A method for predicting oil and gas charging by superimposing ancient and modern structures

By constructing a method for predicting oil and gas injection by combining ancient and modern structures, and by using multiple models and data integration techniques, the deviation problem in oil and gas injection prediction in complex structural areas has been solved, achieving high-precision prediction of oil and gas reservoirs and improving exploration efficiency.

CN120949351BActive Publication Date: 2026-06-09YANAN UNIV
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
YANAN UNIV
Filing Date
2025-09-05
Publication Date
2026-06-09

AI Technical Summary

Technical Problem

Traditional exploration methods struggle to accurately predict oil and gas injection points in complex structural areas. Current structural highs may shift due to later tectonic alteration, causing oil and gas injection points to deviate from their targets. Furthermore, conventional seismic imaging techniques face challenges such as low signal-to-noise ratio, difficulty in structural identification, and poor reservoir prediction accuracy.

Method used

A three-dimensional geological model base was constructed using high-precision seismic data, well stratigraphic data, and paleomagnetic dating results. The current tectonic contour map was generated by combining random forest algorithm and Monte Carlo simulation to reconstruct the thermal-fluid-solid coupled evolution history of the basin. The LSTM+Attention model was used to identify the tectonic transformation periods. The spatiotemporal evolution of erosion was inverted by integrating apatite fission tracks and (U-Th)/He thermochronological data. The Transformer-CGAN model was constructed to generate the probability distribution of sand bodies. The SHAP algorithm was applied to analyze the contribution of reservoir-controlling factors. The uncertainty was reduced by updating the model through Bayesian method to generate a three-dimensional probability volume of favorable target areas.

Benefits of technology

It achieves precise spatiotemporal matching of ancient and modern structural high points, significantly improves the success rate of oil and gas drilling, solves the problem of traditional exploration target deviation, and improves the accuracy of oil and gas reservoir prediction and exploration efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120949351B_ABST
    Figure CN120949351B_ABST
Patent Text Reader

Abstract

This invention discloses a method for predicting hydrocarbon charging based on the superposition of ancient and modern structures, comprising the following steps: Step 1: Outputting a current structural contour map and an uncertainty thermogram that combine spatial accuracy and uncertainty quantification; Step 2: Constructing a structural change index to quantify the destruction / preservation weights of each phase on the trap; Step 3: Integrating apatite fission track and (U-Th) / He thermochronological data to output a paleostructural contour map with error distribution and a paleoriver probability field; Step 4: Generating a three-dimensional volume of sand body probability distribution, coupling a digital core pore network model to simulate the critical threshold for hydrocarbon charging, and generating a sand body connectivity index map to constrain the distribution of high-quality reservoirs; Step 5: Superimposing multiple parameters in the superposition area of ​​ancient and modern structural high points, applying the SHAP algorithm to analyze the contribution of reservoir-controlling elements to focus on the main controlling factors and lock in favorable target areas for hydrocarbon enrichment; Step 6: Generating a three-dimensional probability volume of favorable target areas and combining it with an economic evaluation module to generate an exploration priority ranking.
Need to check novelty before this filing date? Find Prior Art