This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Open AccessArticle
Seismic Waveform Feature Extraction and Reservoir Prediction Based on CNN and UMAP: A Case Study of the Ordos Basin
by
Lifu Zheng
Lifu Zheng
Lifu Zheng received his Bachelor's Degree in Geophysics from the Institute of Disaster Prevention in [...]
Lifu Zheng received his Bachelor's Degree in Geophysics from the Institute of Disaster Prevention in 2014, and is now pursuing Master's Degree in Earth Exploration and Information Technology. He is working as a Senior Engineer at the Beijing Earthquake Agency. His research topics mainly include machine learning and deep learning, seismic data interpretation, and seismic disaster loss assessment.
1,2,
Hao Yang
Hao Yang 1,* and
Guichun Luo
Guichun Luo 2
1
Research Institute of Petroleum Exploration and Development, China National Petroleum Corporation, Beijing 100083, China
2
Beijing Earthquake Agency, Beijing 100080, China
*
Author to whom correspondence should be addressed.
Appl. Sci. 2025, 15(13), 7377; https://doi.org/10.3390/app15137377 (registering DOI)
Submission received: 18 May 2025
/
Revised: 17 June 2025
/
Accepted: 26 June 2025
/
Published: 30 June 2025
Abstract
Seismic waveform feature extraction is a critical task in seismic exploration, as it directly impacts reservoir prediction and geological interpretation. However, large-scale seismic data and nonlinear relationships between seismic signals and reservoir properties are challenging for traditional machine learning methods. To address these limitations, this paper proposes a novel framework combining Convolutional Neural Network (CNN) and Uniform Manifold Approximation and Projection (UMAP) for seismic waveform feature extraction and analysis. The UMAP-CNN framework leverages the strengths of manifold learning and deep learning, enabling multi-scale feature extraction and dimensionality reduction while preserving both local and global data structures. The evaluation experiments, which considered runtime, receiver operating characteristic (ROC) curves, embedding distribution maps, and other quantitative assessments, illustrated that the UMAP-CNN outperformed t-distributed stochastic neighbor embedding (t-SNE), locally linear embedding (LLE) and isometric feature mapping (Isomap). A case study in the Ordos Basin further demonstrated that UMAP-CNN offers a high degree of accuracy in predicting coal seam thickness. Furthermore, our framework exhibited superior computational efficiency and robustness in handling large-scale datasets.
Share and Cite
MDPI and ACS Style
Zheng, L.; Yang, H.; Luo, G.
Seismic Waveform Feature Extraction and Reservoir Prediction Based on CNN and UMAP: A Case Study of the Ordos Basin. Appl. Sci. 2025, 15, 7377.
https://doi.org/10.3390/app15137377
AMA Style
Zheng L, Yang H, Luo G.
Seismic Waveform Feature Extraction and Reservoir Prediction Based on CNN and UMAP: A Case Study of the Ordos Basin. Applied Sciences. 2025; 15(13):7377.
https://doi.org/10.3390/app15137377
Chicago/Turabian Style
Zheng, Lifu, Hao Yang, and Guichun Luo.
2025. "Seismic Waveform Feature Extraction and Reservoir Prediction Based on CNN and UMAP: A Case Study of the Ordos Basin" Applied Sciences 15, no. 13: 7377.
https://doi.org/10.3390/app15137377
APA Style
Zheng, L., Yang, H., & Luo, G.
(2025). Seismic Waveform Feature Extraction and Reservoir Prediction Based on CNN and UMAP: A Case Study of the Ordos Basin. Applied Sciences, 15(13), 7377.
https://doi.org/10.3390/app15137377
Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details
here.
Article Metrics
Article Access Statistics
For more information on the journal statistics, click
here.
Multiple requests from the same IP address are counted as one view.