Near Surface Geophysics - Volume 23, Issue 2, 2025

Climate change, decreased river flow and land subsidence lead to saltwater intrusion posing a significant threat to rice production in Vietnam's Mekong Delta (VMD), one of the world's largest rice exporting regions. Soil salinity in the VMD can be caused by saltwater intrusion into lowland areas through the canal system, or by capillary rise of water from the near surface saline water table, both resulting in salt accumulation in the top soil. Developing appropriate management strategies for adapting rice production systems of the VMD to climate change, both in terms of water and salinity management, requires characterizing and subsequently monitoring of the spatial distribution and temporal dynamics of salinity in the near‐surface aquifers underneath the rice producing area. The distribution of subsurface salinity was investigated using electrical resistivity tomography in the VMD's province, Tra Vinh, as a case study area. Soil salinity was measured for profiles of approximately 300 m length at 44 locations along geological transects in a case study area. Results show that saline water appears at a shallow depth, particularly along the coast and the lower reaches of rivers. Double‐cropped rice fields seem to be more susceptible to salinization via the near‐surface aquifer than other rice cropping systems. The study suggests that temporal fluctuations of the near‐surface aquifer and the dynamics of the exchange between the river and the shallow aquifer need to be investigated in future research.

The airborne transient electromagnetic method (ATEM), as a large‐scale and efficient geophysical exploration method, applies to exploration in areas with complex terrain and harsh environments. However, the ATEM method generates a large amount of data, which demonstrates a non‐linear relationship with the resistivity model. Additionally, the non‐uniqueness of the inversion problem further complicates the computational difficulty of the inversion problem. These problems raise the calculation cost of traditional inversion. Thus, our research group introduced an ATEM one‐dimensional inversion method based on a convolutional neural network (CNN) and gate recurrent unit (GRU). Specifically, the nonlinear relationship between the resistivity model and the electromagnetic response was obtained through the excellent nonlinear processing ability of the deep neural network. The test results suggest that this method had higher accuracy than the traditional shallow neural network inversion method. Compared with the traditional regularization inversion method, the deep learning method exhibited less dependence on the initial model and did not involve complex regularization parameter selection. It commonly needs to only train a large number of diverse data samples and can obtain an inversion result with high accuracy. After the deep neural network training was completed, ATEM field real‐time data were processed under the same hardware parameters. Additionally, the reliability of the CNN–GRU with field data was verified to confirm that the CNN–GRU deep neural network possessed good practicability. The test unveils that the inversion result of the deep neural network was close to the actual model, and the inversion accuracy was high. The one‐dimensional inversion results were combined to obtain the pseudo‐two‐dimensional inversion results, contributing to the improved visualization of inversion results.