KNN IN ACTION: MAPPING THE FUTURE OF OIL WITH PREDICTIVE CLASSIFICATION TECHNIQUES

Abstract

The development of a robust reservoir potential evaluation system is a pivotal task in the advanced stages of reservoir exploitation. Such a system aids researchers in the precise identification of remaining oil potential areas and the implementation of targeted development strategies. Several factors have been proposed by previous researchers for the establishment of an accurate evaluation system. In this context, Siqi Ouyang et al. have favorably suggested porosity, permeability, and contained saturation as primary evaluation indicators, derived from the division of flow unit parameters [1]. Yichao Zhang et al. have introduced a novel quantitative characterization method for remaining oil, which involves three dimensions: the remaining oil reservoir field, hydrodynamic field, and flow relationship field [2]. Lijie Liu et al. have devised a comprehensive index for the classification and evaluation of remaining oil, utilizing criteria such as geological reserve abundance, remaining oil geological reserve abundance, and movable remaining oil drive efficiency [3]. It is worth noting that the current research trend largely revolves around obtaining geological static evaluations from initial geological data. There is a notable absence of development dynamic indicators within the evaluation system.