Machine Learning Application of Core and Log Prediction in Various Depositional Environment Case Studies

Abstract

Abstract Conventional methods of acquiring log and core often exposes project owners to high cost and time-consuming operation. Other than that, massive data availability in different platforms are also persistent issue waiting to be resolved. Artificial Intelligent module of well log artificial intelligent prediction module named Enhanced Resource Monetization Artificial Intelligent (ERMAI) and physical core artificial intelligent prediction module named Core Artificial Intelligent (COREAI) are developed to eliminate expensive operation, factor out human biasness, enable prediction of core data and log data at any depth and all data are kept in structural corporate database. Overall approach presents innovation and agile technologies that integrate data management, data quality assessment and predictive machine learning to maximize the company asset value using existing core and well log data. The development of machine learning algorithms identifies potential outliers, benchmark the valuable data against the current industry standards, increases the confidence in data quality and avoids augmented error in predicting reservoir properties. For core prediction using CatBoost algorithm machine learning methods by combining digital raw data with core photo. And for log prediction using random forest assemble learning methods which using certain training wells for massive prediction.