Ensuring the integrity of wells is fundamental to safe oil and gas production, geothermal energy development, and geological carbon storage. At the heart of well integrity lies cement bonding, which isolates subsurface formations and prevents hazardous fluid migration. Against this backdrop, a team of researchers from China conducted a comprehensive
review of recent advancements in cement bond quality assessment based on ultrasonic measurements.
"Ultrasonic logging has become a powerful non-destructive tools for evaluating cement bond quality behind casing, offering high-resolution insight into both the casing–cement and cement–formation interfaces," shares lead author Prof. Hua Wang, a professor at University of Electronic Science and Technology of China. "Over the past decade, ultrasonic pulse-echo and pitch-catch techniques have advanced cement bond evaluation."
Recent advances in ultrasonic well logging include:
- Automated waveform quality control using variational autoencoders; simultaneous inversion of borehole-fluid and cement acoustic impedance;
- Suppression of casing reflections via phase-shift interpolation and F–K transforms; joint inversion of tool trajectory and borehole properties under eccentric conditions; separation of A0 and S0 modes using variational mode decomposition;
- Machine-learning-based enhancement and arrival-time picking for TIE waveforms; and
- Imaging of the cement annulus–formation interface.
"These approaches have been validated using synthetic simulations, full-scale physical experiments, and field case studies, demonstrating robustness across varied borehole environments and well conditions," says co-author Meng Li, an associate professor at Xi'an Shiyou University. "Machine learning further increases reliability and automation, particularly in complex wavefields and low signal-to-noise settings."
By bridging physics-based modeling with data-driven approaches, this review presents a pathway toward more reliable, scalable, and intelligent ultrasonic cement evaluation—an essential step for meeting increasingly stringent integrity requirements in energy transition applications such as carbon capture and storage.
###
References
DOI
10.1016/j.aiig.2025.100170
Original Source URL
https://doi.org/10.1016/j.aiig.2025.100170
Funding information
This research is supported by a National Natural Science Foundation of China (Grant numbers 42474167, 41974150, 42174158, and W2522002) and Natural Science Basic Research Program of Shaanxi (2023-JC-YB-220), the Shenzhen Science and Technology Program (grant numbers JCYJ20230807120007015 and RCJC20231211 085916003).
About Artificial Intelligence in Geosciences
Artificial Intelligence in Geosciences is an open access journal providing an interdisciplinary forum where ideas and solutions related to artificial intelligence and its applications in geosciences can be shared and discussed. To support this discussion, we encourage authors to open source their code, data, and the labels used in AI.