Deep oil and gas exploration has become a critical frontier in offshore oil and gas development due to growing global energy demand. However, traditional towed-streamer seismic acquisition often struggles to deliver high-resolution imaging of deep and structurally complex subsurface targets. A promising solution is to integrate towed-streamer data with ocean bottom node (OBN) data, which provide broader azimuthal coverage, full-offset sampling, and multi-component recording, thereby complementing streamer acquisition and enhancing image quality. Despite these advantages, conventional fusion methods—typically based on simple linear weighted averaging—are often inadequate for effectively combining the distinct characteristics of OBN and streamer images. Such approaches risk producing inappropriate subsurface representations. To address this limitation, this paper proposes a novel deep learning-based imaging enhancement strategy for the joint utilization of OBN and streamer seismic data in this paper. By leveraging the nonlinear representation capabilities of neural networks, the proposed method learns to adaptively extract and fuse complementary features from both datasets, yielding more coherent, high-resolution, and geologically consistent imaging results. This study begins with a comparative analysis of the imaging characteristics of streamer and OBN data, followed by the design of a tailored deep learning architecture for data fusion. Numerical experiments confirm the feasibility and robustness of the approach. The results demonstrate improved reflector continuity, amplitude fidelity, and structural clarity compared to conventional methods, especially in the complex cases, highlighting the method's potential for advancing subsurface imaging in deep oil and gas exploration scenarios.

Internal multiple suppression is a crucial and challenging task in seismic data processing, aiming to mitigate the impact of internal multiples on imaging and seismic interpretation. A major difficulty arises because internal multiples often overlap with primaries, particularly in complex geological settings, making their accurate suppression difficult. Conventional internal multiple elimination (IME) methods rely on adaptive subtraction, which may cause primary energy loss in regions where primaries and internal multiples overlap. To address this issue, this paper derives internal multiple suppression formulas based on the well-known feedback model from a novel perspective. On this basis, we propose a Closed-Loop Internal Multiple Elimination (CL-IME) method. By formulating a new objective function, the proposed CL-IME method accurately estimates and suppresses internal multiples through inversion, thereby avoiding the primary energy loss associated with adaptive subtraction. Numerical experiments demonstrate that CL-IME achieves significantly higher accuracy than conventional IME in suppressing internal multiples, particularly in regions where primaries and multiples strongly overlap, thereby providing a more reliable approach for seismic data processing in complex structural settings.