A deep learning framework based on improved self-supervised learning for ground-penetrating radar tunnel lining inspection

It is not practical to obtain a large number of labeled data to train a supervised learning network in tunnel lining nondestructive testing with ground-penetrating radar (GPR). To decrease the dependence of supervised learning on the number of labeled data, an improved self-supervised learning algorithm—self-attention dense contrastive...

An Introduction to the Application of Marine Controlled-Source Electromagnetic Methods for Natural Gas Hydrate Exploration

Natural gas hydrates have been an unconventional source of energy since the beginning of this century. Gas-hydrate-filled reservoirs show higher resistivity values compared with water-filled sediments. Their presence can be detected using marine controlled-source electromagnetic methods. We classify acquisition configurations into stationary and...

The feasibility of csem monitoring in gas hydrate production of the range of porosity and saturation

Natural gas hydrates production tests over the last two decades has sown that production is not without risks. Indirect effects in the sedimentary rocks of phase changes are changes in porosity, permeability, and saturation. From a field production test site, porosity changes in the range of 15% to 19% and saturation from 5% to 60% were...