Logging Data Completion Based on an MC-GAN-BiLSTM Model
Liang Guo, Luo Renze, Xingyu Li, Tuo Juanjuan, Canru Lei, Yang Zhou
Abstract
Due to environmental interference and operational errors, problems such as incomplete and random missing logging data have happened during the process of geophysical logging data collection. Since it is difficult to establish a geophysical model based on logging data and geological information, the data complementation effect of conventional methods is not very satisfactory. In this paper, we propose a GAN-LSTM model based on spatiotemporal sequence prediction. In the model, we adopt a generative adversarial network (GAN) as a network framework, and a long short-term memory (LSTM) neural network and a bi-directional long short-term memory (Bi-LSTM) as the basic modules. We use the LSTM instead of a fully-connected layer in the GAN to extract the potential information in the depth domain of the logging data. We complete the missing values of the logging data through an encoding-decoding structure that includes the Bi-LSTM. We use random missing values and consecutive missing values of logging data to simulate a data acquisition environment in the field and threshold control to simulate a processing environment in a laboratory for experiments. The experimental results show that the coefficient of determination (R2) of the GAN-LSTM model reaches 0.906 when 30% of random logging data are missing and 0.851 when 30% of consecutive logging data are missing. The effect of the model proposed in this paper is significantly higher than the commonly used random forest (RF), Sequence to Sequence (Seq2seq) and generative adversarial interpolation network (GAIN) models.