In the rapid development of marine aquaculture, the water quality of aquatic environments is regarded as a main limiting factor. Therefore, it is necessary to assess the water quality and environmental conditions in marine aquaculture areas and find out the main influencing factors regarding damage to the water quality environment. In the present research, pond aquaculture and cage aquaculture areas were sampled in May, August and November in 2018. Nine water quality indicators were detected, including pH, temperature, salinity, dissolved oxygen, molybdate-reactive phosphorus, chemical oxygen demand, chlorophyll a, inorganic nitrogen and antibiotic resistance genes (ARGs). Principal component analysis (PCA) was used to analyze the water quality conditions, spatial–temporal changes, and the driving factors in pond and cage aquaculture areas. The results showed that three main components were extracted from the pond aquaculture area, which explained 66.82% of the results, the most relevant factors are salinity, dissolved oxygen and ARGs. For the cage aquaculture area, three main components were extracted which can account for 72.99% of the results, the most relevant factors are chlorophyll a, salinity and dissolved oxygen. The comprehensive scores of the principal components indicated that the heaviest polluted months in pond and aquaculture areas were August and November, respectively. The water quality of the pond aquaculture area is mainly limited by the volume of the pond, while aquaculture activities and seasonality are the main factors for cage aquaculture. ARGs in cage culture areas showed more variety and frequency compared with pond culture areas, which indicated that terrestrial input might be one of the sources for ARGs occurrence. The results would be helpful for the relevant authorities to select water quality monitoring parameters in marine aquaculture areas.

Dynamic job shop scheduling (DJSS) demands real-time adaptability under unpredictable conditions such as sudden job arrivals, equipment failures, and fluctuating demands. Traditional scheduling approaches—though foundational—often fall short when faced with rapid changes and high computational complexity. Recent developments in artificial intelligence (AI), especially reinforcement learning (RL), offer powerful alternatives by continuously refining scheduling policies through interaction with live shop-floor data. This review systematically examines AI-driven scheduling methods, highlighting how evolutionary heuristics, advanced machine learning, and RL-based algorithms each address the demands of modern manufacturing. Emphasis is placed on RL’s capacity to cope with large state spaces, handle continuous or discrete control, and integrate domain heuristics for more robust real-time decision-making. Despite these advances, challenges remain in algorithm scalability, interpretability, data availability, and standardization of performance metrics. Future directions point toward leveraging digital twins, quantum computing, hybrid models, and explainable RL to ensure more resilient, transparent, and scalable solutions. By illuminating both current achievements and persistent gaps, this review underscores the transformative potential of RL in dynamic scheduling and highlights actionable steps for broader industrial adoption.