Reservoir horizontal principle stress prediction using intelligent fusion model based on physical model constraints: a case study of Daji Block, Eastern Ordos Basin, North China

Abstract

Horizontal principal stress is a fundamental parameter for reservoir reconstruction of oil and gas wells. For improving single well productivity, accurate evaluation of reservoir stress characteristics is of great importance. One of the main challenges in studying the magnitude of the in situ stress is how to obtain the rock mechanical parameters accurately. In order to solve the problem that conventional methods are not very accurate at predicting the rock mechanical parameters of complex lithology reservoirs, taking transitional shale reservoir rocks as the research object, an intelligent fusion model was proposed to predict rock mechanical parameters. Machine learning algorithms such as the nearest neighbor regression, support vector machine, and random forest were selected to construct intelligent fusion models of different rock mechanics parameters based on the laboratory test data. Finally, the logging profile of transitional reservoir horizontal principal stress in the study area was obtained, under the constraints of the empirical physical model and measured in situ stress data. The results showed that the fusion models have better performance on rock mechanics parameters than the single model and have better accuracy in both training and test sets, which meet the engineering requirements showing accuracy in predicting the horizontal principal stress in the study area.