With the rapid progress of big data and artificial intelligence, machine learning technologies such as learning and adaptive control have emerged as a research focus in petroleum engineering. They have various applications in oilfield development, such as parameter prediction, optimization scheme deployment, and performance evaluation. This paper provides a comprehensive review of these applications in three key scenarios of petroleum engineering, namely hydraulic fracturing and acidizing, chemical flooding and gas flooding, and water injection. This article first introduces the steps and methods of machine learning processing in these scenarios, then discusses the advantages, disadvantages, existing challenges, and future prospects of these machine learning methods. Furthermore, this article compares and contrasts the strengths and weaknesses of these machine learning methods, aiming to help researchers select and improve their methods. Finally, this paper identifies some potential development trends and research directions of machine learning in petroleum engineering based on the current issues.

Genetic algorithms (GAs) have been widely applied in Steiner tree optimization problems. However, as the core operation, existing crossover operators for tree-based GAs suffer from producing illegal offspring trees. Therefore, some global link information must be adopted to ensure the connectivity of the offspring, which incurs heavy computation. To address this problem, this article proposes a new crossover mechanism, called leaf crossover (LC), which generates legal offspring by just exchanging partial parent chromosomes, requiring neither the global network link information, encoding/decoding nor repair operations. Our simulation study indicates that GAs with LC outperform GAs with existing crossover mechanisms in terms of not only producing better solutions but also converging faster in networks of varying sizes.

Data imbalance is a common problem in most practical classification applications of machine learning, and it may lead to classification results that are biased towards the majority class if not dealt with properly. An effective means of solving this problem is undersampling in the borderline area; however, it is difficult to find the area that fits the classification boundary. In this paper, we present a novel undersampling framework, whereby the clustering of samples in the majority class is conducted and segmentation is then performed in the boundary area according to the clusters obtained; this enables a better shape that fits the classification boundary to be obtained via the performance of random sampling in the borderline area of these segments. In addition, we hypothesize that there exists an optimal number of classifiers to be integrated into the method of ensemble learning that utilizes multiple classifiers that have been obtained via sampling to promote the algorithm. After passing the hypothesis test, we apply the improved algorithm to the newly developed method. The experimental results show that the proposed method works well.