With the rising global demand for aquatic products, aquaculture has become a cornerstone of food security and sustainability. This review comprehensively analyzes the application of deep learning in sustainable aquaculture, covering key areas such as fish detection and counting, growth prediction and health monitoring, intelligent feeding systems, water quality forecasting, and behavioral and stress analysis. The study discusses the suitability of deep learning architectures, including CNNs, RNNs, GANs, Transformers, and MobileNet, under complex aquatic environments characterized by poor image quality and severe occlusion. It highlights ongoing challenges related to data scarcity, real-time performance, model generalization, and cross-domain adaptability. Looking forward, the paper outlines future research directions including multimodal data fusion, edge computing, lightweight model design, synthetic data generation, and digital twin-based virtual farming platforms. Deep learning is poised to drive aquaculture toward greater intelligence, efficiency, and sustainability.

Unmanned aerial vehicles (UAVs) are becoming an important platform for precision agriculture, supporting both high-throughput sensing and active field operations such as spraying, monitoring, and phenotyping. However, unlike general UAV applications, agricultural environments impose distinctive challenges due to heterogeneous field structures, canopy occlusion, terrain variation, dynamic disturbances, and strong coupling between navigation performance and task quality. To address this gap, this review presents a systematic analysis of UAV navigation in agricultural environments from a system-level perspective. The review first summarizes the core technical components of agricultural UAV navigation, including sensing, localization, mapping, planning, and control. It then discusses how navigation requirements vary across representative scenarios such as open fields, orchards, and terraced farmland, and examines their roles in key applications including aerial mapping, field monitoring, precision spraying, and close-range orchard operations. In addition, datasets, simulation platforms, and evaluation protocols relevant to agricultural UAV navigation are reviewed. Finally, major challenges are identified, including scene heterogeneity, perception degradation, insufficient task-semantic integration, limited control robustness, and the lack of standardized benchmarks. Future research should move toward robust, task-aware, and modular navigation architectures that support reliable and scalable agricultural UAV deployment.

Timely fish disease monitoring is an important requirement for sustainable aquaculture because disease outbreaks can reduce survival, increase treatment inputs, and destabilise production. In aquaponic systems, fish health is also linked to nutrient cycling and the stability of integrated fish–vegetable production, making automated fish-health perception a potentially useful component of resource-efficient farming. Existing classification and detection methods can identify disease categories or approximate lesion locations, but they provide limited information about lesion area, boundary shape, and severity-related spatial extent. This study presents a deep learning framework for pixel-level fish lesion segmentation to support sustainable aquaculture health monitoring, with aquaponic systems considered as a potential application context. The framework combines lesion-preserving frequency augmentation (LPFA), confidence-guided large-kernel encoding (CGLE), and confidence-filtered decoder refinement (CFDR). LPFA expands lesion appearance variation during training while retaining the main lesion layout. CGLE uses coarse prediction confidence to allocate broader contextual modelling to uncertain encoder regions, and CFDR applies selective decoder correction to low-confidence regions. A public freshwater fish disease dataset is reformulated into a dense prediction task with 1750 raw images from seven image-level categories, including six disease categories and one normal healthy category. The images are divided into training, validation, and test subsets at an 8:1:1 ratio, and controlled augmentation strategies are applied online rather than being used to create a larger static dataset. Across five random-seed runs, the proposed method achieves $82.6\pm 0.3$% mIoU, $90.9\pm 0.2$% mDice, and $73.5\pm 0.4$% Boundary IoU. Relative to TransUNet, the mean mIoU rises from $78.4\pm 0.4$% to $82.6\pm 0.3$%, and Boundary IoU rises from $68.8\pm 0.5$% to $73.5\pm 0.4$%, with paired bootstrap testing supporting the stability of the improvement. These results indicate its potential as a lesion-quantification decision-support component for smart and sustainable fish-production systems.