In a groundbreaking development poised to revolutionize the energy sector, researchers have unveiled a novel approach to seismic data interpretation that promises to enhance the accuracy of subsurface imaging and resource estimation. Led by Ming Ma from the Institute of Hydrogeology and Environmental Geology at the Chinese Academy of Geological Sciences, this innovative method focuses on the attenuation characteristics and wave impedance inversion of depth-domain nonstationary seismic data.
The study, published in *Meitian dizhi yu kantan* (which translates to *Modern Geophysics and Exploration*), addresses a critical gap in current seismic interpretation techniques. Traditional methods often overlook the changes in amplitude and phase of seismic waves as they travel through different geological layers, leading to inaccuracies in depth-domain interpretations. “Previous studies have primarily focused on the reduction in dominant wavenumber and waveform stretching with increasing depth, but they have not adequately considered the amplitude and phase changes,” Ma explains. “Our research aims to fill this void by accurately characterizing the waveforms of nonstationary seismic signals in the depth domain and improving the precision of impedance inversion.”
The research introduces a complex mapping relationship between nonstationary seismic reflected waves and formation impedance, incorporating a Q model that reflects the absorption attenuation of strata for seismic waves. This model allows for a more comprehensive description of amplitude attenuation, phase distortion, and the decrease in the primary wavenumber of seismic waves. By leveraging deep learning technology, the study estimates the Q model for strata, employing a multi-head self-attention mechanism to extract accurate attenuation characteristics of depth-domain seismic signals. “We abandoned the assumption of a known Q model in conventional inversion processes,” Ma notes. “Instead, we used synthetic data for network training and validation, making the estimation method more practical and efficient.”
The implications for the energy sector are substantial. Accurate impedance inversion is crucial for identifying and evaluating subsurface resources, such as oil, gas, and coal deposits. The high-resolution absolute impedance data volume determined through this method provides a more reliable basis for decision-making in exploration and production activities. “Our results demonstrate that deep-domain nonstationary seismic inversion technology can capture the physical property parameters of subsurface media more intuitively and accurately,” Ma states. “This technology avoids the instability caused by multiple processing steps, such as inverse Q filtering and recursive inversion, leading to more consistent and reliable results.”
Validation using the Pluto model showed that the Q model and nonstationary inversion achieved through deep learning technology yielded a relative error in impedance of 13.7%, a significant improvement over conventional stationary inversion, which had an error rate of 48.2%. Field tests in the Jinzhong coalfield further confirmed the method’s effectiveness, with the impedance determined using this technology showing a high similarity of 0.9488 to the impedance curve based on log data.
This research not only enhances the accuracy of seismic interpretation but also paves the way for future developments in the field. By integrating advanced deep learning techniques with seismic data analysis, the study opens new avenues for improving the efficiency and reliability of subsurface imaging. As the energy sector continues to evolve, such innovations will be instrumental in meeting the growing demand for accurate resource estimation and sustainable exploration practices.
In summary, Ming Ma’s research represents a significant leap forward in seismic data interpretation, offering a more precise and reliable method for understanding the subsurface. The commercial impacts for the energy sector are profound, with potential applications ranging from enhanced resource estimation to improved exploration strategies. As the industry continues to embrace advanced technologies, this study serves as a testament to the power of innovation in driving progress and shaping the future of energy exploration.