The accurate prediction of crop yields is crucial for enhancing agricultural efficiency and ensuring food security. This study assesses the performance of the CNN-LSTM-Attention model in predicting the yields of maize, rice, and soybeans in Northeast China and compares its effectiveness with traditional models such as RF, XGBoost, and CNN. Utilizing multi-source data from 2014 to 2020, which include vegetation indices, environmental variables, and photosynthetically active parameters, our research examines the model’s capacity to capture essential spatial and temporal variations. The CNN-LSTM-Attention model integrates Convolutional Neural Networks, Long Short-Term Memory, and an attention mechanism to effectively process complex datasets and manage non-linear relationships within agricultural data. Notably, the study explores the potential of using kNDVI for predicting yields of multiple crops, highlighting its effectiveness. Our findings demonstrate that advanced deep-learning models significantly enhance yield prediction accuracy over traditional methods. We advocate for the incorporation of sophisticated deep-learning technologies in agricultural practices, which can substantially improve yield prediction accuracy and food production strategies.

In order to solve the problems of large amounts of calculation and long calculation times of the A-star algorithm in three-dimensional space, based on the R5DOS model, this paper proposes a three-dimensional space UAV path planning model. The improved R5DOS intersection model is combined with the improved A-star algorithm. Together, they construct a local search process, and the R5DOS path planning model is established by reducing the number of search nodes. The path planning model is simulated through MATLAB software and the model can greatly reduce the number of nodes and computational complexity of the A-star algorithm in three-dimensional spaces, while also reducing the calculation time of the UAV. Finally, we compare the improved A-star algorithm with the original A-star algorithm and the geometric A-star algorithm. The final fitting result proves that the improved A-star algorithm has a shorter computation time and fewer node visits. Overall, the simulation results confirm the effectiveness of the improved A-star algorithm and they can be used as a reference for future research on path planning algorithms.

To enhance agricultural productivity through the accurate detection of pests under the constrained resources of mobile devices, we introduce LP-YOLO, a bespoke lightweight object detection framework optimized for mobile-based insect pest identification. Initially, we devise lightweight components, namely LP_Unit and LP_DownSample, to serve as direct substitutes for the majority of modules within YOLOv8. Subsequently, we develop an innovative attention mechanism, denoted as ECSA (Efficient Channel and Spatial Attention), which is integrated into the network to forge LP-YOLO(l). Moreover, assessing the trade-offs between parameter reduction and computational efficiency, considering both the backbone and head components of the network, we use structured pruning methods for the pruning process, culminating in the creation of LP-YOLO(s). Through a comprehensive series of evaluations on the IP102 dataset, the efficacy of LP-YOLO as a lightweight object detection model is validated. By incorporating fine-tuning techniques during training, LP-YOLO(s)n demonstrates a marginal mAP decrease of only 0.8% compared to YOLOv8n. However, it achieves a significant reduction in parameter count by 70.2% and a remarkable 40.7% increase in FPS, underscoring its efficiency and performance.

Path planning is one of the key elements for achieving rapid and stable flight when unmanned aerial vehicles (UAVs) are conducting monitoring and inspection tasks at ultra-low altitudes or in orchard environments. It involves finding the optimal and safe route between a given starting point and a target point. Achieving rapid and stable flight in complex environments is paramount. In environments characterized by high-density obstacles, the stability of UAVs remains a focal point in the research of path planning algorithms. This study, utilizing a feature attention mechanism, systematically identifies distinctive points on the obstacles, leading to the development of the RFA-Star (R5DOS Feature Attention A-star) path planning algorithm. In MATLAB, random maps were generated to assess the performance of the RFA-Star algorithm. The analysis focused on evaluating the effectiveness of the RFA-Star algorithm under varying obstacle density conditions and different map sizes. Additionally, comparative analyses juxtaposed the performance of the RFA-Star algorithm against three other algorithms. Experimental results indicate that the RFA-Star algorithm demonstrates the shortest computation time, approximately 84%-94% faster than the RJA-Star algorithm and 51%-96% faster than the Improved A-Star. The flight distance is comparable to the RJA-Star algorithm, with slightly more searched nodes. Considering these factors collectively, the RFA-Star algorithm exhibits a relatively superior balance between computational efficiency and path quality. It consistently demonstrates efficient and stable performance across diverse complex environments. However, for comprehensive performance enhancement, further optimization is necessary.

Accurate crop yield prediction is crucial for formulating agricultural policies, guiding agricultural management, and optimizing resource allocation. This study proposes a method for predicting yields in China’s major winter wheat-producing regions using MOD13A1 data and a deep learning model which incorporates an Improved Gray Wolf Optimization (IGWO) algorithm. By adjusting the key parameters of the Convolutional Neural Network (CNN) with IGWO, the prediction accuracy is significantly enhanced. Additionally, the study explores the potential of the Green Normalized Difference Vegetation Index (GNDVI) in yield prediction. The research utilizes data collected from March to May between 2001 and 2010, encompassing vegetation indices, environmental variables, and yield statistics. The results indicate that the IGWO-CNN model outperforms traditional machine learning approaches and standalone CNN models in terms of prediction accuracy, achieving the highest performance with an R² of 0.7587, an RMSE of 593.6 kg/ha, an MAE of 486.5577 kg/ha, and an MAPE of 11.39%. The study finds that April is the optimal period for early yield prediction of winter wheat. This research validates the effectiveness of combining deep learning with remote sensing data in crop yield prediction, providing technical support for precision agriculture and contributing to global food security and sustainable agricultural development.

With the global population growth and increasing food demand, the development of precision agriculture has become particularly critical. In precision agriculture, accurately identifying areas of nitrogen stress in crops and planning precise fertilization paths are crucial. However, traditional coverage path-planning (CPP) typically considers only single-area tasks and overlooks the multi-area tasks CPP. To address this problem, this study proposed a Regional Framework for Coverage Path-Planning for Precision Fertilization (RFCPPF) for crop protection UAVs in multi-area tasks. This framework includes three modules: nitrogen stress spatial distribution extraction, multi-area tasks environmental map construction, and coverage path-planning. Firstly, Sentinel-2 remote-sensing images are processed using the Google Earth Engine (GEE) platform, and the Green Normalized Difference Vegetation Index (GNDVI) is calculated to extract the spatial distribution of nitrogen stress. A multi-area tasks environmental map is constructed to guide multiple UAV agents. Subsequently, improvements based on the Double Deep Q Network (DDQN) are introduced, incorporating Long Short-Term Memory (LSTM) and dueling network structures. Additionally, a multi-objective reward function and a state and action selection strategy suitable for stress area plant protection operations are designed. Simulation experiments verify the superiority of the proposed method in reducing redundant paths and improving coverage efficiency. The proposed improved DDQN achieved an overall step count that is 60.71% of MLP-DDQN and 90.55% of Breadth-First Search–Boustrophedon Algorithm (BFS-BA). Additionally, the total repeated coverage rate was reduced by 7.06% compared to MLP-DDQN and by 8.82% compared to BFS-BA.