Fahad Iqbal Syed

Hydraulic fracturing is one of the revolutionary technologies widely applied to develop tight hydrocarbon reservoirs. Moreover, hydraulic fracture design optimization is an essential step to optimize production from tight reservoirs. This study presents the implementation of three new socio-inspired algorithms on hydraulic fracturing optimization. The work integrates reservoir simulation, artificial neural networks, and preceding optimization algorithms to attain the optimized fractures. For this study, a tight gas production dataset is initially generated numerically for a defined set of the fracture half-length, fracture height, fracture width, fracture conductivity, and the number of fractures’ values. Secondly, the generated dataset is trained through a neural network to predict the effects of preceding parameters on gas production. Lastly, three new socio-inspired algorithms including cohort intelligence (CI), multi-cohort intelligence (multi-CI), and teaching learning-based optimization (TLBO) are applied to the regressor output to obtain optimized gas production performance with the combination of optimum fracture design parameters. The results are then compared with the traditionally used optimizers including particle swarm optimization (PSO) and genetic algorithm (GA). The results demonstrated that the multi-CI and TLBO converge at the global best position more often with a success rate of at least 95% as compared to CI, PSO, and GA. Moreover, the CI, PSO, and GA are found to stuck many times at the local maximum. This concludes that the multi-CI and TLBO are good alternatives to PSO and GA considering their high performance in determining the optimum fracture design parameters in comparison.

Shale gas reservoirs are contributing a major role in overall hydrocarbon production, especially in the United States, and due to the intense development of such reservoirs, it is a must thing to learn the productive methods for modeling production and performance evaluation. Consequently, one of the most adopted techniques these days for the sake of production performance analysis is the utilization of artificial intelligence (AI) and machine learning (ML). Hydrocarbon exploration and production is a continuous process that brings a lot of data from sub-surface as well as from the surface facilities. Availability of such a huge data set that keeps on increasing over time enhances the computational capabilities and performance accuracy through AI and ML applications using a data-driven approach. The ML approach can be utilized through supervised and unsupervised methods in addition to artificial neural networks (ANN). Other ML approaches include random forest (RF), support vector machine (SVM), boosting technique, clustering methods, and artificial network-based architecture, etc. In this paper, a systematic literature review is presented focused on the AI and ML applications for the shale gas production performance evaluation and their modeling.