Next Article in Journal
A Similarity-Based Approach for Diagnosing the Aging of Lithium-Ion Batteries in Second Life Combining Time Series and Machine Learning
Previous Article in Journal
Evaluation of the Grading and Morphology of Recycled Asphalt Pavement Clusters Using the Emulsification–Separation Disposal Method
Previous Article in Special Issue
Hybrid Huff-n-Puff Process for Enhanced Oil Recovery: Integration of Surfactant Flooding with CO2 Oil Swelling
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

Seismic Waveform Feature Extraction and Reservoir Prediction Based on CNN and UMAP: A Case Study of the Ordos Basin

by
Lifu Zheng
1,2,
Hao Yang
1,* and
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
(This article belongs to the Special Issue Current Advances and Future Trend in Enhanced Oil Recovery)

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.
Keywords: Convolutional Neural Network; reservoir prediction; dimensionality reduction; seismic waveform analysis; Uniform Manifold Approximation and Projection Convolutional Neural Network; reservoir prediction; dimensionality reduction; seismic waveform analysis; Uniform Manifold Approximation and Projection

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

Back to TopTop