This study addresses the challenges in large-scale unmanned aerial vehicle (UAV) clusters, specifically the scalability issues and limitations of using reactive routing protocols for inter-cluster routing. These traditional methods place an excessive burden on cluster heads and struggle to adapt to frequently changing topologies, leading to decreased network performance. To solve these problems, we propose an innovative inter-cluster routing protocol (ICRP), which is based on a hybrid ant colony algorithm. During the route establishment phase, ICRP uses this algorithm to identify the optimal relay node. This approach is inspired by the foraging behavior of Physarum polycephalum, combining factors such as the number of hops from the source node, the load condition of the node, and its weight in the pheromone calculation. In the route maintenance phase, ICRP uses a predictive repair and contraction mechanism to dynamically maintain routes, accommodating the high mobility of UAVs. Comparative simulations in OMNeT + + showed that this protocol surpasses ad-hoc on-demand distance vector (AODV), fuzzy-logic-assisted-AODV, and Enhanced-Ant-AODV routing protocols in packet delivery rate and end-to-end transmission delay. Furthermore, it showed superior adaptation to network environments with high-speed node mobility.

The extensive application of unmanned aerial vehicle (UAV) technology has increased academic interest in object detection algorithms for UAV images. Nevertheless, these algorithms present issues such as low accuracy, inadequate stability, and insufficient pre-training model utilization. Therefore, a high-quality object detection method based on a performance-improved object detection baseline and pretraining algorithm is proposed. To fully extract global and local feature information, a hybrid backbone based on the combination of convolutional neural network (CNN) and vision transformer (ViT) is constructed using an excellent object detection method as the baseline network for feature extraction. This backbone is then combined with a more stable and generalizable optimizer to obtain high-quality object detection results. Because the domain gap between natural and UAV aerial photography scenes hinders the application of mainstream pre-training models to downstream UAV image object detection tasks, this study applies the masked image modeling (MIM) method to aerospace remote sensing datasets with a lower volume than mainstream natural scene datasets to produce a pre-training model for the proposed method and further improve UAV image object detection accuracy. Experimental results for two UAV imagery datasets show that the proposed method achieves better object detection performance compared to state-of-the-art (SOTA) methods with fewer pre-training datasets and parameters.

To solve the problem of collaborative search mission planning (CSMP) for a heterogeneous unmanned aerial vehicle (UAV) swarm for dynamic targets, this paper proposes a new CSMP scheme for a heterogeneous UAV swarm. First, a new polar coordinate system motion method is used to establish the UAV motion model and decision input solution model, which effectively solves the path‐unified coding problem of a heterogeneous UAV swarm. Then, in the mission area, a dynamically updated multisearch situation map model is established. Finally, to improve the global searching capability of a UAV, an improved path optimization algorithm PSO‐Rolling Horizon Control (PSO‐RHC) is designed. Multiple Monte Carlo simulations are performed for three time‐sensitive moving target types and three constraint types. The simulation results show that the task execution efficiency indexes of the proposed scheme for the decision input solution model, pheromone update mechanism, and optimization algorithm are improved by 188%, 72%, and 102%, respectively, and the overall performance is improved by 227%.

Net ecosystem productivity (NEP) is a crucial parameter for assessing the carbon cycle dynamics in terrestrial ecosystems. This study analyzed the spatial and temporal evolution characteristics and future trends of NEP in Henan Province over the past 20 years based on MOD17A3HGF, meteorological, and land-use data, employing the frequency counting method, trend test, Hurst index, and the center of gravity model. Various areas of changes in vegetation carbon sequestration were explored, and the driving factors were quantitatively assessed through correlation analysis, Sankey diagrams, and Geodetector. The results demonstrate that: 1) Continuous temporal changes in NEP in Henan, with annual average values fluctuating between 272.84 and 451.39 gC·m^-2·a¹, exhibiting an overall upward trend. 2) Spatially, there is a distinct distribution of NEP, concentrating more in the south and less in the north. While the study area generally experiences a dominant gradual enhancement of vegetation carbon sequestration capacity, the middle and north of Zhengzhou City exhibit a significant decline, which is expected to persist in the future. The migration of the centers of gravity of NEP over the past 20 years is characterized by stage-specific differentiation. 3) Among the various land cover types, forests have the strongest carbon sequestration capacity; however, cropland emerges as the province’s main source of NEP due to its extensive size. 4) The driving factors for spatial differentiation in NEP exhibit some temporal variability. Overall, climate factors and atmospheric pollution exert stronger influences, with the interactive explanatory power of the two-factor interaction being higher than that of the single factor. The results of this study can serve as a scientific theoretical basis for ecological policy-making and sustainable development in Henan Province.

Multispectral image reconstruction, which aims to recover a three-dimensional (3D) spatial–spectral signal from a two-dimensional measurement in a spectral camera based on ghost imaging via sparsity constraint (GISC), has been attracting much attention recently. However, faced with abundant 3D spectral data, the reconstruction quality cannot meet the visual requirements. Based on the robust data processing capability of deep learning, a novel network called SSTU-Net3+ is constructed by improving U-Net3+ with a spatial–spectral transformer (SST). To enhance the feature representation of images during reconstruction, mixed pooling modules and new convolution processes are proposed to improve the performance of the encoder and decoder, with U-Net3+ as the backbone. To boost the quality of reconstructed images, with split and concatenate (Concat) operations, we construct SST modules by exploiting both spatial and spectral correlations of multispectral images to refine the spatial and spectral features. Furthermore, we employ the SST in the decoder to reconstruct the desired 3D cube. Given similar network parameters, experiments on GISC spectral imaging data show that, compared to convolutional neural network–based methods, the average peak signal-to-noise ratio of images reconstructed using SSTU-Net3+ is improved by 3%, the structural similarity is enhanced by 3%, and the spectral angle mapping is cut by 12%. Particularly, compared to differential ghost imaging and compressed sensing, the reconstruction quality of SSTU-Net3+ has been significantly improved. SSTU-Net3+ can process a large amount of 3D multispectral image data more efficiently and construct the target image more accurately than the abovementioned methods.