1. State Key Laboratory of Nuclear Resources and Environment, East China University of Technology, Nanchang, Jiangxi,330013, China
2. National Key Laboratory of Uranium Resources Exploration-Mining and Nuclear Remote Sensing East China University of Technology, Nanchang, Jiangxi, 330013, China
3. No.1 Oil Production Plant, Changqing Oilfi eld Company, PetroChina, Yan’an, Shanxi, 716000, China
4. Aribore Survey and Remote Sensing Center of Nuclear Industry, Shijiazhuang, Hebei, 050002, China
Abstract Seismic attributes encapsulate substantial reservoir characterization information and can eff ectively support reservoir prediction. Given the high-dimensional nonlinear between sandbodies and seismic attributes,this study employs the RFECV method for seismic attribute selection, inputting the optimized attributes into a LightGBM model to enhance spatial delineation of sandbody identifi cation. By constructing training datasets based on optimized seismic attributes and well logs, followed by class imbalance correction as input variables for machine learning models, with sandbody probability as the output variable, and employing grid search to optimize model parameters, a high-precision sandbody prediction model was established. Taking the 3D seismic data of Block F3 in the North Sea of Holland as an example, this method successfully depicted the three-dimensional spatial distribution of target formation sandstones. The results indicate that even under strong noise conditions, the multi-attribute sandbody identifi cation method based on LightGBM eff ectively characterizes the distribution features of sandbodies. Compared to unselected attributes, the prediction results using selected attributes have higher vertical resolution and inter-well conformity, with the prediction accuracy for single wells reaching 80.77%, significantly improving the accuracy of sandbody boundary delineation.
Fund: This study was co-funded by the China National Nuclear Corporation-State Key Laboratory of Nuclear Resources and Environment (East China University of Technology) Joint Innovation Fund Project (No. 2023NRE-LH-08), the Natural Science Foundation of Jiangxi Province, China (No. 20252BAC240270), the Funding of National Key Laboratory of Uranium Resources Exploration-Mining and Nuclear Remote Sensing (2025QZ-YZZ-08), and the National Major Science and Technology Project on Deep Earth of China (No.2024ZD1003300).
About author: Teng-fei Ren, Master's student, graduated from Shandong Jianzhu University with a Bachelor of Engineering degree in 2022. He is currently a master's student in the School of Geophysics and Space Exploration at East China University of Technology. His research focuses on seismic attribute analysis and sandbody identification.
Cite this article:
. A Seismic Multi-Attribute Sandbody Identification Method Based on the LightGBM-RFECV Coupling Algorithm[J]. APPLIED GEOPHYSICS, 2025, 22(3): 757-769.
2025, Vol. 22 
