Carbonate microfacies classification model based on dual neural network: a case study on the fourth member of the upper Ediacaran Dengying Formation in the Moxi gas field, Central Sichuan Basin

Abstract The dual neural network (DNNW) model combines two networks to imitate artificial sedimentary facies division by learning the characteristics of multi-type logging curves corresponding microfacies a coring section. predicts many non-coring wells in research zone through data. After comparing classification performance fully connected (FCNWW) and AutoML when dealing with three FNDA, EALS, HRA datasets, DNNW shows high stability assists exploration Moxi gas field. Four are identified thin section observation, including thrombolite boundstone (MF1), laminated stromatolite (MF2), siliceous laminar (MF3), micritic dolostone (MF4). Results suggest fourth member Dengying Formation field is carbonate platform deposition: specifically, restricted margin.