Agricultural machinery trajectory operation mode identification aims to determine the spatiotemporal distribution characteristics of agricultural machinery trajectories, thereby understanding the machinery's activity at each time step. It is a multivariate time series classification task. However, existing methods are limited to capturing feature interactions only within local trajectory points, without fully utilizing the global contextual information hidden within the trajectory. To effectively model the contextual information of trajectories to accurately identify operation modes pattern of agricultural machinery, we propose a dual-domain context-aware network (DCANet). First, we propose a multi-angle feature enhancement method that uses physical kinematics formulas and mathematical statistics methods to expand the feature set of trajectories, thereby fully exploiting the inherent information. We then design a frequency-domain context-aware module consisting of two components: a local awareness bottleneck module and a learnable frequency-domain attention context module. The former is used to model the local dependencies. Based on this, the latter uses a discrete wavelet transform and a multi-head attention mechanism to calculate the correlation and dependency of trajectory features in multiple frequency subspaces, adaptively analysing trajectory feature changes in the time-frequency domain. Finally, we design an information aggregation context module. Based on the construction of the spatiotemporal relationship graph of agricultural machinery trajectory points, we combine it with a multi-filter graph convolution operator to capture the multi-scale features of trajectory points in different channels. To validate DCANet, we evaluated it on 3 datasets against 12 related methods. The results demonstrate that DCANet achieves superior performance, with accuracies of 89.03%, 90.24%, and 90.47%, and F1-scores of 71.81%, 84.62%, and 90.43%, respectively.

Agricultural machinery trajectory operation mode identification aims to automatically distinguish field operation scenes and road driving scenes by leveraging the spatiotemporal features of massive agricultural machinery trajectories and is a key basis task in precision agriculture. In recent years, machine learning algorithms have been increasingly applied to agricultural machinery trajectory operation mode identification. However, these models typically depend on hyperparameters, and the empirically determined parameter structures often limit the model’s potential performance, resulting in inferior generalization across different trajectory scenarios. To address this challenge, we propose a parameter search framework based on deeply weakly informed deep reinforcement learning (DWIDRL) for agricultural machinery trajectory operation mode identification, which can automatically determine the parameter structure according to the features of trajectory samples. First, we leveraged deep reinforcement learning to model parameter search as a Markov Decision Process (MDP) and developed an automated parameter search framework, enabling intelligent parameter optimization. Second, it incorporates the state aggregation context module, which encodes both global and local states, enabling the model to adaptively search for parameters according to different trajectory scenarios. Third, we propose a deeply weakly informed learning strategy that enables the model to interact with the agent’s output, adaptively adjusting the optimal parameter search policy based on past experience. Finally, to increase the accuracy of the parameters within extensive search spaces, we propose a gradual search mechanism based on parameter space attenuation, which methodically narrows the search scope at each successive layer, thereby significantly improving the precision of the results. To validate the effectiveness of the proposed framework, we conducted parameter optimization experiments on five agricultural machinery trajectory operation mode identification models across four distinct trajectory scenarios. Consequently, on one trajectory dataset, our method achieves a maximum improvement of 20.95% in average F1-score and 15.31% in accuracy. The results demonstrate that the proposed framework significantly enhances model performance and generalizability by identifying optimal parameter configurations in a shorter amount of time.

Agricultural machinery operation mode identification is crucial for advancing precision agriculture. This task classifies machinery trajectory points into “field” or “road” categories. Existing research on identifying agricultural machinery operation modes is hindered by insufficient mining of trajectory spatiotemporal features, inadequate propagation of trajectory semantic and graph topology features due to trajectory long-range dependencies, and a lack of capture of characteristic differences between nodes in a heterogeneous trajectory graph. To overcome the above shortcomings, we propose a multifiltered graph convolutional neural network with a self-learning graph topology model (MFGCN-SLT). First, we propose statistical feature enhancement via mathematical and statistical methods to capture the statistical features of trajectory points spatiotemporally. We employ an attention-based feature weighting strategy to adaptively emphasize discriminative spatiotemporal and statistical features of trajectory points. Third, we propose a self-learning adjacency matrix module that automatically constructs the adjacency matrix via an end-to-end graph structure learning paradigma to more effectively capture the graph topological features in the trajectory and the actual trajectory graph structure. Finally, an adaptive homophily graph convolutional network model is proposed, which is divided into two parts: we apply an augmented Laplacian operator that contains multiple adjacency matrices in time and space to better capture long-range semantic information in the trajectory; we incorporate multiple graph filters in graph convolution to capture the variability between different classes of trajectory points and establish a homogeneous graph after convolution to retain multiple types of trajectory information. To verify the effectiveness of the proposed model, experiments were carried out on the actual harvesting trajectories of two crops provided by the Key Laboratory of Agricultural Machinery Monitoring and Big Data Applications Ministry of Agriculture and Rural Affairs. The MFGCN-SLT model achieved accuracies of 98.86

Agricultural machinery is one of the most significant sources of non-road mobile emissions in recent years.Yet accurate estimation of its carbon and pollutant emissions is often hindered by the fuel consumption data and localized emission factors.In this study,a prediction framework was developed for tractor fuel consumption,CO2,and NOx emissions from tractors.Massive BeiDou trajectory data were also integrated with portable emission measurement system(PEMS)measurements and the national operational emission inventory.1)The samples were incorporated with complete fields from the BeiDou trajectory data and multidimensional features,such as the tractor speed,direction,engine speed,and torque.A feature set was constructed to predict the fuel consumption.A feature engineering process was conducted on the dataset of trajectory samples with complete fields from the 2023 summer harvest.The trajectories were segmented into kinematic fragments with a time step of 100s.A Residual Deep Neural Network(ResDNN)model with a 21-layer structure was employed to predict fuel consumption,with an R2 of 0.75 and a MAPE of 24.46％.Fuel consumption features were further constructed for the missing feature fields,according to the operational duration and distance.Various algorithms of machine learning were used for the predictive models.Light Gradient Boosting Machine(LightGBM)model performed best(R2=0.77,MAPE=39.28％).2)Localized emission models were established.PEMS tests were then conducted on four typical China Ⅳ standard tractors with the rated powers of 51.5,58.8,88.2,and 177 kW under varying engine loads.According to the experimental data,machine learning algorithms(ridge regression,random forest,decision tree,SVM,and LightGBM)were compared to construct emission prediction models using multi-dimensional input features.The evaluation results indicated that the ResDNN model achieved the best performance for fuel consumption prediction with the features(R2=0.75,and MAPE=24.46％),effectively resolving the gradient degradation in deep networks.In the simplified feature set,the LightGBM model performed optimally(R2=0.77,and MAPE=39.28％).Support Vector Machine was identified as the optimal model for CO2 emissions(R2=0.95,MAPE=5.98％)prediction,while LightGBM performed best for NOx emissions(R2=0.86,MAPE=13.78％).Importance analysis revealed that instantaneous fuel consumption and engine speed were the most critical determinants for CO2 emission,whereas environmental parameters shared a higher contribution to NOx prediction.Finally,these models were applied to the trajectory data of 870,192 tractors equipped with BeiDou terminals during the 2023 summer harvest(May 25 to June 25).A high-resolution national emission inventory was estimated after application.The total fuel consumption was 47.01×106 L,thus generating 128.21 ×103t of CO2 and 281.9t of NOx.The average daily emissions per tractor were 147.33 kg for CO2 and 0.32 kg for NOx.Spatially,the emissions were concentrated in major agricultural provinces,such as Jiangsu,Henan,and Heilongjiang.Temporally,the emission peaks coincided perfectly with the busy farming rhythm.This finding can provide support data for carbon and pollutant emissions from large-scale agricultural machinery in green agriculture.

With the advancement of agricultural modernization, agricultural machinery is widely used for crop harvesting. Traditionally, agricultural machines must be refueled at gas stations regularly, affecting the harvesting efficiency. A mobile refueling service has emerged in recent years, in which refueling tankers can move to serve the refueling request. However, the current mobile refueling system is still in an on-demand mode, which may not achieve timely response. Therefore, in this paper, we propose a new mobile refueling mode, i.e., predictive mobile refueling. To tackle the challenge of sparse rewards in predictive mobile refueling, we develop a two-stage reinforcement learning-based scheduling strategy MobRef, which decouples the scheduling process into a central request dispatcher and a distributed tanker reposition scheduler, and further introduces a potential energy-based reward shaping function to facilitate the training of the reposition scheduler. Extensive experiments on two real-world datasets demonstrate the effectiveness of MobRef, which outperforms the best baseline by 12.71% on average. We also present a deployed system based on MobRef, which is used internally in China National Petroleum Corporation.

Agricultural machinery trajectory operation mode identification constitutes a key spatiotemporal data processing task for achieving precision agriculture. The objective of this task is to learn the features from agricultural machinery trajectories, thus assigning appropriate semantic labels to unclassified trajectory points. Existing studies have focused on spatiotemporal correlations within local areas but have failed to model dependencies at different scales, while most identification models heavily depend on the manually labelled data for training. To address these shortcomings and improve identification accuracy, we propose a dual-context encoder with spatiotemporal feature enhancement (DCST-Encoder). First, a spatiotemporal feature enhancement (STFE) scheme captures both the instantaneous motion state and the overall motion state aggregated over a temporal window of agricultural machinery, thereby enriching the expressive power of trajectory information. Next, a dual-context encoder (DC-Encoder) incorporates a global context extraction module (GCEM) and a local context aggregation module (LCAM) to comprehensively model the dependencies that exist at different scales within agricultural machinery trajectories. Finally, a dual-stream collaborative pretraining (DSCP) strategy pretrains the model, enabling the automatic learning of more generalized spatiotemporal representations from massive agricultural machinery trajectories. On paddy, wheat and corn harvester trajectory datasets, the accuracies of the DCST encoder were 91.00%, 90.32% and 90.12%, respectively, and the corresponding F1 scores were 90.99%, 90.02% and 72.53%, respectively. Compared with the current state-of-the-art models, the accuracy values were improved by 6.52%, 3.40% and 1.22%, respectively, and the F1 scores were improved by 6.58%, 7.17% and 4.10%, respectively. The proposed DCST-Encoder provides a comprehensive and generalizable framework for this task, where the limitations of local dependency modelling and reliance on labelled data are simultaneously addressed through multiscale contextual learning and self-supervised pretraining. The source code can be accessed at: https://github.com/pjw2146087/DCST-Encoder.

Using the potential spatiotemporal features in trajectory data to identify the operation mode of agricultural machinery is an important basic task in the field of precision agriculture. However, existing methods for identifying the operation mode of agricultural machinery trajectories fail to model the dependencies of agricultural machinery trajectories from different ranges, and the imbalanced data distributions of different categories of agricultural machinery trajectory data produce identification bias. To overcome the above defects, this paper proposes a multi-range spatiotemporal information capture network based on amplified feature deformation (VRPNet). First, to solve the identification bias caused by the imbalanced data distribution of the model, we design a data balancing module based on a factorized variational autoencoder (FVAE), which independently factors and encodes the features of minority class trajectory samples and then decodes and generates quasi-trajectories similar to the original trajectory points to balance the data distributions of different categories. Second, to explore the potential spatiotemporal information of trajectories fully, we propose a trajectory information multi-scale amplification module, which applies kinematic methods and statistical methods to extract multi-scale features of agricultural machinery trajectories in different spatiotemporal ranges to mine the inherent information of agricultural machinery trajectories. Finally, to comprehensively model the dependencies of agricultural machinery trajectories, we propose a spatial correlation capture module based on a low-rank approximation matrix (LRSC) and a dynamic multi-path convolution bottleneck based on feature deformation (FD-DPC) to assemble into a trajectory context encoder to explore the feature interactions of agricultural machinery trajectories in different ranges. To verify the effectiveness of the method, we conducted experiments on paddy and wheat trajectory public datasets. The results show that the accuracies of VRPNet on the paddy and wheat trajectory datasets are 94.20% and 96.06%, respectively, which are improvements of 1.72% and 1.92%, respectively, over those of the currently widely used models.

Classifying each point in global navigation satellite system positioning trajectories as either in-field or on-road is pivotal for analyzing the operational performance of agricultural vehicles. This paper introduces a field-road trajectory segmentation method which significantly enhances segmentation robustness through a self-supervised learning approach. The method involves pre-training a trajectory representation model with self-supervised learning, which is subsequently fine-tuned for trajectory segmentation applications. Our model employs dual encoders: point-level and trajectory-level to capture essential multi-level spatio-temporal features for accurate trajectory segmentation. The point-level encoder focuses on extracting detailed features for individual points and performing point-density classification, while the trajectory-level encoder enriches these features by integrating trajectory similarity computations. Meanwhile, utilizing a combination of Convolutional Neural Networks and Transformer networks, the model adeptly handles both temporal and spatial dependencies in trajectory data, crucial for dynamic adaptation to various trajectories. The accuracy of our method achieves 93.95% and 89.32% on two manually labeled datasets, respectively, and experiments on the raw trajectory dataset demonstrate that a pre-training trajectory representation model can effectively capture the trajectory characteristic. Extensive validation confirms the superior efficacy of the proposed method and its potential impact on the evaluation efficiency of practical agricultural operations. The source code is available at the following address: https://github.com/peanut2code/PreTR-TS.

The positioning environment of farm roads is complex and variable, with defined scenes including open sky, forest, overpass, and tunnel. Relying solely on the Global Navigation Satellite System (GNSS) for positioning throughout the operation of unmanned agricultural machines is insufficient. This study addressed the need for rapid and accurate identification of farm road scene types to select appropriate positioning devices for unmanned agricultural machines. Real-time satellite signal data, obtained through onboard GNSS receivers and combined with broadcast ephemeris data, were used to extract positioning status and track satellite statistics and distribution features. A classifier based on a sliding window was developed, and an inference based on tracked satellite numbers was proposed to detect the farm road positioning scene and calculate the length of different road segments. This study was conducted using real-world working conditions at an agricultural machinery cooperative in Miyun, Beijing, China, where three sets of GNSS data were collected from the farm road using a vehicle-mounted all-frequency GNSS receiver. The results showed that the classification accuracy for open-sky, overpass, and tunnel scenes was 93.96%, with a recall rate of 98.31% and an F1 score of 95.82%. Compared with random forest and XGBoost, the F1 scores improved by 17.83 and 5.70, respectively. This method, based on GNSS multi-feature fusion, can provide a reference for selecting multi-source positioning devices and planning the routes of unmanned agricultural machines.

To address the issues of the existing frustum-based methods’ underutilization of image information in road 3D object detection as well as the lack of research on agricultural scenes, we constructed an object detection dataset using an 80-line LiDAR and a camera in a complex tractor road scene and proposed a new network called FrustumFusionNets (FFNets). Initially, we utilize the results of image-based 2D object detection to narrow down the search region in the 3D space of the point cloud. Next, we introduce a Gaussian mask to enhance the point cloud information. Then, we extract the features from the frustum point cloud and the crop image using the point cloud feature extraction pipeline and the image feature extraction pipeline, respectively. Finally, we concatenate and fuse the data features from both modalities to achieve 3D object detection. Experiments demonstrate that on the constructed test set of tractor road data, the FrustumFusionNetv2 achieves 82.28

A perception system is one of the most important components for the autonomous driving of agricultural machinery.However,there are only a few perception datasets specifically designed for agricultural scenarios,due to their difference from the typical urban scenarios in previous studies.In contrast to the urban examples,the agricultural applications can suffer from harsh working circumstances.It is often required for the perception sensors and algorithms.In this study,a low-cost perception system was proposed for the two-stage detection using millimeter-wave radar and a monocular camera.3D object detection was then performed on the autonomous driving of the agricultural machinery under agricultural scenarios.Firstly,a multimodal perception dataset of the agricultural scenes was constructed to incorporate the LiDAR(light detection and ranging),INS(inertial navigation system),camera,and millimeter-wave radar data with a hardware-level data synchronization and target-level data annotation.Then the middle fusion strategy was used to build a neural network model,known as CFPNet.Preliminary detection of the target was also implemented with the improved network of the center point detection.Furthermore,the radar point cloud features were extracted from the frustum region of interest to supplement the image features.Finally,the preliminary detection information and radar feature were combined to perform a secondary detection.The 3D object attributes(depth,direction,and velocity)were regressed concurrently.The results show that the mAP(mean average precision)of the CFPNet on the self-built multimodal dataset of the agricultural perception was 86.5%,which was 5.5 percentage points higher than the baseline,and the mATE(mean average translation error)was 0.197 m lower than the baseline.An additional experiment on small object detection was conducted to verify the effectiveness of the CFPNet.The better performance was achieved in a recall rate of 1 for the selected small objects,which was 0.3 higher than before the improvement,indicating the better performance of the detection.Deployment experiments were conducted to test the applicability of the CFPNet.A frame rate of 7.4 frames per second was 211%of the baseline in the low-computing agricultural scenarios.Experiments on the public datasets were conducted to test the CFPNet in the rest scenarios.The favorable performance was achieved on the NuScenes public dataset,with the mATE,mASE,and mAVE of 0.792 m,0.236,and 0.52 m/s,respectively.Since the CFPNet was specifically designed for monocular cameras,its mAP lagged behind.Furthermore,the CFPNet can directly provide the speed information of the target without the preceding and following frames.This finding can provide a feasible solution and technical support for the 3D object detection in agricultural scenarios,especially with low computing power.

The key preprocessing task in the classification of agricultural machinery trajectory data involves segmenting trajectory points into field and road segments and assigning them corresponding semantic labels. Existing density-based clustering methods struggle to distinguish weakly connected trajectories between high-density fields and low-density roads, which results in the misclassification of adjacent fields and connecting roads as a whole. To overcome these limitations, the present study proposes a classification method that is based on a local direction centrality measurement clustering algorithm (CLDCM) and a direction statistical feature (DSF). Specifically, CLDCM uses differences between the local direction centrality measurement to distinguish internal points and boundary points of different fields. As a result, boundary points generate enclosed spaces to restrict connections among internal points within the same field, thereby preventing cross-cluster connections and isolating weakly connected fields. After that, the distribution of agricultural machinery movement directions is computed using statistical methods. Subsequently, the trajectory points at the intersections of fields and roads are analyzed and corrected according to the differences in the direction distributions of the fields and road segments. To validate the effectiveness of the proposed method, experiments were conducted on three real agricultural machinery trajectory datasets. Results demonstrate that our method achieves an average F1-score improvement of 12.16% on all trajectory datasets, compared with the existing leading method for agricultural machinery trajectory field-road classification. In particular, for the wheat harvester trajectory dataset, CLDCM-DSF outperforms the existing leading method in the field category with a significant increase in F1-score and recall by 20.85% and 32.05%, respectively, while increasing the F1-score and precision by 21.91% and 32.01%, respectively, in the road category. Overall, this study provides a novel and effective method for field-road classification, which helps uncover the spatiotemporal evolution patterns behind agricultural machinery trajectories and the underlying factors influencing agricultural planting and harvesting.

Maize(Zea mays L.)is a major crop for global food security at present.Advanced breeding is often required to enhance yield,stress resistance,and adaptability,particularly for high-throughput,non-destructive,and accurate acquisition of plant phenotypic parameters.Three-dimensional(3D)point clouds acquired by LiDAR can provide unprecedented detail of plant architecture,compared with 2D imaging.However,their widespread application has been confined to the accurate instance segmentation of individual plants within dense populations in real-world fields.Furthermore,conventional clustering or geometry algorithms cannot solve the convoluted spatial arrangement,complex plant morphologies,extensive canopy adhesion-where the leaves of adjacent plants are tightly interwoven-and mutual occlusion among plants.The efficient and reliable extraction of phenotypic data has been severely constrained to the fragmented or incorrectly merged plant instances.In this study,an instance segmentation framework,3D-MaizeNet,was proposed to integrate LiDAR data with deep learning.Individual maize plants were accurately extracted for the high-throughput measurement of key agronomic traits,such as plant height and stem height.Three stages are included.1)The structural integrity of the individual plant was preserved to avoid the compromise during simplistic preprocessing.An adaptive block segmentation was introduced using crop row detection.The row-planting pattern of farmlands was divided used to divide the large-scale point cloud into plant-centric blocks.This approach was used to effectively minimize the interference from overlapping canopies in adjacent rows.A high-quality,field-derived point cloud dataset was constructed for robust model training.2)A local spatial encoding module was designed to learn fine-grained geometric features from complex canopy structures(e.g.,leaf angles and stem orientations).Concurrently,an attention aggregation down-sampling module was integrated to reduce the loss of key spatial features during feature extraction.Salient information was selectively preserved to distinguish among tightly packed plants.3)According to the high-fidelity instance segmentation,an pipeline was established for the high-throughput quantification of plant height and stem height-two pivotal phenotypic parameters closely related to yield potential and lodging resistance.Field-scanned data was were collected to validate the efficacy of the framework.Experimental results showed that the 3D-MaizeNet achieved a mean Average Precision(mAP)of 0.959 and an overall accuracy of 0.964 in instance segmentation,indicating the superior performance to identifyin identifying and delineate delineating the individual plant.Furthermore,the key traits were extracted for the strong correlations with manual ground-truth measurements,with coefficients of determination(R2)of 0.91 and 0.89 for plant height and stem height,respectively.The high-throughput and precise phenotyping platform can provide the technical support to advance the maize genomics,Genome-Wide Association Studies(GWAS),and ultimately the molecular breeding for next-generation crops.

Background and aim Maintaining an appropriate nitrogen (N) status is crucial for achieving desirable grain quality in barley. N fertilization is typically applied at sowing, leaving limited scope for in-season adjustment. Timely monitoring is essential for grain N concentration prediction and quality assessment. This study aimed to develop an artificial intelligence (AI) driven framework to estimate N concentration, N uptake, N nutrition index (NNI), and dry matter (DM) using unmanned aerial vehicle (UAV)-based multispectral imagery collected at three key growth stages (jointing, DC30; heading, DC55; and flowering, DC65). Methods Two machine learning algorithms, random forest (RF) and Keras-based feedforward neural network (KFNN), were used to estimate N-related indicators. Multiple vegetation indices (VIs) were extracted from multispectral data. Feature importance ranking and non-dominated sorting genetic algorithm (NSGA) were applied to optimize input variables for improving model performance and robustness. Results The results showed that N-related indicators were better estimated at DC55 and DC65 stage, while DM were well predicted at DC30 stage. KFNN consistently outperformed RF in modeling complex traits such as N uptake and DM, with D-index improvements exceeding 10%. NSGA-optimized feature sets outperformed traditional importance ranking by improving both model stability and predictive accuracy. The top 3 VIs combinations achieved a favorable balance between accuracy and redundancy. All models achieved D-index values above 0.75 across N-related indicators and DM. Conclusion This study demonstrates that combining growth-stage-specific modeling with AI-based feature optimization provides a scalable and cost-effective approach for real-time N monitoring, supporting precision N management in spring barley.

Perception is a fundamental component of autonomous driving systems. While LiDAR-based methods have achieved remarkable progress in object detection, their reliability can degrade under adverse weather conditions. Radar point clouds provide a robust alternative due to their resilience to bad weather and low-illumination scenarios. However, radar point clouds are typically sparse, unordered, and less informative than LiDAR data, making it challenging to directly apply existing LiDAR-based perception methods. To address these challenges, we propose IRGNN, an Invariant Radar Graph Neural Network for radar point cloud object detection. IRGNN first reconstructs radar point clouds into graph representations using translation- and rotation-invariant feature designs, enabling robust modeling of sparse radar measurements. It then employs an improved message passing neural network (MPNN) with residual connections and a virtual node layer to enhance local feature propagation and global context modeling. Finally, task-specific heads are applied to the learned graph representations for object classification and bounding box prediction. Experimental results on the RadarScenes dataset show that IRGNN outperforms existing radar-based object detection methods and achieves competitive performance. In addition, IRGNN significantly reduces computational cost and memory usage during inference, demonstrating its effectiveness and practical potential for efficient radar-based perception in autonomous driving.

Agricultural machinery trajectory operation mode identification is a specific branch of multivariate time series classification that aims to use spatiotemporal features in the trajectories of agricultural machines to identify agricultural activity scenarios and assign corresponding semantic labels to each trajectory point. However, existing methods often focus on extracting local features from trajectory data, failing to comprehensively model the dependencies of agricultural machinery trajectory data and limiting the identification accuracy. To address the above problems, we propose an adaptive spatiotemporal two-branch network (ASTTNet) for trajectory operation mode identification of agricultural machinery. First, we propose a temporal feature enhancement (TFE) module, which further characterizes the trend of the motion state of agricultural machinery in different time ranges to explore the spatiotemporal information in the trajectory data fully. Second, we construct a two-branch network that consists of a global feature extraction (GFE) module and a learnable local feature extraction (LLFE) module. Specifically, the GFE branch efficiently model global dependencies in agricultural trajectory data. The LLFE branch model the local dependencies between trajectory points. Finally, to regulate the information flow between the GFE and LLFE, we propose a self-adaptive balancing strategy module (SBO), which reduces information redundancy between the two branches by decoupling their feature representation spaces. To validate the effectiveness of our method, we conducted experiments on real collected paddy harvester, wheat harvester and tractor trajectory datasets. The results show that the f1 scores of ASTTNet on the paddy harvester, wheat harvester and tractor trajectory datasets are 91.29%, 85.07% and 93.69%.

Precise time and frequency synchronization measurements are critical for many advanced applications, including mobile communications, the Internet of Things (IoT), and low Earth orbit (LEO) satellite internet. Real-time precise point positioning (RT-PPP) technology has become one of the dominant methods for real-time high-precision time-frequency transfer and synchronization. This study proposes an enhanced BDS RT-PPP time transfer and synchronization method utilizing bias modeling and develops a high-precision RT-PPP time synchronization terminal. After correcting inconsistent pseudorange biases, the RT-PPP time transfer precision reaches 0.19 ns for GPS and 0.16 ns for BDS, while the frequency stability over an averaging time of 1.5 & times; 10(4 )s reaches 4.01 & times; 10(-15). Compared with the conventional RT-PPP solution, the proposed bias-corrected method improves the time and frequency transfer performance of both GPS and BDS by approximately 30%. Furthermore, after clock information processing based on BDS RT-PPP, real-time pulse-per-second (PPS) physical signal synchronization with an average precision of 0.20 ns is achieved, and average frequency stability reaches 2.56 & times; 10(-15) at 1 day averaging time in two time links. When combined with a low-cost oven-controlled crystal oscillator (OCXO), the proposed system demonstrates frequency stability comparable to that of commercial hydrogen masers at 1 day averaging time, providing a portable solution for modern time and frequency stability measurements.

Nitrogen (N) is an essential element for crop growth, productivity, and quality, making it a fundamental component of crop nutrition. In precision agriculture, rapid and non-destructive monitoring of crop N status is crucial for formulating N management strategies to optimize N application and assessing crop performance. This review investigates the integration of remote sensing (RS) in precision N management, particularly focusing on addressing temporal, scale, and geometric consideration in RS applications. The study reviews RS monitoring techniques from three perspectives: firstly, determining optimal fertilization timing based on crop phenology; secondly, introducing RS platforms, including proximal sensing, airborne RS, and satellites for monitoring crop N status; and finally, examining the use of multi-angle RS techniques for N monitoring. The literature reviewed in this study shows that 29% of publications focus on N monitoring at joining and 24% at grain-filling stage, limiting the window for making decisions for in-season N management. This paper concludes that integrating appropriate monitoring platforms, multi-angle observations, and dynamic modeling offers a promising approach for assessing crop N status. This integrated approach provides an essential decision-making tool for N fertilization, advancing precision agriculture for its broader implication. Advancing dynamic crop models, in-field digital twins, multi-scale RS for seamless monitoring, and artificial intelligence for real-time N status diagnosis together will pave the way for precision N management in modern agriculture.

Time synchronization is a critical requirement in sixth-generation (6G) communication systems and Internet of Things (IoT) applications. However, the standard timing services provided by global navigation satellite systems (GNSS) are increasingly unable to meet the growing demands for precision and stability in modern networks. The proposed system leverages a single-difference time transfer (SDPT) method to achieve tens of picoseconds precision, enabling effective clock disciplining for oven-controlled crystal oscillators (OCXO). A clock disciplining within a phase-locked loop (PLL) structure further optimizes the output of time and frequency signals, enhancing OCXO stability. Additionally, a differential precise time synchronization system (DPTSS) by the BeiDou navigation satellite system (BDS)/global positioning system (GPS) is developed to deliver high-precision time reference signals for communication networks. Experimental results demonstrate that the real-time 1 pulse-per-second (1PPS) interval achieved by the BDS/GPS time link is better than 0.1 ns, with long-term frequency stability reaching the 10(-16) level. Furthermore, the proposed system achieves an 1PPS signal synchronization precision of 0.73 ns in communication networks, significantly outperforming the other state-of-the-art methods.