Seawater intrusion is a global environmental issue, and seawater intrusion monitoring requires a multidisciplinary approach to improve accuracy. The seawater/freshwater interface simplified models in coastal aquifers are generally divided into two types: abrupt interface model and wedge-shaped interface model. Electrical resistivity tomography (ERT) is the visualization of the subsurface resistivity distribution in 2D or 3D, which have been widely used in the seawater intrusion monitoring. This paper presented a geoelectrical recognition model to classify the simplified seawater/freshwater interface types in the process of seawater intrusion based on Convolutional Neural Network (CNN). The seawater intrusion laboratory experiments were carried out to simulate the process of seawater intrusion caused by water level of seawater rise or the water level of freshwater drop, and the ERT method was carried out to monitor the resistivity of the aquifer during the experiments, and the geoelectrical recognition model was used to classify the interface types. The results showed that the ERT method offered a fast and non-destructive approach for monitoring seawater intrusion, and the accurate recognition results of interface types were obtained using the well-trained recognition model in the laboratory experiments.