Pathogen infection has greatly reduced crop production. As the symptoms of diseases usually appear when the plants are infected severely, rapid identification approaches are required to monitor plant diseases at early the infection stage and optimize control strategies. Hyperspectral imaging, as a fast and nondestructive sensing technology, has achieved remarkable results in plant disease identification. Various models have been developed for disease identification in different plants such as arable crops, vegetables, fruit trees, etc. In these models, important algorithms, such as the vegetation index and machine learning classification and methods have played significant roles in the detection and early warning of disease. In this paper, the principle of hyperspectral imaging technology and common spectral characteristics of plant disease symptoms are discussed. We reviewed the impact mechanism of pathogen infection on the photo response and spectrum features of the plants, the data processing tools and algorithms of the hyperspectral information of pathogen-infected plants, and the application prospect of hyperspectral imaging technology for the identification of plant diseases.

Weeds are among the major factors that could harm crop yield. Site-specific weed management has become an effective tool to control weed and machine vision combined with image processing is an effective approach for weed detection. In this work, an encoder-decoder deep learning network was investigated for pixel-wise semantic segmentation of crop and weed. Different input representations including different color space transformations and color indices were compared to optimize the input of the network. Three image enhancement methods were investigated to improve model robustness against different lighting conditions. The results show that for images without enhancement, color space transformation and vegetation indices without NIR (Near Infrared) information did not improve the segmentation results, while inclusion of NIR information significantly improved the segmentation accuracy, indicating the effectiveness of NIR information for precise segmentation under weak lighting condition. Image enhancement improved the image quality and consequently the robustness of segmentation models against different lighting conditions. The best MIoU value for pixel-wise segmentation was 88.91% and the best mean accuracy of object-wise segmentation was 96.12%. The deep network and image enhancement methods applied in this work provided promising segmentation results for weed detection and did not need large amount of data for model training, which is suitable for site-specific weed management.

Introduction: Development of weed and crop detection algorithms provides theoretical support for weed control and becomes an effective tool for the site-specific weed management. For weed and crop object detection tasks in the field, there is often a large difference between the number of weed and crop, resulting in an unbalanced distribution of samples and further posing difficulties for the detection task. In addition, most developed models tend to miss the small weed objects, leading to unsatisfied detection results. To overcome these issues, we proposed a pixel-level synthesization data augmentation method and a TIA-YOLOv5 network for weed and crop detection in the complex field environment.Methods: The pixel-level synthesization data augmentation method generated synthetic images by pasting weed pixels into original images. In the TIA-YOLOv5, a transformer encoder block was added to the backbone to improve the sensitivity of the model to weeds, a channel feature fusion with involution (CFFI) strategy was proposed for channel feature fusion while reducing information loss, and adaptive spatial feature fusion (ASFF) was introduced for feature fusion of different scales in the prediction head.Results: Test results with a publicly available sugarbeet dataset showed that the proposed TIA-YOLOv5 network yielded an F1-scoreweed, APweed and mAP@0.5 of 70.0%, 80.8% and 90.0%, respectively, which was 11.8%, 11.3% and 5.9% higher than the baseline YOLOv5 model. And the detection speed reached 20.8 FPS.Discussion: In this paper, a fast and accurate workflow including a pixel-level synthesization data augmentation method and a TIA-YOLOv5 network was proposed for real-time weed and crop detection in the field. The proposed method improved the detection accuracy and speed, providing very promising detection results.

With the acceleration of agricultural intelligent transformation, deep reinforcement learning (DRL), leveraging its adaptive perception and decision-making capabilities in complex environments, has emerged as a pivotal technology in advancing the intelligent upgrade of agricultural machinery and equipment. For example, in UAV path optimization, DRL can help UAVs plan more efficient flight paths to cover more areas in less time. To enhance the systematicity and credibility of this review, this paper systematically examines the application status, key issues, and development trends of DRL in agricultural scenarios, based on the research literature from mainstream Chinese and English databases spanning from 2018 to 2024. From the perspective of algorithm–hardware synergy, the article provides an in-depth analysis of DRL’s specific applications in agricultural ground platform navigation, path planning for intelligent agricultural end-effectors, and autonomous operations of low-altitude unmanned aerial vehicles. It highlights the technical advantages of DRL by integrating typical experimental outcomes, such as improved path-tracking accuracy and optimized spraying coverage. Meanwhile, this paper identifies three major challenges facing DRL in agricultural contexts: the difficulty of dynamic path planning in unstructured environments, constraints imposed by edge computing resources on algorithmic real-time performance, and risks to policy reliability and safety under human–machine collaboration conditions. Looking forward, the DRL-driven smart transformation of agricultural machinery will focus on three key aspects: (1) The first aspect is developing a hybrid decision-making architecture based on model predictive control (MPC). This aims to enhance the strategic stability and decision-making interpretability of agricultural machinery (like unmanned tractors, harvesters, and drones) in complex and dynamic field environments. This is essential for ensuring the safe and reliable autonomous operation of machinery. (2) The second aspect is designing lightweight models that support edge-cloud collaborative deployment. This can meet the requirements of low-latency responses and low-power operation in edge computing scenarios during field operations, providing computational power for the real-time intelligent decision-making of machinery. (3) The third aspect is integrating meta-learning with self-supervised mechanisms. This helps improve the algorithm’s fast generalization ability across different crop types, climates, and geographical regions, ensuring the smart agricultural machinery system has broad adaptability and robustness and accelerating its application in various agricultural settings. This paper proposes research directions from three key dimensions-“algorithm capability enhancement, deployment architecture optimization, and generalization ability improvement”-offering theoretical references and practical pathways for the continuous evolution of intelligent agricultural equipment.

The rapid and accurate estimation of leaf chlorophyll content (LCC), an important indicator of crop photosynthetic capacity and nutritional status, is of great significance for precise nitrogen fertilization management. To explore the existence of a versatile regression model that can be successfully used to estimate the LCC for different varieties under different growth stages and nitrogen stress conditions, a study was conducted in 2023 across the growing season for winter wheat with five species and five nitrogen application levels. Two machine learning regression algorithms, support vector machine (SVM) and random forest (RF), were used to establish the bridge between UAV-derived multispectral vegetation indices and ground truth LCC (relative chlorophyll content, SPAD), taking the multivariate linear regression (MLR) algorithm as a reference. The results show that the visible atmospherically resistant index, vegetative index, and normalized difference vegetation index had the highest correlation with ground truth LCC, with a Pearson’s correlation coefficient of 0.95. All three regression algorithms (MLR, RF, and SVM) performed well on the training dataset (R²: 0.932–0.944, RMSE: 3.96 to 4.37), but performed differently on validation datasets with different growth stages, species, and nitrogen application levels. Compared to winter wheat species and nitrogen application levels, the growth stages had the greatest influence on the generalization ability of LCC estimation models, especially for the dough stage. At the dough stage, compared to MLR and RF, SVM performed best, with R² increasing by 0.27 and 0.10, respectively, and RMSE decreasing by 1.13 and 0.46, respectively. Overall, this study demonstrated that the combination of UAV-derived multispectral VIs and the SVM regression algorithm could be successfully applied to map the LCC of winter wheat for different species, growth stages, and nitrogen stress conditions. Ultimately, this research is significant as it shows the successful application of UAV data for mapping the LCC of winter wheat across diverse conditions, offering valuable insights for precision nitrogen fertilization management.