A deep-learning framework with seismic-frequency-band constraints for thin-reservoir characterization

Фреймворк глубокого обучения с ограничениями по частотной полосе сейсмических данных для характеристики тонких коллекторов
Hao Li, Fan Yang, Dongfeng Zhao, Guofa Li, Chunxiang Guo
2025-01-09

deep-learning frameworkgeophysical inversionseismic-frequency-band constraintsthin-layer sand bodiesthin-reservoir characterization
ABSTRACT The characterization of the spatial structures of thin-layer sand bodies is the foundation for detailed reservoir description and physical property estimation. This requires using the geophysical inversion technique to make full use of the subsurface sedimentation information found in well-logging and seismic data for comprehensive evaluation. However, the traditional model-based inversion method is limited by the frequency bandwidth of seismic data, and the resolution of the inversion results cannot meet the accuracy requirements of thin-layer reservoir characterization. In this paper, we introduce a convolutional model and seismic-frequency-band constraints into a deep-learning framework to create a high-resolution inversion framework under physical constraints and then test our technical scheme in the model and on field data. We construct a 3D thin-layer sand body model with specific geologic implications and carry out inversion tests based on sparse spike inversion, geostatistical inversion, and a deep-learning framework. The experimental results demonstrate the feasibility of the deep-learning framework and reveal its limitations in characterizing the spatial distribution of sand bodies. After introducing the convolutional model and seismic-frequency-band constraints, the inversion results more clearly distinguish the spatial distribution and superposition relationships of different sand bodies. The results obtained based on the field data fully confirm the effectiveness and applicability of our method.
1
A deep-learning inversion framework incorporates a convolutional model and seismic-frequency-band constraints to improve thin-reservoir characterization under physical constraints.
2
Adding the convolutional model and seismic-frequency-band constraints more clearly resolves the spatial distribution and superposition relationships of different sand bodies.
3
Field-data results confirm the method’s effectiveness and applicability for high-resolution thin-reservoir inversion.
4
Synthetic 3D thin-layer sand-body experiments compare sparse-spike inversion, geostatistical inversion, and the proposed deep-learning framework, demonstrating its feasibility.
5
Without the added constraints, the framework has limitations in accurately characterizing the spatial distribution of sand bodies.

thin-layer sand bodies (thin reservoirs) characterized from well-logging and seismic data

high-resolution spatial characterization and inversion of sand-body distribution and superposition relationships under seismic-frequency-band and physical constraints

Publication Details
Publication Date
2025-01-09
Journal
Publisher
ISSN
Cited by
1
Access Type
Author Information
Authors
Hao Li
Fan Yang
Dongfeng Zhao
Guofa Li
Chunxiang Guo
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%