Accurate sea surface temperature (SST) forcasting is essential for ocean monitoring, especially during extreme weather events when air-sea interactions intensify. This study introduces TCN-PatchTST, an enhanced variant of PachTST, utilizing observations from four buoys around Taiwan for 72-hour SST forecasting. The results indicate that TCN-PatchTST consistently outperforms physical and data-driven baselines, including HYCOM, XGBoost, LSTM and the standard PatchTST in terms of prediction accuracy and demonstrates greater stability during extreme weather conditions. Additionally, SHAP analysis interprets the main factors influencing SST variability. Findings suggest that this multivariable approach significantly improves the reliability of SST forecasts across varying environmental conditions.
In recent years, the fields of artificial intelligence and information technology have undergone rapid and transformative development. Technologies such as machine learning, image recognition, image generation, and big data analytics are now widely integrated into environmental monitoring applications. A critical question emerges: How can these innovative technologies be leveraged to address the persistent challenges facing the management of Marine Protected Areas (MPAs), thereby ushering in a new era of intelligent governance? This paper, focusing on the case of Taiwan's Chaojing marine protected area, identifies current management issues and proposes a suite of intelligent technology tools. These include the use of artificial intelligence (AI) for the automated analysis of coral reef bleaching and for monitoring the activity of indicator fish species to assess conservation efficacy. Furthermore, the integration of coastal surveillance and aerial drones can enhance environmental monitoring by identifying diver numbers, marine pollution, and illegal fishing activities. Ultimately, by empowering marine citizen scientists, this approach has the potential to reshape Taiwan's marine ecotourism industry, fostering broader public participation in marine conservation. This study provides a context-dependent and modular framework that is transferable to marine protected areas with comparable institutional capacity and technological infrastructure.
