GMAC: A Geant4-based Monte Carlo Automated computational platform for developing nuclear tool digital twins

Nuclear technology is widely used for hydrocarbon exploration by deploying nuclear tools of detection to help obtain important parameters of a given geographical formation. Monte Carlo software is generally used to simulate nuclear tools in the environment of well logging, to accurately predict their responses downhole. In other words, a digital Monte Carlo twin of the designated tool is constructed, and its responses, are used to identify features that are important, for instance, for assessing the feasibility of deployment of the tool or optimizing the design of its hardware. However, the downhole environment is complex and changeable, such that it is determined by many parameters, e.g., the formation, the fluid, and the structure of the well. A significant modeling setup is thus often required to be able to consider all environmental variations, where this increases the burden on field engineers who need to construct several batches of repetitive models to simulate the same tool in a variety of environments. The appropriate automation of this process is thus highly desirable. In this work, the authors propose downhole Geant4-based Monte Carlo Automated Computational Platform (GMAC) to develop digital twins of nuclear tools. We construct a platform that enables us to design a Monte Carlo digital twin of a given nuclear tool. GMAC can automate the process of simulating the tool under various environments based on minimum user input and provide a comprehensive evaluation of its performance. The proposed platform also provides feasible means to optimize the tool by connecting the CAE twin directly to the Monte Carlo twin. The main structure and developer/user functions of the GMAC are discussed in detail. Three examples of nuclear tools are also provided to detail and verify its complete process from tool design to application. The results confirm the correctness and efficiency of the proposed computational platform.