This paper aims to solve the limitations of traditional gravity physical property inversion methods such as insufficient depth resolution and difficulties in parameter selection, by proposing an improved 3D gravity inversion method based on deep learning. The deep learning network model is established using the fully convolutional U-net network. To enhance the generalization ability of the sample set, the large-scale training set and test set are generated by the random walk, based on the forward theory. Founded on the traditional loss function’s definition, this paper introduces an improvement incorporating a physical constraint to measure the degree of data fitting between the predicted and the real gravity data. This improvement significantly boosted the accuracy of the deep learning inversion method, as verified through both a single model and an intricate combination model. Finally, we applied this improved inversion method to the gravity data from the Gamburtsev Subglacial Mountains in the interior of East Antarctica, obtaining a comprehensive 3D crustal density structure. The results provide new evidence for the presence of a dense crustal root situated beneath the central Gamburtsev Province near the Gamburtsev Suture.

In shallow waters, the interpretation of the frequency-domain marine controlled-source electromagnetic (CSEM) data is challenging due to the airwave. The airwave dominates and will lead to misinterpretation of the data set. A differential-field approach is presented to attenuate the airwave for the shallow-water marine CSEM data. The difference of the fields between two consecutive receivers or source points is calculated and weighted by the geometric spreading related factor. By using differential fields, the detectability given by the field ratio between the models with and without the target is enhanced, which indicates that the impact of airwaves is suppressed.