SIMULATION STUDY OF CO₂ FLOODING AND WATER-ALTERNATING-GAS INJECTION FOR ENHANCED OIL RECOVERY IN TIGHT OIL RESERVOIRS: A CASE STUDY OF BLOCK X

2026-08-24T22:21:09+05:00

As a key element in unconventional oil and gas resources, tight reservoirs face many challenges throughout the development stages due to their extremely low porosity and permeability characteristics. Traditional crude oil extraction techniques often fail to achieve optimal extraction efficiency. Therefore, Enhanced Oil Recovery (EOR) technologies are crucial for improving crude oil production in unconventional reservoirs. Among the key tertiary oil recovery techniques, CO₂ injection has garnered significant attention in contemporary research. This study uses the CMG reservoir simulation software to create a representative reservoir model of tight oil reservoirs and simulates two injection techniques, including CO₂ injection and Water-Alternating-Gas (WAG) injection. The study evaluates key indicators such as oil production rate, gas-oil ratio (GOR), and oil and gas recovery rates. Continuous Gas Drive: A moderate injection rate (8000–10000 m³/day) is recommended to balance recovery rate and gas breakthrough risk. A high rate (12000 m³/day) shows higher short-term recovery but causes rapid pressure drop and significant gas breakthrough; a low rate (6000 m³/day) maintains steady pressure but has low efficiency. WAG Injection Timing: Delayed gas injection (after water flooding) can reduce GOR by 20–30%, as the water flooding first mobilizes crude oil, enhancing the gas displacement efficiency. WAG Gas-to-Water Ratio: A moderate gas-to-water ratio (1:1–1:2) is optimal, with recovery rates improving by 10–15% compared to extreme ratios (2:1 or 1:5). A high gas-to-water ratio (2:1) leads to increased gas breakthrough, while a low ratio (1:5) is stable but results in slow recovery growth. The results of this study provide theoretical support and technical guidance for the development of tight oil reservoirs, offering practical engineering applications.

FAKE NEWS DETECTION USING NATURAL LANGUAGE PROCESSING AND MACHINE LEARNING: A MULTI-DATASET COMPARATIVE STUDY WITH SMOTE-BASED CLASS BALANCING AND HYPERPARAMETER OPTIMIZATION

2026-07-31T11:53:09+05:00

Unfortunately, fake news has also become an issue in the digital era as it can be damaging to people, organisations and even countries. In this study, a holistic machine learning method to detect fake news using natural language processing (NLP) techniques is presented. The classifiers that are tested are the following: Logistic Regression (LR), Decision Tree (DT), Random Forest (RF), Passive Aggressive Classifier (PAC), Support Vector Machine (SVM), Multinomial Naive Bayes (MNB). The technique consists of text preprocessing, TF-IDF vectorization, SMOTE (Synthetic Minority Over-sampling Technique) to overcome the class imbalance and Hyperparameter tuning using GridSearchCV and 5-fold cross validation.

We conduct tests with two datasets: a small news dataset (6,335 samples) and a large dataset of mixed fake-real (44,898 samples). With SMOTE and hyperparameter tuning, Naïve Bayes is improved by 5.5% (from 86.0% to 91.5%) and Random Forest by 0.6% (from 90.4% to 91.0%). All of the models achieve a greater accuracy on the larger data set.

Spectrum of Engineering Sciences

SIMULATION STUDY OF CO₂ FLOODING AND WATER-ALTERNATING-GAS INJECTION FOR ENHANCED OIL RECOVERY IN TIGHT OIL RESERVOIRS: A CASE STUDY OF BLOCK X

FAKE NEWS DETECTION USING NATURAL LANGUAGE PROCESSING AND MACHINE LEARNING: A MULTI-DATASET COMPARATIVE STUDY WITH SMOTE-BASED CLASS BALANCING AND HYPERPARAMETER OPTIMIZATION