An ensemble-based strategy for robust predictive volcanic rock typing efficiency on a global-scale: A novel workflow driven by big data analytics.

Laboratory measurements, paleontological data, and well-logs are often used to conduct mineralogical and chemical analyses to classify rock samples. Employing digital intelligence techniques may enhance the accuracy of classification predictions while simultaneously speeding up the whole classification process. We aim to develop a comprehensive approach for categorizing igneous rock types based on their global geochemical characteristics. Our strategy integrates advanced clustering, classification, data mining, and statistical methods employing worldwide geochemical data set of ~25,000 points from 15 igneous rock types. In this pioneering study, we employed hierarchical clustering, linear projection analysis, and multidimensional scaling to determine the frequency distribution and oxide content of igneous rock types globally. The study included eight classifiers: Logistic Regression (LR), Gradient Boosting (GB), Random Forest (RF), K-nearest Neighbors (KNN), Support Vector Machine (SVM), Artificial Neural Network (ANN), and two ensemble-based classifier models, EN-1 and EN-2. EN-1 consisted of LR, GB, and RF aggregates, whereas EN-2 comprised the predictions of all ML models used in our study. The accuracy of EN-2 was 99.2 %, EN-1 achieved 98 %, while ANN yielded 98.2 %. EN-2 provided the best performance with highest initial curve for longest time on the receiver operating characteristic (ROC) curve. Based on the ranking features, SiO2 was deemed most important followed by K2O and Na2O. Our findings indicate that the use of ensemble models enhances the accuracy and reliability of predictions by effectively capturing diverse patterns and correlations within the data. Consequently, this leads to more precise results in rock typing globally.

Reservoir rock typing assessment in a coal-tight sand based heterogeneous geological formation through advanced AI methods.

Geoscientists now identify coal layers using conventional well logs. Coal layer identification is the main technical difficulty in coalbed methane exploration and development. This research uses advanced quantile-quantile plot, self-organizing maps (SOM), k-means clustering, t-distributed stochastic neighbor embedding (t-SNE) and qualitative log curve assessment through three wells (X4, X5, X6) in complex geological formation to distinguish coal from tight sand and shale. Also, we identify the reservoir rock typing (RRT), gas-bearing and non-gas bearing potential zones. Results showed gamma-ray and resistivity logs are not reliable tools for coal identification. Further, coal layers highlighted high acoustic (AC) and neutron porosity (CNL), low density (DEN), low photoelectric, and low porosity values as compared to tight sand and shale. While, tight sand highlighted 5-10% porosity values. The SOM and clustering assessment provided the evidence of good-quality RRT for tight sand facies, whereas other clusters related to shale and coal showed poor-quality RRT. A t-SNE algorithm accurately distinguished coal and was used to make CNL and DEN plot that showed the presence of low-rank bituminous coal rank in study area. The presented strategy through conventional logs shall provide help to comprehend coal-tight sand lithofacies units for future mining.

Improving predictions of shale wettability using advanced machine learning techniques and nature-inspired methods: Implications for carbon capture utilization and storage.

The utilization of carbon capture utilization and storage (CCUS) in unconventional formations is a promising way for improving hydrocarbon production and combating climate change. Shale wettability plays a crucial factor for successful CCUS projects. In this study, multiple machine learning (ML) techniques, including multilayer perceptron (MLP) and radial basis function neural networks (RBFNN), were used to evaluate shale wettability based on five key features, including formation pressure, temperature, salinity, total organic carbon (TOC), and theta zero. The data were collected from 229 datasets of contact angle in three states of shale/oil/brine, shale/CO2/brine, and shale/CH4/brine systems. Five algorithms were used to tune MLP, while three optimization algorithms were used to optimize the RBFNN computing framework. The results indicate that the RBFNN-MVO model achieved the best predictive accuracy, with a root mean square error (RMSE) value of 0.113 and an R2 of 0.999993. The sensitivity analysis showed that theta zero, TOC, pressure, temperature, and salinity were the most sensitive features. This research demonstrates the effectiveness of RBFNN-MVO model in evaluating shale wettability for CCUS initiatives and cleaner production.

Hydrocarbon Potential Assessment of Carbonate-Bearing Sediments in a Meyal Oil Field, Pakistan: Insights from Logging Data Using Machine Learning and Quanti Elan Modeling.

The Meyal oil field (MOF) is among the most important contributors to Pakistan's oil and gas industry. Northern Pakistan's Potwar Basin is located in the foreland and thrust bands of the Himalayan mountains. The current research aims to delineate the hydrocarbon potential, reservoir zone evaluation, and lithofacies identification through the utilization of seven conventional well logs (M-01, M-08, M-10, M-12, M-13P, and M-17). We employed the advanced unsupervised machine-learning method of self-organizing maps for lithofacies identification and the novel Quanti Elan model technique for comprehensive multimineral evaluation. The shale volume, porosity, permeability, and water saturation (petrophysical parameters) of six wells were evaluated to identify the reservoir potential and prospective reservoir zones. Well-logging data and self-organizing maps were used in this study to provide a less costly method for the objective and systematic identification of lithofacies. According to the SOM and Pickett plot analyses, the zone of interest is mostly made up of pure limestone oil zone, whereas the sandy and dolomitic behavior with a mixture of shale content shows non-reservoir oil-water and water zones. The reservoir has good porosity values that range from 0 to 18%, but there is a high water saturation of up to 45% in reservoir production zones. The presence of shale in the entire reservoir interval has a negative effect on the permeability value, but the petrophysical properties of the Meyal oil reservoir are good enough to permit hydrocarbon production. According to the petrophysical estimates, the Meyal oil field's Sakesar and Chorgali Formations are promising reservoirs, and new prospects for drilling wells in the southern and central portions of the eastern portion of the research area are recommended.

An Emerged Challenge of Air Pollution and Ever-Increasing Particulate Matter in Pakistan; A Critical Review.

This study, for the first time, aims to evaluate the situation of air quality in Pakistan critically; through a detailed assessment of sources, policies, and key challenges to identify the plausible way forward. Air pollution and particulate matter have merged as a global challenge in recent years because of its growing health and socio-economic risks. The intensity and impacts of these risks have become more pronounced, especially in developing countries like Pakistan that lack adequate warning, protection, and management systems. Various epidemiological studies have linked poor air quality with different health disorders and increasing death rates. In Pakistan, mortality rates as a result of exposure to increased levels of air pollutants, especially particulate matter, are alarming. According to the World Bank's estimates, Pakistan's annual burden of disease from outdoor air pollution is responsible for around 22,000 premature adult deaths and 163,432 DALYs (disability-adjusted life years) lost. The concentration of major air pollutants in Pakistan, such as NOx, O3, and SO2 have also been increasing significantly over the last two decades. Several studies are also reporting multiple instances of air quality around the major cities of Pakistan being consistently exceeding the national guidelines. During teh year 2019 PM2.5 cocnentrations in the city of Lahore revealed that almost every single day was in exceedance of the WHO and national air quality standards. Although the substantial effects of these rising pollutant concentrations in Pakistan have been stated in a few studies, however, the total extent, nature of contributing factors, and consequences remain inadequately understood. This study aims to use data available from monitoring stations, satellites, and literature to highlight the gaps in our understanding and emphasize the critical challenges associated with poor air quality faced in Pakistan. Topmost is the lack of air quality monitoring systems followed by poor initiatives by policymakers and enforcement agencies. A way forward while addressing these key challenges is also discussed, which focuses on the development of flexible monitoring, new technologies, and monitoring approaches in addition to communications among the various public, private agencies, and all relevant stakeholders.