A deep learning-based tree pruning evaluation system is proposed in this study, which integrates hyperspectral images, sensor data, and expert system rules. The system aims to enhance the accuracy and robustness of tree pruning tasks through multimodal data fusion and online learning strategies. Various models, including Mask R-CNN, SegNet, Tiny-Segformer, Box2Mask, CS-Net, SVM, MLP, and Random Forest, were used in the experiments to perform tree segmentation and pruning evaluation, with comprehensive performance assessments conducted. The experimental results demonstrate that the proposed model excels in the tree segmentation task, achieving a precision of 0.94, recall of 0.90, F1 score of 0.92, and mAP@50 and mAP@75 of 0.91 and 0.90, respectively, outperforming other comparative models. These results confirm the effectiveness of multimodal data fusion and dynamic optimization strategies in improving the accuracy of tree pruning evaluation. The experiments also highlight the critical role of sensor data in pruning evaluation, particularly when combined with the online learning strategy, as the model can progressively optimize pruning decisions and adapt to environmental changes. Through this work, the potential and prospects of the deep learning-based tree pruning evaluation system in practical applications are demonstrated.

Seed varietal purity and physiological viability are critical determinants of crop yield and quality. However, non-destructive assessment faces significant challenges in fine-grained variety discrimination and the perception of internal defects. This study proposes S3-Net, an AI-driven multimodal sensing framework that integrates vision–language alignment with dual-spectral sensor fusion for autonomous seed quality evaluation. We introduce a Knowledge–Vision Alignment (KVA) module that incorporates encyclopedic morphological descriptions to guide feature learning, significantly enhancing few-shot generalization. Complementarily, a Dual-Spectral Fusion (DSF) module combines high-resolution RGB textures with penetrative Short-Wave Infrared (SWIR) sensing to jointly characterize external and internal traits. Experimental results on a custom multimodal dataset of 6000 samples across 12 crop categories demonstrate that S3-Net achieves 96.9% accuracy for species identification and 95.8% for viability detection. Notably, S3-Net outperforms ResNet-50 by 40.3% in extreme 1-shot scenarios. With a stable inference throughput of 95 fps, the system meets the high-throughput demands of industrial-scale applications, providing a robust and efficient solution for intelligent agricultural phenotyping.

To address prevalent challenges in field-based wheat pest recognition—namely, viewpoint perturbations, sample scarcity, and heterogeneous data distributions—a pest identification framework named CropCLR-Wheat is proposed, which integrates self-supervised contrastive learning with an attention-enhanced mechanism. By incorporating a viewpoint-invariant feature encoder and a diffusion-based feature filtering module, the model significantly enhances pest damage localization and feature consistency, enabling high-accuracy recognition under limited-sample conditions. In 5-shot classification tasks, CropCLR-Wheat achieves a precision of 89.4%, a recall of 87.1%, and an accuracy of 88.2%; these metrics further improve to 92.3%, 90.5%, and 91.2%, respectively, under the 10-shot setting. In the semantic segmentation of wheat pest damage regions, the model attains a mean intersection over union (mIoU) of 82.7%, with precision and recall reaching 85.2% and 82.4%, respectively, markedly outperforming advanced models such as SegFormer and Mask R-CNN. In robustness evaluation under viewpoint disturbances, a prediction consistency rate of 88.7%, a confidence variation of only 7.8%, and a prediction consistency score (PCS) of 0.914 are recorded, indicating strong stability and adaptability. Deployment results further demonstrate the framework’s practical viability: on the Jetson Nano device, an inference latency of 84 ms, a frame rate of 11.9 FPS, and an accuracy of 88.2% are achieved. These results confirm the efficiency of the proposed approach in edge computing environments. By balancing generalization performance with deployability, the proposed method provides robust support for intelligent agricultural terminal systems and holds substantial potential for wide-scale application.