-XGBoost demonstrated superior performance, accurately predicting total oil production, CO2 storage, and efficiency, with high R2 scores of 0.99159, 0.97515, and 0.98706, and corresponding lower RMSE values of 2.8 × 10−2, 1.5 × 10−1, and 2.4 × 10−2. Coupling the proxy with particle swarm optimization (PSO) yielded 12.8% increase in cumulative oil production and 11% increase in CO2 storage. Furthermore, in terms of speed, the projected workflow requires less minutes to complete predictions and optimization, while traditional numerical simulators require 4–5 min per scenario. These findings validates the robustness and computational efficiency of the proposed machine learning workflow for predicting CO2-WAG performance and optimization.

Tight gas reservoirs require unconventional recovery techniques to obtain maximum production and need a detailed understanding of reservoir rock elastic parameters. Pab Formation has intervals of low permeability with promising hydrocarbon saturation. The study aims to provide a thorough analysis of the effect of porosity and mineralogical composition on the rock physics properties and brittleness index of the Pab Formation. In the present study, an investigation into clay minerals and types was conducted using cross-plot analysis from well log data, and validation was performed using SEM and XRD results from core samples. The research incorporates the calculation of the elastic parameters from the specialized user-defined equation and rock physics template (RPT). The findings of this research through petrography and XRD analysis of core samples reveal sandstone as the dominant lithology of the Pab Formation and are rich in quartz and kaolinite; cross-plot analysis also showed the presence of these clay minerals. Combining elastic moduli, porosity, and current petrophysical data for RPT analysis will serve as a robust framework and can be beneficial for similar studies in other basins.

Understanding seismic faults is essential for generating prospects, modeling reservoirs, and assessing carbon dioxide storage. Identifying faults in complex tectonic regimes presents significant challenges, especially in areas that have undergone multiple phases of tectonic activity. Even with advances in structural seismic attributes and machine learning, interpreters often rely on manual methods to examine complex fault systems. This work introduces a method for predicting three-dimensional seismic faults using convolutional neural networks (CNNs), effectively overcoming the constraints of conventional interpretation techniques. The research uses CNNs to demonstrate the effectiveness of seismic attributes in training models that identify faults with high accuracy and consistency. This approach, unlike manual interpretation, reduces time, costs, and subjective errors by leveraging automated learning techniques, thereby improving reproducibility and efficiency while reducing interpreter bias. The research highlights the growing importance of solid computational tools in geophysics, especially as seismic datasets become more complex and wider. The approach significantly enhances confidence in artificial intelligence-assisted geological analysis by validating its performance with real-world data. The validation accuracy rises from 0.936 to 0.9436 across configurations, while the validation loss increases from 0.5635 to 0.9941 across diverse patches of the trained model.

South Asia faces a sustained tension between rapid economic expansion and growing environmental and public health pressures. Although the trade-energy-emissions-health relationship in the region has been studied with a range of parametric and single-country models, comparatively little descriptive work has placed CO2 intensity and CO2 damages alongside trade openness, energy consumption, and health expenditure across the full set of South Asian economies. This study addresses that descriptive gap. Using publicly available country-level data for Afghanistan, Bangladesh, Bhutan, India, Maldives, Nepal, Pakistan, and Sri Lanka over 1990–2020, we conduct an exploratory, comparative analysis using descriptive statistics, one-sample t-tests with Cohen's d and Hedges' g effect sizes, and the one-sample Chi-square and Kolmogorov–Smirnov non-parametric tests. The analysis is distributional and country-comparative; it does not estimate causal effects or long-run dynamic relationships. The results indicate that India, Sri Lanka, and Maldives correspond to the upper end of the regional distribution for CO2-related indicators, while Bhutan, Nepal, and Afghanistan are linked with higher relative health expenditure. These cross-country patterns are associated with the qualitative expectations of the Environmental Kuznets Curve and Ecological Modernization Theory, which are used here as interpretive frameworks rather than empirically tested theories. The findings suggest directions for future panel-econometric, SEM, and dynamic modelling research aimed at assessing causal and long-run mechanisms.

Pakistan has potential for geothermal energy within the subsurface, but these resources are still unexplored due to limited research. The present study prime aims to utilize seismic and well data to explore the geothermal potential of the sandstone reservoir. Facies analysis was performed based on well data through machine learning, demonstrating that the major facies present are sandstone and shale in the target Formation. It has been inferred in the current assessment that the presence of radioactive elements in these lithologies is an active source of heat in the subsurface. Deep Feed Forward Neural Network (DFFNN) techniques were employed to populate geothermal reservoir parameters into the seismic section. DFFNN can enhance the integration of seismic and well data for reservoir characterization by estimating rock properties obtained from seismic inversion methods. DFFNN approach achieved correlation values from 88.60–93 % for geothermal properties at the well position. This study is novel due to its combination of statistical methods and an artificial intelligence approach that enables the identification of geothermal perspective maps (heat production and radiogenic heat production) on seismic sections that are typically not studied before. The outcomes of subsurface geothermal reservoir parameters average values derived from well logs data: average porosity (18 %), volume of shale (22.67 %), heat production (0.988 µW/m3), radiogenic heat production (0.847 µW/m3), and permeability (17.74 mD) are quite promising which indicates that the current study region is favorable for geothermal resources. It has been concluded that the current study approaches have improved the prediction accuracy of geothermal reservoir properties.

One form of renewable energy that is gaining attention globally is geothermal energy resources. Geothermal energy potential exists in Pakistan; however, these resources have not yet been fully tapped because of a lack of research. The present study aims to utilize 2D seismic and well data to explore the geothermal potential of the Lower Indus Basin, specifically in the Sanghar Block, and the target was the Lower Goru Formation sandstone reservoir. The 2D seismic structural interpretation confirms that the area has normal faulting with the horst and graben structure, indicating extension tectonics. A seismic attributes analysis was performed on 2D seismic data, such as spectral decomposition, similarity variance, trace envelop, and instantaneous frequency. It also confirms the presence of geothermal anomalies, such as high frequency and reflectance, at the Lower Goru Formation. Two wells, Sono-2 and Sono-5, were utilised for studies in which heat production, formation temperature, average porosity, shale volume, and permeability were computed. Seismic inversion was performed to assess the impedance in the overall study block. Model-based seismic inversion analysis results indicated that 98 % and 92 % correlation were achieved at the Sono-2 and Sono-5 wells, respectively. Probabilistic Neural Network (PNN) techniques were employed for geothermal reservoir properties and interpolated in the seismic section to assess geothermal potential. The outcomes obtained from geothermal properties via PNN indicated excellent correlation values of 94.50-98.80 % around the well location. The findings of the study suggested the presence of geothermal resources in the study region.

More than 70% of the global hydrocarbon reserves are present in carbonated rocks. Evaluating prospects in carbonate reservoirs is a complicated task because of their unique depositional features. The Eocene carbonates in the Joyamair oil field are heterogeneous and present challenges defining the entrapment and sealing mechanism by applying traditional methods. Although structural interpretation revealed a positive triangular geometry, estimating accurate reservoir properties requires an effective model for assessing hydrocarbon presence. Therefore, an optimized machine learning (ML) approach has been deployed to address reservoir challenges and delineate the potential with a high success rate after drawing a comparison with the conventional approach. Two wells were utilized for petrophysical evaluation in the conventional method, while one well (Joyamair-04) was kept blind in a supervised ML approach. Extra Tree Regressor (ETR) produced a low volume of shale and effective porosity (PHIE) high results with more than 99% R2 and least mean square error score. Random Forest Regressor (RFR) showed water saturation (Sw) results with about 100% accuracy compared to conventional interpretation at a blind well. Volumetric reserve estimation also proved economical hydrocarbon reserves present in the reservoir formation. The study revealed that integrating conventional and ML techniques along with structural geometry aided better reservoir characterization and reserve estimation. The study proved that ML algorithms outperformed traditional petrophysical methods in accuracy and efficiency.

Pore pressure is a decisive measure to assess the reservoir’s geomechanical properties, ensures safe and efficient drilling operations, and optimizes reservoir characterization and production. The conventional approaches sometimes fail to comprehend complex and persistent relationships between pore pressure and formation properties in the heterogeneous reservoirs. This study presents a novel machine learning optimized pore pressure prediction method with a limited dataset, particularly in complex formations. The method addresses the conventional approach's limitations by leveraging its capability to learn complex data relationships. It integrates the best Gradient Boosting Regressor (GBR) algorithm to model pore pressure at wells and later utilizes Continuous Wavelet Transformation (CWT) of the seismic dataset for spatial analysis, and finally employs Deep Neural Network for robust and precise pore pressure modeling for the whole volume. In the second stage, for the spatial variations of pore pressure in the thin Khadro Formation sand reservoir across the entire subsurface area, a three-dimensional pore pressure prediction is conducted using CWT. The relationship between the CWT and geomechanical properties is then established through supervised machine learning models on well locations to predict the uncertainties in pore pressure. Among all intelligent regression techniques developed using petrophysical and elastic properties for pore pressure prediction, the GBR has provided exceptional results that have been validated by evaluation metrics based on the R2 score i.e., 0.91 between the calibrated and predicted pore pressure. Via the deep neural network, the relationship between CWT resultant traces and predicted pore pressure is established to analyze the spatial variation.

Accurate insights into the spatial distribution of cultivated areas, land use for effective agricultural management, and improvement of food security planning, especially in developing countries. Therefore, this study examined the impact of land changes and population growth on agricultural land and wheat crop productivity. First, by incorporating more than three decades of satellite data (1990–2022) and different Landsat missions with machine learning algorithms, high-confidence classes were defined for different land features, including cropland. Second, the wheat grown area was identified using the cropland extraction based wheat acreage assessment method (CLE-WAAM). Third, population dynamics were examined by applying an exponential growth model to forecast population growth and predict food demand. These findings necessitate the integrated methodological development for wheat demand and supply mechanisms using the two-step floating catchment area (2SFCA) approach for a more thorough analysis of socioeconomic developments. The results revealed that the cropland area was transformed into non-cropland, with a percentage of 8.01. A 79% rise in the population occured between 1990 and 2022, with a projected increase of 112% by 2030. Specifically, the wheat cultivation area decreased by 28%, despite stagnant parameters observed since 2000. The proposed method contributes efficiently to the United Nations’ sustainable development goal (02: Zero Hunger) using satellite, geospatial, and statistical data integration.

Accurately characterizing reservoir petrophysical parameters and delineating lithofacies is challenging in heterogeneous formations. Traditional seismic interpretations may be uncertain, but probabilistic neural network (PNN) modeling and seismic inversion constrained by well log data have improved interpretation accuracy and reduced uncertainty in determining reservoir properties such as volume and distribution. It is necessary to determine reservoir assessment parameters precisely and conduct a thorough integrated study of promising blocks that hold paramount potential and will help reduce drilling risk and increase the recovery of oil and gas resources. This paper provides a comprehensive integrated approach to differentiate lithofacies within a gas-prone reservoir (Lower Goru Formation) and predict the potential for hydrocarbon resources in the Sinjhoro Block of Pakistan. This approach involves petrophysical analysis, rock physics, seismic attributes, seismic inversion, multi-attribute analysis, and PNN for estimating petrophysical parameters for source and reservoir rock evaluation. The trace-based 2D extracted attributes, such as pronounced root mean square amplitude anomalies within the Talhar Shale, indicate that hydrocarbon indicators are aligned with the seismic structure interpretation and are considered an appropriate tool for extracting information from poststack seismic data. The results obtained through an integrated approach effectively optimize lateral and vertical facies heterogeneities in target formations, enabling the precise prediction of reservoir parameter distributions. The petrophysical analysis results indicated the presence of gas sands in Basal Sands (hydrocarbon saturation = 53

Identification and classification of lithology and estimating total organic carbon (TOC) content in organic shale for source rock evaluation are challenging through indirect approaches in the sedimentary basin and have been addressed in current research through machine learning (ML) approaches. The Kohat sub‐basin is the most prolific basin of Pakistan due to its multiple active petroleum fields and prospective strata ranging from the Cambrian to the Miocene, supported by a hydrocarbon system. While earlier investigations have suggested the potential presence of oil and gas in the source rocks, the region has encountered difficulties making substantial oil discoveries due to a limited understanding of source rock evaluation and complex geological structures. The present study deals with seismic structural interpretation, geochemical analysis for source rock evaluation, lithology identification through ML, and estimation of TOC content using conventional well logs, ML, and lab measured data. The numerical models and ML algorithms based on well log data were applied to estimate TOC content. Lithology delineations through ML were performed within each formation, particularly shale, marl, and limestone in the Patala Formation and sandstone and shale in the Hangu Formation. To evaluate the Paleocene (Hangu and Patala formations) source potential in the basin, a thorough geochemical investigation and source rock evaluation of X‐01 core/well cuttings were conducted. TOC, Rock‐Eval (RE) pyrolysis, vitrinite reflectance techniques, and well log analysis were employed. The TOC values of Hangu Formation are 0.90%–3.20%, which lies in fair to excellent, and Patala Formation 0.82%–2.70%, which shows fair to good TOC content. In this study, it has been inferred that Passey’s method provided better results in estimating the TOC in comparison to core/well cutting measured TOC. The TOC estimate results indicate that the correlation coefficient ( R ) values for well log ∆logR method exceed 0.92 for both formations. In contrast, the random forest (RF)–based ML method demonstrates an R value of 0.94. The Kerogen currently seems to be type II and type III. Generation potential is mostly poor, but at some points, Patala and Hangu show fair to good potential. Study formations’ vitrinite reflectance ( R o ) exists in the oil window. R o values represent vitrinite as the dominant maceral in the Paleocene strata. The second principal maceral is inertinite, and the third maceral is solid bitumen. Pyrite is observed as the main accessory mineral in Paleocene strata. This study proves that well log data can be employed confidently to assess the organic source rock potential even without geochemical data in similar basins around the globe.

Fimkassar Oil Field (FOF) is located in the Potwar Sub Basin, having a fractured carbonate supply that includes reservoir formations (Chorgali-Sakesar). The Sakesar Limestone, considered a significant and established reservoir in numerous oil and gas fields in the Potwar Plateau, was evaluated for reservoir potential in the current work. This study conducts a petrophysical analysis to evaluate hydrocarbon potential, as well as an analysis of outcrop and core samples to investigate the porosity and permeability of the Sakesar Limestone. Seismic data structure interpretation was performed to assess the subsurface structure patterns, and seismic attributes were employed to identify fractures in Sakesar Limestone. The reservoir petrophysical properties were compared with the core samples analysis results of the Sakesar Limestone. The porosity and permeability of outcrop and core samples of Sakesar Limestone were determined in the laboratory. Two wells of the FOF have been taken for well log interpretation. The porosity calculated from the outcrop and core samples is 0.68 %-11.65 % and 3.86 %- 10.76 %, respectively. The permeability calculated from the outcrop samples ranges from 0.0 to 26.82 mD. The lithological cross-plots were used to identify the lithology, and rock physics analysis provided information on the fluid type present in the formation. The correlation of the reservoir properties indicated that Sakesar Limestone has hydrocarbon potential and is a good reservoir.

Geothermal resource exploration has grown in importance globally as a research hotspot due to the depletion of conventional fossil fuel reserves and green energy initiatives. This research's prime objective is to explore the geothermal potential, primarily focused on the Paleocene rock geothermal systems in Southeast Pakistan. Globally, the use of remote sensing for geothermal anomaly detection has gained much attention recently due to the increased focus on green energy. This study aimed to identify regions with geothermal anomalies using land surface temperature (LST) data, a geospatial dataset to develop geological mapping, and geophysical well logs analysis to compute heat production and petrophysical analysis. An overview of geo-pressurized systems and geothermal resources' location in Southeast Pakistan has been provided to get an idea of the geothermal target in this region. The LST values were quantitatively classified into five categories: very high, high, medium, low, and very low, and LST results indicate that the data cluster lies in 20 %, 54 %, 4 %, 3 %, and 19 %, respectively. Normalized difference vegetation index results showed that 96 % of the study area lies in bare soil to mixed surface, and only 4 % of the region lies in full vegetation. Petrophysics results indicate that the Ranikot Formation has very good effective porosity ranges of 20-24 % in the studied wells, suggesting a potential candidate for enhanced geothermal systems (EGS). Basin modeling was performed to delineate subsurface heat flow (109-113 mW/m2), temperature (60-150 degrees C), and effective porosity (22-24 %) distribution mapping. The concentration number (C-N) model and log-log plots techniques were employed to map gamma-ray and heat production values to separate the geothermal anomaly and spatial correlation from its background. Emerging advancements in technologies such as EGS for exploiting geothermal energy and reducing exploration risk are crucial economically in geothermal reservoirs. These innovations have attracted researchers to explore the potential to utilize geothermal energy significantly. Still, their successful implementation principally relies on an indepth understanding of the local geological conditions of the basin.

The potential of agriculture land monitoring serves as the lifeblood of communities, nourishing populations and fostering economic growth on a global scale. Towards the advancement of the computational approach, this study employed an analytical hierarchal process modeling for agriculture land suitability assessment by integrating a comprehensive array of 4 major criteria with a decision matrix, including 19 influencing parameters. This research incorporates the field data, including soil chemical and physical properties, irrigation water accessibility and irrigation water quality parameters, which are analyzed with cutting-edge remote sensing data layers and climatic variables using an integrated modelling approach. Thorough field observations and integrated methodology improved the conventional practices by considering the close interactions between soil, irrigation water, cropland and topography. The most innovative aspect of this research is based upon the seamless fusion of data layers of different datasets, which improves agriculture's suitability. Pairwise comparisons are systematically conducted to assign weights to each parameter, ensuring a robust decision-support framework with weighted overlay. The finding showed that the 72209.03 acres (9.13 %) cropland is highly suitable, whereas the 717738.48 acres (90.77 %) area is suitable, and the 788.49 acres (0.1 %) area is less suitable for crop cultivation. The study emphasizes the significance of each parameter in influencing suitability, contributing valuable insights into sustainable land management practices. The findings provide meaningful information for policymakers, land use planners and agriculture stakeholders interested in optimizing land management strategies to ensure sustainable agriculture development.

Petrophysics primarily focuses on understanding the relationship between rock properties and fluid behavior. However, traditional petrophysical modeling has certain limitations. In the context of the Berryman theory, the aspect ratio of pores is considered in petrophysical modeling. The challenge lies in the inability to directly measure the pore aspect ratio, leading to the use of an empirically fixed value. To address this issue, we propose a method for correcting the pore aspect ratio through genetic algorithms (GAs) in conjunction with the Berryman model. By revising the pore aspect ratio ( $\alpha $ ), we enhance the accuracy of forward modeling. To incorporate the revised pore aspect ratio into the petrophysical inversion process, we utilize a data-driven deep learning approach to solve this unconventional problem. Specifically, we employ a convolution long short-term memory (CNN-LSTM) network to jointly invert multiple reservoir parameters, including the revised pore aspect ratio. This approach was applied to a tight sandstone reservoir in a specific work area.

The comprehension of seismic faults is essential for generating prospects, modeling reservoirs, and assessing CO 2 storage. Identifying faults in complex tectonic regimes presents significant challenges, especially in areas that have undergone multiple phases of tectonic activity. Even with progress in structural seismic attributes and machine learning, interpreters frequently depend on manual techniques to examine complex fault systems. This work introduces a method for predicting 3D seismic faults through the application of Convolutional Neural Networks (CNNs), which effectively overcomes the constraints associated with conventional interpretation techniques. The project utilizes Convolutional Neural Networks (CNNs) to illustrate the effective use of seismic attributes in training models that can identify faults with high accuracy and consistency. This method, in contrast to manual interpretation, minimizes time consumption and subjective error by utilizing automated learning techniques, thereby enhancing reproducibility, efficiency, and reducing interpreter bias. The research emphasizes the increasing significance of strong computational tools in geophysical engineering, particularly as seismic datasets grow more complex and extensive. Additionally, the framework plays a significant role in strengthening confidence in AI-assisted geological analysis through the validation of its performance using real-world data. This approach minimizes dependency on manual processes while showcasing the capability of machine learning to enhance reliable, scalable, and objective workflows for subsurface interpretation.

Kadanwari Gas Field (KGF) is located in the Middle Indus Basin (MIB), Pakistan is characterized by a variety of heterogenous sedimentary facies, and unique reservoir architecture. These factors make the area more challenging with respect to identification of hydrocarbon potential. Several studies were conducted to delineate the true potential of the basin which were mostly limited to Cretaceous reservoirs only. Therefore, an effort was made to reveal the reservoir characteristics Ranikot Formation (Paleocene) using an integrated approach using 3D seismic and well data. Petrophysical analyses, rock physics analysis, seismic interpretations, structural framework modelling, seismic inversion, facies modelling, and static modelling were performed to describe the reservoir characteristics and structural variation of the formation. The petrophysical study revealed the Ranikot Formation contains lower values of volume of shale (15–25