Inter-well reservoir parameter prediction based on LSTM-Attention network and sedimentary microfacies

The essence of predicting inter-well reservoir parameters is to find the distribution pattern of these parameters in three-dimensional space, which is closely related to the distribution of sedimentary microfacies. Existing research on neural network-based prediction of reservoir parameters can be divided into two directions: vertical and horizontal. The former predicts the logging curves of individual wells, while the latter predicts average data points between wells. However, there is a lack of research on prediction methods for logging curves inter-wells within the entire three-dimensional space. This paper aims to incorporate geological conceptual information, such as sedimentary microfacies, into the spatial prediction of reservoir parameters, and to study the prediction method of well-logging curves, taking porosity as an example. The goal is to achieve the effect of obtaining a predicted well-log porosity curve for a designated location in the study area by inputting spatial coordinates and sedimentary microfacies information. The research method combines the Long Short-Term Memory (LSTM) network and Attention Mechanism, uses real logging data for experiments, conducts multi-method comparisons, discusses the impact of sedimentary microfacies and different neural network methods on the prediction effect of inter-well reservoir parameters, and carries out generalization experiments of the method in new areas. The experimental results show that the research method is effective and can achieve the purpose of describing the spatial distribution of reservoir parameters and guiding geological exploration and development work.