Article · Applied Computing and Geosciences · July 2, 2025
Natural fracture network model using Gaussian simulation and machine learning algorithms
Timur Merembayev, Yerlan Amanbek
Abstract
In this paper, a fracture network model is proposed to enhance the understanding of subsurface fracture characterization. The model combines geostatistical methods such as sequential indicators and Gaussian simulations. The model uses data from natural faults in Kazakhstan to predict the segment, azimuth, and length of fractures in unknown areas. The model is validated by comparing the simulated fracture networks with the original fracture data and by hiding some regions within the fracture network. The results show that the geostatistical methods perform better than the machine learning algorithm for azimuth prediction, while the machine learning algorithm performs better for length prediction. In addition, the validation of the fracture network model is conducted by comparing the production curve profiles in the tracer test setting. They are in good agreement.
More by Timur Merembayev
- Reliable Learning-Enabled Multi-Robot Coverage with Masked Entity-Attention MAPPO: A Controlled Multi-Seed StudyAI · 2026
- COMPARATIVE EVALUATION OF SEMANTIC SEGMENTATION MODELS FOR CRACK DETECTIONScientific Journal of Astana IT University · 2026
- Mathematical Modeling to Optimize Sensor Performance for Enhanced Sensitivity and Measurement Accuracy in a Biogas PlantPreprints.org · 2026
- Deep Learning Approaches for Autoregressive Fracture Network Path Prediction: A Comprehensive Study on the Teapot Dome DatasetIEEE Access · 2026