Search

SUMMARY: Due to the strong heterogeneity of the reservoir, it is difficult to extend the classical reservoir parameter prediction model to the new work area. Traditional geological methods rely on experience, while machine learning algorithms lack consideration of reservoir heterogeneity. This makes it impossible for these methods to achieve good predictive performance in new work areas. In this paper, we discuss designing a multilayer deep transfer learning network (MDTL). The network enables accurate prediction of reservoir parameters in new areas based on core and logging data from mature areas. For the architectural design, we establish a network structure that realizes data interaction in different work areas. For network parameter optimization, we design a multilayer maximum mean discrepancy loss function. It guides network training to learn feature knowledge about data in different work areas. For logging data processing, we explore a support vector machine method to remove abnormal noise in logging data. We apply MDTL to predict shale gas porosity and total organic carbon content in southern Sichuan. Compared to state-of-the-art reservoir parameter prediction models, MDTL achieves the best performance in new well areas. The network integrates the idea of multilayer transfer learning, reduces the influence of reservoir heterogeneity and effectively ensures the prediction accuracy. [ABSTRACT FROM AUTHOR]

Due to the diversity of pore types, it is challenging to characterize the Middle East's Cretaceous carbonate reservoir or accurately predict its petrophysical properties. In this paper, pore structure in the reservoir is first classified using a comprehensive method. Then, based on the identified pore structure types, a new permeability model with high prediction precision is established. The reservoir is dominated by 6 pore types, such as intergrain pores and moldic pores, and 6 rock types. Grainstone, algal packstone, algal wackestone, and foraminifera wackestone are porous rock types, and echinoderm wackestone and mudstone are nonporous rock types. The types of pore structure in the study area can be divided into four types. Type I has midhigh porosity and medium-high permeability due to its large throat, while type II has a fine throat type with midhigh porosity and midpermeability. Due to their isolated pores, the permeability is low in types III and IV, and out of these two, type III has better storage capacity. Movable fluid saturation calculated by the spectral coefficient method and r apex can characterize the boundary between the connected pores and unconnected pores very well in the research area. It is not accurate enough to simply classify the pore structure by permeability and porosity. The combination of porosity, permeability, r apex , flow zone indicator, and the reservoir quality index can effectively distinguish and classify pore structure types in noncoring wells. The characteristics of each pore structure type are consistent with those of the fractal dimension, which thereby proves the effectiveness of the pore structure classification. New permeability prediction models are proposed for different pore structure types, and good prediction results have been obtained. This study is of great significance for enhancing oil recovery. [ABSTRACT FROM AUTHOR]