Intelligent Drilling and Completion: A Review

Application of Machine Learning in Energy Systems – a Comparative Analysis of Three Case Studies

“…There are numerous algorithms which have been used in the different papers analyzed by Li et al 2022 [7] (cf. Figure 5) but among those only five algorithms are highly utilized in most of the fields, which are Artificial Neural Networks (ANN), Random Forests (RF), Support Vector Machine (SVM), Particle swarm optimization (PSO) and Genetic algorithms (GA) (cf.…”

“…Table 1). These five commonly used algorithms are defined by us based on the repetition and total usage count not less than 10 times across the whole research fields in Li et al 2022 [7]. Overall, ANNs define the by far most widely used approach and the usage of ANNs is popular in most fields (cf.…”

“…Figure 6). Table 1: Research fields and number of the five most commonly used algorithms in each of these for the analyzed papers from Li et al [7].…”

“…Year completion technologies using machine learning has shown potential to improve the drilling process's efficiency and accuracy [7]. Our study builds upon the comprehensive literature review conducted by Li et al [7] and strives to offer insights into the particular domains of drilling where machine learning can be applied, as well as the types of algorithms that can be leveraged for specific tasks to enhance efficiency [7]. Li et al 2022 [7] cite a total of 160 papers, include a number 137 in their analysis over the research fields (cf.…”

“…Our study builds upon the comprehensive literature review conducted by Li et al [7] and strives to offer insights into the particular domains of drilling where machine learning can be applied, as well as the types of algorithms that can be leveraged for specific tasks to enhance efficiency [7]. Li et al 2022 [7] cite a total of 160 papers, include a number 137 in their analysis over the research fields (cf. Table 1), from which we further analyze 124 while excluding papers where machine learning is not used.…”