This study focuses on the application of electrical resistivity tomography (ERT) for monitoring the growth process of CO₂ hydrate in subsea carbon sequestration, aiming to provide technical support for the safety assessment of marine carbon storage. By designing single-target, dual-target, and multi-target hydrate samples, convolutional neural networks (CNNs), recurrent neural networks (RNNs), and residual neural networks (ResNets) were constructed and compared with traditional image reconstruction algorithms (e.g., back-projection) to quantitatively analyze ERT imaging accuracy. The experiments used boundary voltage as the input and internal conductivity distribution as the output, employing the relative image error (RIE) and image correlation coefficient (ICC) to evaluate algorithmic performance. The results demonstrate that neural network algorithms—particularly RNNs—exhibit superior performance compared to traditional image reconstruction methods due to their strong noise resistance and nonlinear mapping capabilities. These algorithms significantly improve the edge clarity in target identification, enabling the precise capture of the hydrate distribution during carbon sequestration. This advancement effectively enhances the monitoring capability of CO₂ hydrate reservoir characteristics and provides reliable data support for the safety assessment of hydrate reservoirs.