Application of machine learning in hydraulic fracture optimization

Abstract The subject of artificial intelligence (AI) in general and application of machine learning (ML) has gained lots of popularity in the past few years throughout various industries. This rise in popularity is due to new technologies such as sensors and high-performance computing services (e.g., Apache Hadoop, NoSQL, etc.) that enable big-data acquisition and storage in different fields of study. Big data refers to a quantity of data that is too large to be handled (i.e., gathered, stored, and analyzed) using common tools and techniques, for example, Terabytes of data. In the oil and gas industry, in addition to pressure, rate, and surface and downhole seismic measurements, we are now able to collect information using fiber optics that provide high-resolution temperature and acoustic measurements in time and space. The oil and gas industry has also collected large amounts of data corresponding to evaluation, drilling, completion, stimulation, and operation of the wells. This valuable and expensive data has not been studied and analyzed in detail, simply due to the lack of knowledge and the complexity of the data collected. The application of AI in the oil and gas industry, using different data mining and ML techniques, has enabled us to use this information not only to optimize drilling, completions, stimulation, and operation procedures but also to make real-time decisions to avoid any failure or malfunction, that is, real-time operation center or RTOC. The application of AI will empower our industry to take advantage of new technologies developed in industrial monitoring systems such as sensor technologies, high-performance computing, and use our current and previously collected data to increase the NPV of different projects.