To enhance remote sensing for maritime safety and security, various sensors need to be integrated into a centralized maritime surveillance system (MSS). High-frequency (HF) radar systems are a type of mainstream technology widely used in international marine remote sensing and have great potential to detect distant sea surface targets due to their over-the-horizon (OTH) capability. However, effectively recognizing targets in spectra with intrinsic strong disturbance echoes and random environmental noise is still challenging. To avoid the above problem, this paper proposes an adaptive signal identification method to detect target signals based on a rapid and flexible threshold. By integrating a watershed segmentation algorithm, the subsequent direction result can be used to automatically compute the direction of arrival (DOA) of the targets. To assist in the orientation of the object, forward intersections are integrated with the technique. Hence, the proposed technique can effectively recognize vessel echoes with automatic identification system (AIS) verification. Experiments have demonstrated the promising feasibility of the proposed method’s performance.

A network of high-frequency radars (HFRs) has been deployed around Taiwan. The wide-area data coverage is dedicated to revealing near real-time sea-surface current information. This paper investigates three primary objectives: (1) describing the seasonal current synoptic variability; (2) determining the influence of wind forcing; (3) describing the tidal current field pattern and variability. Sea surface currents derived from HFR data include both geostrophic components and wind-driven components. This study explored vector complex correlations between the HFR time series and wind, which was sufficient to identify high-frequency components, including an Ekman balance among the surface currents and wind. Regarding the characteristics of mesoscale events and the tidal field, a year-long high-resolution surface dataset was utilized to observe the current–eddy–tide interactions over four seasons. The harmonic analysis results derived from surface currents off of northeastern Taiwan during 2013 are presented. The results agree well with the tidal parameters estimated from tide-gauge station observations. The analysis shows that this region features a strong, mixed, mainly semidiurnal tide. Continued monitoring by a variety of sensors (e.g., satellite and HFR) would improve the understanding of the circulation in the region.

A phase gradient (PG)-based algorithm is proposed in this study to determine coastal bathymetry from X-band radar images. Although local wavenumbers with the same spatial resolution of the wave field can be obtained from the wave field using the PG method, only a single wavenumber result can be extracted from each location theoretically. Due to the influence of unavoidable noise on the wave field image, single wavenumber estimation often shows high uncertainty. This study combines a bandpass filter and directional pass filter to produce different nearly monocomponent wave fields from X-band radar images and then estimates more wavenumbers from these wave fields using the PG method. However, the distributions of wavenumbers in higher-frequency bins still show high variance because the strength of wave signals is weak. We confirmed that the uncertain wavenumber–frequency pairs can be improved using the Kalman filter and are more consistent with the dispersion relation curve. To decrease the influence of inaccurate wavenumbers, we also use the strength of the wave signals as the weights for the least-squares fit. Although the depth errors from shallow-water areas are still unavoidable, we can remove the inaccurate depth estimation from shallow-water areas according to the coefficients of determination of the fitting. In summary, the algorithm proposed in this study can obtain a bathymetry map with high spatial resolution. In contrast to the depth result estimated using a single wavenumber of each frequency bin, we confirm that more wavenumbers from each of the frequency bins are helpful in fitting the dispersion relation curve and obtaining a more reliable depth result.

Expanding offshore wind energy introduces complex marine pollution liability challenges for specific emerging markets like Taiwan. Traditional static regulations often trigger administrative conflicts and struggle to adapt to dynamic stakeholder behaviors. This study develops an integrated socio-technical model combining evolutionary game theory (EGT) and system dynamics (SD) to analyze the strategic co-evolution between regulators and developers. The model is strictly calibrated using empirical data from Taiwan’s offshore wind sector to simulate various scenarios. Phase plane simulations reveal an “excess-liability paradox”. Crucially, the mathematical stability analysis identifies the intangible value of corporate reputation as the structural prerequisite for system convergence. Statutory penalties serve effectively as a complementary deterrent signal, but long-term stability requires normative shifts. We propose combining high statutory penalty deterrence with ESG-linked reputation mechanisms, providing a fundamental theoretical reference for emerging offshore wind markets facing similar initial regulatory and economic trade-offs.

Short-term coastal surface-current forecasts at forecast lead times ($\tau$ = 1–12 h) are critical for search and rescue (SAR), pollution response, and vessel routing. From a 2015–2019 archive of hourly CODAR high-frequency radar (HFR) observations off Southwestern Taiwan, we developed grid-point long short-term memory (LSTM) models using historical observations alone, without atmospheric forcing or data assimilation (training 2015–2017, validation 2018, test 2019). Because harmonic tides account for ~19% of the surface-current variance, we tested harmonic detiding under a matched architecture and tuning protocol, comparing a raw-input LSTM with a detided variant (LSTM-HA) that forecasts the detided residual and reconstructs the total current. In the out-of-sample 2019 test year ($\tau$ = 12 h), LSTM-HA ranked highest ($R$ = 0.768/0.729 for $u$/$v$) and reduced $RMSE$ by ~34% relative to Persistence; both LSTM configurations far exceeded HA-Persistence and tide-free HYCOM, and the LSTM-HA advantage was statistically significant and spatially pervasive. An independent single-drifter Lagrangian proof-of-concept (December 2020) gave 12 h mean separations of 8.52/9.20 km for LSTM/LSTM-HA, comparable to the HFR observations (9.26 km) and below HYCOM. For this tide-influenced focus area, the benefit of LSTM-HA emerges from approximately $\tau$ = 3 h and becomes most relevant over $\tau$ = 6–12 h. At $\tau$ = 1–3 h, the raw-input LSTM performs nearly equivalently while forecasting the total current directly. Broader seasonal validation, including monsoon and typhoon forcing, remains a priority.

Rip currents are a leading cause of coastal drowning accidents worldwide, yet their detection remains challenging due to their significant spatial variability and intermittent nature. While traditional in-situ methods provide high-fidelity but localized insights, optical imagery is often constrained by specific illumination and weather windows. To extend monitoring capabilities across broader areas and diverse environmental conditions, shore-based microwave radar offers a robust alternative. This study investigates the detection and characterization of rip current signatures using time-series microwave radar imagery, focusing on the development of an automated operational technology. Radar imagery captures the observed area by recording variations in backscatter intensity, which are primarily driven by wave breaking and surface roughness. In X-band radar, small-scale surface scatterers, such as breaking gravity waves, facilitate Bragg scattering, which is significantly modulated by rip current dynamics in the surf and outer surf zones.Our proposed framework adopts a two-stage approach. In the first stage, conventional image processing techniques, including temporal averaging and filtering, are employed to identify candidate rip current patterns from radar sequences. To enhance detection robustness and mitigate false alarms, the second stage introduces an artificial intelligence-based recognition model trained to discriminate rip current signatures from transient wave breaking and background noise. Comparative analyses demonstrate that this AI-assisted approach significantly improves detection consistency across varying sea states. By combining the physical interpretability of traditional image processing with the predictive power of AI, this framework enables near-real-time, continuous rip current monitoring. These results highlight the potential of intelligent microwave radar systems to support coastal safety applications, including early warning systems and real-time hazard mitigation.