Massive database generation for 2.5D borehole electromagnetic measurements using refined isogeometric analysis

• Published in: Computers & geosciences 2021-10, Vol.155, p.104808, Article 104808
• Main Authors: Hashemian, Ali, Garcia, Daniel, Rivera, Jon Ander, Pardo, David
• Format: Article
• Language: English
• Subjects: 2.5D numerical simulation; Borehole resistivity measurements; Deep learning inversion; Geosteering; Refined isogeometric analysis
• ISSN: 0098-3004; 1873-7803
• DOI: 10.1016/j.cageo.2021.104808

Borehole resistivity measurements are routinely inverted in real-time during geosteering operations. The inversion process can be efficiently performed with the help of advanced artificial intelligence algorithms such as deep learning. These methods require a massive dataset that relates multiple Earth models with the corresponding borehole resistivity measurements. In here, we propose to use an advanced numerical method — refined isogeometric analysis (rIGA) — to perform rapid and accurate 2.5D simulations and generate databases when considering arbitrary 2D Earth models. Numerical results show that we can generate a meaningful synthetic database composed of 100,000 Earth models with the corresponding measurements in 56 h using a workstation equipped with two CPUs. •We use rIGA discretizations for simulating 2.5D borehole electromagnetic measurements.•We generate a synthetic database as a preliminary stage for deep learning inversion.•Computational cost of rIGA is compared to that of IGA and FEA discretizations.•rIGA generates the database O(p) times faster than high-continuity IGA discretization.