Seismic interpretation is a fundamental approach for obtaining static and dynamic information about subsurface reservoirs, such as geological faults/salt bodies and associated fluid types and distribution. Due to the exponential growth in seismic data volume and considerable uncertainty in manual interpretation, deep learning (DL) algorithms have been introduced to assist seismic interpretation. Our investigation of the trained neural networks suggests that they underperform on seismic data with different noise characteristics. One of the main issues is that the noise patterns of seismic data are highly inconsistent due to many factors, including geological features, sampling parameters and human intervention. To address this problem, we propose a noise pattern transfer (NPT) framework to transfer or remove seismic noise style between datasets by treating noise patterns as styles of image, which can also improve the generality of automatic seismic interpretation algorithms. Extensive experiments on three synthetic datasets and two field seismic datasets demonstrate the promising performance of our proposed NPT approach. Pairs of clean and stylised seismic data are generated by extending the use of the neural style transfer algorithm beyond the artistic domain. We then demonstrate how our method achieves superior noise pattern transferability between datasets and denoising performance on field datasets. Associated improvements in accuracy and generalisation of the neural network-based fault recognition tasks successfully demonstrate the practicality of our NPT approach. The source code is made publicly available online at https://github.com/Magnomic/nptcode.

Design of the interfacial properties is a significant fundamental issue in the field of composite materials. Much attention has been paid to the improvement of the interface strength, while there has been a little work concerning the mechanical design of the interface for fiber-reinforced polymers (FRPs) in which the fiber is transversely isotropic thanks to its orientation feature. Based on the conception of neutral inclusion and imperfect interface conditions, the interface parameters are obtained for the FRPs by using Kolosov constant. We demonstrate the effect of the thermal residual stresses on the neutrality for FRPs in this paper. If the interface has the properties of design parameters without consideration of thermal stress, the presence of thermal residual stress/strain would break the neutrality in the cases of equal-biaxial tension and pure shear. In particular, the neutral fiber does not exist unless the thermal stress is eliminated in the equal-biaxial tension. In the case of uniaxial tension, the neutral fiber does not exist in absence of thermal stress, while the neutrality would become possible by properly controlling the thermal residual stress. Because the large thermal residual stress will result in the formation of cracks in matrix, a trade-off design is necessary between the neutrality and the initiation of matrix cracking.

No abstract