Cotton is a vital economic crop in global agriculture and the textile industry, contributing significantly to food security, industrial competitiveness, and sustainable development. Traditional technologies such as spectral imaging and machine learning improved cotton cultivation and processing, yet their performance often falls short in complex agricultural environments. Deep learning (DL), with its superior capabilities in data analysis, pattern recognition, and autonomous decision-making, offers transformative potential across the cotton value chain. This review highlights DL applications in seed quality assessment, pest and disease detection, intelligent irrigation, autonomous harvesting, and fiber classification et al. DL enhances accuracy, efficiency, and adaptability, promoting the modernization of cotton production and precision agriculture. However, challenges remain, including limited model generalization, high computational demands, environmental adaptability issues, and costly data annotation. Future research should prioritize lightweight, robust models, standardized multi-source datasets, and real-time performance optimization. Integrating multi-modal data—such as remote sensing, weather, and soil information—can further boost decision-making. Addressing these challenges will enable DL to play a central role in driving intelligent, automated, and sustainable transformation in the cotton industry.

This review comprehensively examines the application of deep learning technologies across the entire soybean production chain, encompassing areas such as disease and pest identification, weed detection, crop phenotype recognition, yield prediction, and intelligent operations. By systematically analyzing mainstream deep learning models, optimization strategies (e.g., model lightweighting, transfer learning), and sensor data fusion techniques, the review identifies their roles and performances in complex agricultural environments. It also highlights key challenges including data quality limitations, difficulties in real-world deployment, and the lack of standardized evaluation benchmarks. In response, promising directions such as reinforcement learning, self-supervised learning, interpretable AI, and multi-source data fusion are proposed. Specifically for soybean automation, future advancements are expected in areas such as high-precision disease and weed localization, real-time decision-making for variable-rate spraying and harvesting, and the integration of deep learning with robotics and edge computing to enable autonomous field operations. This review provides valuable insights and future prospects for promoting intelligent, efficient, and sustainable development in soybean production through deep learning.

We introduce a holographic model that exhibits a coexistence state of the Weyl semimetal and the topological nodal line state, providing us with a valuable tool to investigate the system’s behavior in the strong coupling regime. Nine types of bulk solutions exhibiting different IR behaviors have been identified, corresponding to nine different types of boundary states. These nine states include four distinct phases, namely the Weyl-nodal phase, the gap-nodal phase, the Weyl gap phase and the gap-gap phase, four phase boundaries, which are the Weyl-Dirac phase, the gap-Dirac phase, the Dirac-gap phase and the Dirac-nodal phase, and finally a double critical point. A phase diagram is plotted that exhibits qualitative similarity to the one obtained in the weak coupling limit. The anomalous Hall conductivity, which serves as an order parameter, and the free energy are calculated, with the latter showing the continuity of the topological phase transitions within the system. Our study highlights the similarities and differences in such a topological system between the weak and strong coupling regimes, paving the way for further experimental observations.