AUTHOR=Su Zhaodong , Cao Junxing , Xiang Tao , Fu Jingcheng , Shi Shaochen 

TITLE=Seismic prediction of porosity in tight reservoirs based on transformer

JOURNAL=Frontiers in Earth Science

VOLUME=Volume 11 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/earth-science/articles/10.3389/feart.2023.1137645

DOI=10.3389/feart.2023.1137645

ISSN=2296-6463

ABSTRACT=Porosity is a crucial index in reservoir evaluation. The porosity of tight reservoirs is small, the seismic response of porosity changes is feeble, and the relationship is complicated, which makes the porosity inversion prediction accuracy of tight reservoirs based on seismic low. This paper proposes a Transformer-based seismic multi-attribute inversion prediction method for tight reservoir porosity. The method takes preferred multiple seismic attributes as input data and porosity as output data. The Transformer mapping transformation network consists of an encoder, a multi-head attention layer, and a decoder and is optimized for training with a gating mechanism and a variable selection module. Applying the method proposed in this paper to the actual data of a tight sandstone gas exploration area in the Sichuan Basin, the obtained porosity prediction results have a coincidence rate of 95% with the well data.