Traditional manual or semi-mechanized pesticide spraying methods often suffer from issues such as redundant coverage and cumbersome operational steps, which fail to meet current pest and disease control requirements. Therefore, there is an urgent need to develop an efficient pest control technology system. This paper builds upon the Deep Q-Network algorithm by integrating the Bi-directional Long Short-Term Memory structure to propose the BL-DQN algorithm. Based on this, a path planning framework for pest and disease control using agricultural drones is designed. This framework comprises four modules: remote sensing image acquisition via the Google Earth platform, task area segmentation using a deep learning U-Net model, rasterized environmental map creation, and coverage path planning. The goal is to enhance the efficiency and safety of pesticide application by drones in complex agricultural environments. Through simulation experiments, the BL-DQN algorithm achieved a 41.68% improvement in coverage compared with the traditional DQN algorithm. The repeat coverage rate for BL-DQN was 5.56%, which is lower than the 9.78% achieved by the DQN algorithm and the 31.29% of the Depth-First Search (DFS) algorithm. Additionally, the number of steps required by BL-DQN was only 80.1% of that of the DFS algorithm. In terms of target point guidance, the BL-DQN algorithm also outperformed both DQN and DFS, demonstrating superior performance.

Traditional pesticide application methods pose systemic threats to sustainable agriculture due to inefficient spraying practices and ecological contamination. Although agricultural drones demonstrate potential to address these challenges, they face critical limitations in energy-constrained complete coverage path planning for field operations. This study proposes a novel BiLG-D3QN algorithm by integrating deep reinforcement learning with Bi-LSTM and Bi-GRU architectures, specifically designed to optimize segmented coverage path planning under payload-dependent energy consumption constraints. The methodology encompasses four components: payload-energy consumption modeling, soybean cultivation area identification using Google Earth Engine-derived spatial distribution data, raster map construction, and enhanced segmented coverage path planning implementation. Through simulation experiments, the BiLG-D3QN algorithm demonstrated superior coverage efficiency, outperforming DDQN by 13.45%, D3QN by 12.27%, Dueling DQN by 14.62%, A-Star by 15.59%, and PPO by 22.15%. Additionally, the algorithm achieved an average redundancy rate of only 2.45%, which is significantly lower than that of DDQN (18.89%), D3QN (17.59%), Dueling DQN (17.59%), A-Star (21.54%), and PPO (25.12%). These results highlight the notable advantages of the BiLG-D3QN algorithm in addressing the challenges of pesticide spraying tasks in agricultural UAV applications.

Introduction: Weeds compete with crops for water, nutrients, and light, negatively impacting maize yield and quality. To enhance weed identification accuracy and meet the requirements of precision agriculture, we propose a lightweight semantic segmentation model named DSC-DeepLabv3+.Methods: MobileNetV2 is adopted as the backbone, and standard convolutions in atrous spatial pyramid pooling (ASPP) and decoder modules are replaced with depthwise separable dilated convolutions (DSDConv), significantly reducing model complexity and improving segmentation efficiency. To capture rich contextual information, strip pooling is incorporated into the ASPP module, forming the strip pooling–atrous spatial pyramid pooling (S-ASPP) structure. In addition, a convolutional block attention module (CBAM) is introduced to refine feature representations, and multi-scale features are further fused using the CBAM–Cascade Feature Fusion (C-CFF) module to improve semantic understanding.Results: Experimental results show that the proposed model reduces the number of parameters from 54.714M to 2.89M and decreases the computational cost from 167.139 GFLOPs to 15.326 GFLOPs, while achieving an inference speed of 42.89 FPS and a mean Intersection over Union (mIoU) of 85.57%.Discussion: These results demonstrate that DSC-DeepLabv3+ strikes an effective balance between accuracy and efficiency, outperforming several classical lightweight models, making it a promising solution for accurate and efficient weed segmentation in agricultural applications.

Introduction: The traditional strawberry picking operation has long relied on manual work. With the aging trend of the population becoming more and more obvious, the application of intelligent picking technology has become an irreversible trend. However, existing recognition methods still face bottlenecks such as suboptimal recognition accuracy and low computational efficiency. To address these issues, this study constructs a lightweight detection model, LBS-YOLO, based on an improved YOLOv11n architecture, significantly the model’s accuracy and interference robustness while greatly compressing the parameter quantity. Methods: The LBS-YOLO model is built upon YOLOv11n as the baseline network. In order to enhance the ability of backbone network feature representation, the model designs a lightweight LAWDS module. This design combines channel attention with spatial reconstruction operation to optimize the information retention efficiency in the down-sampling process, thus effectively enhancing the multi-scale feature representation ability and gradient flow propagation performance. Then in the feature fusion stage, the model introduces a Bidirectional Feature Pyramid Network (BiFPN), which not only enables cross-scale feature fusion but also achieves adaptive weighting through a learnable weight allocation mechanism. At last, adopts the C3k2_Star module to replace the conventional C3K2 for improved feature representation. Results: On the used strawberry dataset, the LBS-YOLO model reached 88.6% mAP@0.5 and 75.8% mAP@0.5:0.95, which were 2.2 and 1.3 percentage points higher than YOLOv11n, respectively. The LBS-YOLO model improves the recall rate from 83.2% of YOLOv11n to 86.4%, and the F1-score from 81.2% to 82.9%. Its computational complexity is 6.6 GFLOPs and its reasoning speed is 260.7 FPS. Even better, LBS-YOLO only needs 3.4MB of storage space and 1.6 million parameters, which are 34.6% and 38% less than YOLOv11n respectively. Discussion: The experiment demonstrates that, the LBS-YOLO model can significantly reduce the number of parameters and effectively improve the detection accuracy and operation efficiency. It successfully alleviated the problems of false detection and missed detection, thereby providing reliable technical support for strawberry growth monitoring, maturity identification and automatic picking.

Traditional path planning algorithms often fail to simultaneously ensure operational efficiency, energy constraint compliance, and environmental adaptability in agricultural scenarios, thereby hindering the advancement of precision agriculture. To address these challenges, this study proposes a deep reinforcement learning algorithm, MoE-D3QN, which integrates a Mixture-of-Experts mechanism with a Bi-directional Long Short-Term Memory model. This design enhances the efficiency and robustness of UAV path planning in agricultural environments. Building upon this algorithm, a hierarchical coverage path planning framework is developed. Multi-level task maps are constructed using crop information extracted from Sentinel-2 remote sensing imagery. Additionally, a dynamic energy consumption model and a progressive composite reward function are incorporated to further optimize UAV path planning in complex farmland conditions. Simulation experiments reveal that in the two-level scenario, the MoE-D3QN algorithm achieves a coverage efficiency of 0.8378, representing an improvement of 37.84–63.38% over traditional algorithms and 19.19–63.38% over conventional reinforcement learning methods. The redundancy rate is reduced to 3.23%, which is 38.71–41.94% lower than traditional methods and 4.46–42.77% lower than reinforcement learning counterparts. In the three-level scenario, MoE-D3QN achieves a coverage efficiency of 0.8261, exceeding traditional algorithms by 52.13–71.45% and reinforcement learning approaches by 10.15–50.2%. The redundancy rate is further reduced to 5.26%, which is significantly lower than the 57.89–92.11% observed with traditional methods and the 15.57–18.98% reported for reinforcement learning algorithms. These findings demonstrate that the MoE-D3QN algorithm exhibits high-quality planning performance in complex farmland environments, indicating its strong potential for widespread application in precision agriculture.

This study accurately inverts key growth parameters of rice, including Leaf Area Index (LAI), chlorophyll content (SPAD) value, and height, by integrating multisource remote sensing data (including MODIS and ERA5 imagery) and deep learning models. Dehui City in Jilin Province, China, was selected as the case study area, where multidimensional data including vegetation indices, ecological function parameters, and environmental variables were collected, covering seven key growth stages of rice. Data analysis and parameter prediction were conducted using a variety of machine learning and deep learning models including Partial Least Squares (PLSs), Support Vector Machine (SVM), Random Forest (RF), and Long Short-Term Memory Networks (LSTM), among which the LSTM model demonstrated superior performance, particularly at multiple critical time points. The results show that the LSTM performed best in inverting the three parameters, with the LAI inversion accuracy on 21 August reaching a coefficient of determination (R²) of 0.72, root mean square error (RMSE) of 0.34, and mean absolute error (MAE) of 0.27. The SPAD inversion accuracy on the same date achieved an R² of 0.69, RMSE of 1.45, and MAE of 1.16. The height inversion accuracy on 25 July reached an R² of 0.74, RMSE of 2.30, and MAE of 2.08. This study not only verifies the effectiveness of combining multisource data and advanced algorithms but also provides a scientific basis for the precision management and decision-making of rice cultivation.