Multi-Task Deep Learning Seismic Impedance Inversion Optimization Based on Homoscedastic Uncertainty

Abstract

Seismic inversion is a process to obtain the spatial structure and physical properties of underground rock formations using surface acquired seismic data, constrained by known geological laws and drilling and logging data. The principle of seismic inversion based on deep learning is to learn the mapping between seismic data and rock properties by training a neural network using logging data as labels. However, due to high cost, the number of logging curves is often limited, leading to a trained model with poor generalization. Multi-task learning (MTL) provides an effective way to mitigate this problem. Learning multiple related tasks at the same time can improve the generalization ability of the model, thereby improving the performance of the main task on the same amount of labeled data. However, the performance of multi-task learning is highly dependent on the relative weights for the loss of each task, and manual tuning of the weights is often time-consuming and laborious. In this paper, a Fully Convolutional Residual Network (FCRN) is proposed to achieve seismic impedance inversion and seismic data reconstruction simultaneously, and a method based on the homoscedastic uncertainty of the Bayesian model is used to balance the weights of the loss function for the two tasks. The test results on the synthetic datasets of Marmousi2, Overthrust, and Volve field data show that the proposed method can automatically determine the optimal weight of the two tasks, and predicts impedance with higher accuracy than single-task FCRN model.

Transformer and Convolutional Hybrid Neural Network for Seismic Impedance Inversion

“…In this paper, the relative weight factor λ in the loss function is selected through ablation experiments, and cannot be guaranteed the optimal. In this regard, it can be improved to use some methods such as homescedic uncertainty [18] and gradient normalization [49] to treat the λ as a trainable parameter. Second, we conduct anti-noise tests about the networks.…”

Deep carbonate fault–karst reservoir characterization by multi‐task learning

“…Many researchers have applied MTL to solve practical geophysical problems such as seismic image processing (Wu, Liang, Shi, Geng, et al, 2019), P/S wave separation and reverse time migration for vertical seismic profiling (VSP) (Y. Wei et al, 2020), super-resolution of seismic velocity model (Li et al, 2020), seismic structural curvature volume extraction (Ao et al, 2020) and seismic inversion (Meng et al, 2022;Zheng et al, 2022).…”

“…In addition, training data are insufficient to train an accurate network, and the shared training data and parameters of MTL play a role in data augmentation (Y. Zhang & Yang, 2021). Many researchers have applied MTL to solve practical geophysical problems such as seismic image processing (Wu, Liang, Shi, Geng, et al., 2019), P/S wave separation and reverse time migration for vertical seismic profiling (VSP) (Y. Wei et al., 2020), super‐resolution of seismic velocity model (Li et al., 2020), seismic structural curvature volume extraction (Ao et al., 2020) and seismic inversion (Meng et al., 2022; Wang, Wang, et al., 2021; Zheng et al., 2022).…”

Seismic Elastic Parameter Inversion via a FCRN and GRU Hybrid Network with Multi-Task Learning

“…Multi-task learning aims to empower the network to concurrently learn multiple tasks, enhance the generalization ability by leveraging diverse data from each task to extract more reliable features [38], improve the performances of individual tasks, and mitigate overfitting. Due to the interconnection between seismic data and elastic parameters [39], it is advantageous to integrate multi-task learning into the multi-parameter inversion of seismic data [40][41][42][43][44]. In the multi-task network, multiple tasks utilize a shared representation simultaneously.…”