Abstract
Well-logging is an important formation characterization and resource evaluation method in oil and gas exploration and development. However, there has been a shortage of well-logging data because Well-logging can only be measured by expensive and time-consuming field tests. In this study, we aimed to find effective machine learning techniques for well-logging data prediction, considering the temporal and spatial characteristics of well-logging data. To achieve this goal, the convolutional neural network (CNN) and the long short-term memory (LSTM) neural networks were combined to extract the spatial and temporal features of well-logging data, and the particle swarm optimization (PSO) algorithm was used to determine hyperparameters of the optimal CNN-LSTM architecture to predict logging curves in this study. We applied the proposed CNN-LSTM-PSO model, along with support vector regression, gradient-boosting regression, CNN-PSO, and LSTM-PSO models, to forecast photoelectric effect (PE) logs from other logs of the target well, and from logs of adjacent wells. Among the applied algorithms, the proposed CNN-LSTM-PSO model generated the best prediction of PE logs because it fully considers the spatio-temporal information of other well-logging curves. The prediction accuracy of the PE log using logs of the adjacent wells was not as good as that using the other well-logging data of the target well itself, due to geological uncertainties between the target well and adjacent wells. The results also show that the prediction accuracy of the models can be significantly improved with the PSO algorithm. The proposed CNN-LSTM-PSO model was found to enable reliable and efficient Well-logging prediction for existing and new drilled wells; further, as the reservoir complexity increases, the proxy model should be able to reduce the optimization time dramatically.
Highlights
Well-logging is the process of characterizing the variations in physical properties of formations, such as electromagnetic, acoustic, nuclear radiation, and thermal energy, with depth along a borehole using specialized instrumentation
We proposed a new neural network architecture that was composed of convolutional neural network (CNN) and long short-term memory (LSTM), which respectively extracts the temporal and spatial characteristics of well-logging data to predict the well logs of interest
We analyzed the application of artificial intelligence (AI) in well-logging curve reconstruction, and propose a logging prediction method based on the combination of CNN and LSTM with the particle swarm optimization (PSO) algorithm, taking into account the developmental trend of AI technology
Summary
Well-logging is the process of characterizing the variations in physical properties of formations, such as electromagnetic, acoustic, nuclear radiation, and thermal energy, with depth along a borehole using specialized instrumentation. More and more oilfield researchers are using deep learning techniques to predict different reservoir properties, such as permeability, porosity, and fluid saturation, from available well-logging data to reduce the cost of exploration and development. Researchers have proposed a series of algorithms with shallow-learning mechanisms [5,6,7]. These algorithms are only suitable for the application and theoretical analysis of specific-scale data, and their effect is not good for the application of large-sample data analysis or feature extraction from complex feature data. Deep learning can represent data feature information at multiple levels; it can automatically abstract high-dimensional data at different levels to accomplish specific tasks [9]
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have