Permeability extraction from multiple well logs using particle swarm optimization based factor analysis

Abstract In this paper, we present an innovative factor analysis algorithm for hydrocarbon exploration to estimate the intrinsic permeability of reservoir rocks from well logs. Unlike conventional evaluation methods that employ a single or limited number data types, process simultaneously all available derive first statistical and relate it by regression analysis. For solving problem analysis, introduce improved particle swarm optimization method, which searches global minimum distance between observed calculated gives quick estimation scores. The learning factors intelligent computational technique such as cognitive social constants are specified hyperparameters using simulated annealing heuristic hyperparameter estimator. Instead arbitrary fixation these hyperparameters, refine them in iterative give reliable both formation permeability. estimated parameters consistent with literature recommendations. We demonstrate feasibility proposed well-log method Hungarian oilfield study involving open-hole wireline logs core data. determine spatial distribution along borehole more wells approach, serves efficient multivariate tool advanced modeling.