The captivating vastness of our oceans and their intriguing phenomena warrant further exploration and beckon us to venture into the maritime realms. As we delve into oceanography, we gain profound insights and encounter intricate challenges. First, we will need observe the ocean with a variety of sensors, devices, systems and technology. Then we need to understand the perceived data, together with numerical simulations and other data analysis methods. Finally, we explore the ocean so that humans can benefit from the ocean with engineering technology. With the advancement of artificial intelligence (AI) technology, our understanding of marine phenomena and exploration of the ocean is evolving. The integration of AI technologies, such as machine learning and data analytics, is revolutionizing how we study the oceans. These intelligent systems can process vast amounts of oceanographic data, identifying patterns and correlations once unobtainable. Niu et al. (2023) reviewed the advances of machine learning in underwater acoustics in recent years, including source localization, target recognition, communication, and geoacoustic inversion. The generative digital twin ocean architecture was systematically proposed by Chen et al. ( 2023a) ranging from real-time data pools to key technologies to proofof-concept applications. Specifically, the key components of a digital twin ocean prototype system included data pool, artificial intelligence oceanographic model, and three-dimensional visualization interactions. Chen et al. (2023b) provided a comprehensive overview of the principles, methodologies, applications, and prospect of oceanic lidar remote sensing, emphasizing the different mechanism in system design as well as data processing algorithms and their applications in the remote sensing of oceanic environmental parameters. An underwater visual feature matching method based on attenuation invariance was proposed by Yu et al. (2023). The approach could improve the accuracy of underwater visual feature matching. And the Multiple Water Types (MWT) dataset and the Underwater Image Feature Descriptor (UIFD) evaluation dataset were set to compensate for the lack of an underwater visual feature matching evaluation dataset. Gu et al. (2023) refined the connotation and advantages of underwater computational imaging technology, especially in combination with highly complex and non-linear application scenarios, and sorted out potential development space and breakthroughs. This capability accelerates our insights into marine systems and unlocks novel avenues for interdisciplinary research. These endeavors underscore the pivotal role that intelligent marine technology and systems (IMTS) must assume in sha** the scientific landscape of the twenty-first century. However, the pace of progress in this domain falls short of expectations, leaving an enormous void, specifically in comprehensive academic journals encompassing various disciplines.

As we navigate the evolving landscape of marine science and technology, the fusion of AI and oceanic exploration holds immense promise. Specifically, AI-driven simulations and models enable us to simulate complex oceanic interactions with unprecedented accuracy. The predictive power of these models allows us to anticipate the behavior of oceans under different scenarios, aiding in disaster preparedness, climate change mitigation, and sustainable resource management. It propels us toward a future where we unravel the mysteries of the oceans, address pressing global challenges, and inspire a new generation of researchers and innovators. A new method based on object detection and point regression models was proposed by Dong et al. (2023) to locate fish keypoints. The proposed method could effectively detect underwater fish individuals, and accurately estimated the keypoints. It could not only improve fish detection efficiency and health monitoring, but also optimize aquaculture management and profit. Jiang et al. (2023) described in detail the application status of ocean color satellite (HY-1), ocean dynamics satellite (HY-2) and ocean observation and monitoring satellite (GF-3) in ocean parameter inversion, target identification and detection, ocean early warning and forecasting. Cui et al. (2023) summarized the research status of underwater robots, focused on the research status of underwater bionic robots with different materials, structures, and motion modes, analyzed the propulsion mechanism of different underwater robots, the control strategies adopted in the propulsion process of underwater robots, and the problems existing in the research and development. Based on the open source program OpenFOAM, the influence of wall roughness on the performance of centrifugal dredge pump was studied by Liang et al. (2023) using the wall function method and the equivalent sand roughness model. And k-omega SST turbulence model was used to calculate the steady state of the dredge pump under 10 different wall roughness. Zhang et al. (2023) investigated the scour profile, the scour hole depth, the deposition mound height and their positions produced by the propeller and ducted propeller varying over time. Meanwhile, the relationship between the max deposition mound position and the max scour hole depth was analysed. Besides, they used scour classic formula to fit scour data on time scale. This symbiotic relationship between the mesmerizing oceans and innovative AI reshapes the horizons of possibility and propels humanity toward a more enlightened understanding of our maritime world.

The field of marine sciences faces a growing repertoire of intricate challenges that will not unravel under solitary disciplinary efforts. Thus, the solution we propose is fostering collaborative synergies born out of cross-disciplinary studies, particularly marine science and AI. A shining example is the ENSO spring predictability barrier breakthrough, thanks to investigations involving neural networks. Similarly, understanding the roles of deep learning in predicting marine phenomena enriches our grasp of marine environmental sciences. Our newly launched journal provides a conduit for such impactful, cross-disciplinary explorations.

Enter 'Intelligent Marine Technology and Systems', a pioneering platform that unveils breakthroughs and theories in marine environmental sensing, ocean big data, marine AI, and marine equipment and applications. Although its focus is on the intersection of technological innovation and marine science, the journal’s scope transcends conventional boundaries. Moreover, their collaborative effort between esteemed institutions—the Ocean University of China and the Laoshan National Laboratory—is published under the banner of Springer Nature. The sponsors have pledged to cover all fees, including those for Open Access to articles published before 2025. To ensure the journal’s success, we have harnessed the expertise of 37 editors, most of whom are prolific researchers (with nearly one-half representing international perspectives), alongside a resolute trio of full-time professional editors.

The future of IMTS holds immense promise for sustainable ocean development and global security. By addressing the challenges posed by climate change, adopting integrated development management practices, harnessing big data and digital technologies, and exploring environmental sensing and AI, we can enhance the resilience and productivity of the oceans. Furthermore, with concerted efforts and investments in research and innovation, we can pave the way for a future where intelligent marine systems play a vital role in sustainable development and global security for generations to come. Collectively, we are proud to introduce IMTS, the first comprehensive high-level international academic journal in the field of intelligent marine science. With our international editorial board and strong support from the academic sponsors and Springer Nature, we warmly welcome you to collaborate with us to make IMTS a leading platform for discoveries and innovations in the field.