Search Results (56)

In Chinese solar greenhouses, row spacing of 40–80 cm and persistent 80–95% RH impose two fundamental constraints: conventional wheeled platforms exceed the inter-row turning radius, and unprotected electronics show <200 h MTBF under continuous humidity. These constraints define the design envelope for integrated inspection–detection–spraying robots. This review synthesizes 139 studies (2020–2026) from China, Europe, and North America. Beyond narrative synthesis, we contribute two quantitative tools: (1) a latency budget analysis decomposing the perception-to-spray pipeline—perception (30–50 ms), inference (50–140 ms), decision (5–10 ms), actuation (10–20 ms), and nozzle response (5–15 ms)—revealing a 100–235 ms total delay, translating to 3.0–7.1 cm spray-target displacement at 0.3 m/s; and (2) a standardized validation protocol with eight metrics for multi-site field trials. Four technical gaps persist. Rail-mounted platforms dominate, but autonomous systems lack validated high-humidity reliability. YOLO-based models achieve 93–94% mAP at 10–20 FPS on edge devices, yet cross-crop generalization is unproven, while Transformers are too slow (2–5 FPS) for real-time deployment. PWM-controlled spraying saves 20–40% of pesticide in controlled trials, but drift control and deposition uniformity under real canopies are rarely quantified with sufficient engineering detail. The quantified latency causes systematic spray-target misalignment that open-loop controllers cannot correct. We propose five future directions with quantifiable targets: low-cost modular platforms (50,000–80,000 RMB/unit vs. current 180,000–250,000 RMB); edge-optimized perception (>15 FPS on <15 W hardware); closed-loop latency compensation (<2 cm displacement); adoption of the proposed protocol for cross-system comparison; and multi-robot collaboration for >1 ha greenhouses. Full article

Remote supervision of agricultural robots depends on continuous interpretation of robot status and wireless link quality. In smart greenhouses, crop canopies, metallic frames, cultivation rows, and non-line-of-sight propagation can cause intermittent packet loss and RSSI attenuation. Treating such transient degradation as immediate communication failure can interrupt robot operation unnecessarily, whereas delayed recognition of persistent loss can compromise safety. This study proposes a probabilistic communication-state inference method for remotely supervised agricultural robots. The robot-to-gateway wireless link is represented by three states: normal, degraded, and failure. The degraded state acts as an uncertainty buffer that preserves recoverable degradation before failure escalation. Packet reception ratio, received signal strength, and trajectory-derived context are used to update state probabilities through a bounded transition mechanism. Field experiments with a mobile agricultural robot in a smart greenhouse showed an accuracy of $0.915\pm 0.007$ and a macro F1-score of $0.907\pm 0.008$, while reducing the premature failure rate to $18.0\pm 1.4\%$. Comparisons with threshold-based, moving-average, and adapted WSN fault-detection baselines, including a FedLSTM-inspired baseline, showed that binary fault-detection logic cannot explicitly preserve recoverable degraded communication intervals. The results indicate that probabilistic degradation modeling supports communication-aware remote supervision by distinguishing transient degradation from failure-level communication loss. Full article

The diagnosis of missing seedlings in high-density drill-seeded crops is often hindered by the strong coupling between visual perception and diagnostic rules, which leads to an irreversible cascade amplification of underlying missed detection errors. To address this dilemma, this paper proposes a “Perception–Topology” collaborative decoupling framework oriented toward row structure perception. In the perception phase, a row-structure-enhanced detection model (RS-YOLO) is constructed. It integrates Space-to-Depth (SPD) conversion, a Selective Frequency-domain Aggregation Module (SFAM), and a Row-Structure Attention Mechanism (RSM) to effectively suppress tire rut interference and explicitly reinforce the spatial topological priors of crops. In the diagnostic phase, an Adaptive Intra-row Gap Analysis (AIGA) algorithm is proposed. By utilizing a dynamic median intra-plant spacing scale and core canopy geometric pruning, this algorithm fundamentally reformulates missing seedling diagnosis into a physical interruption metric of one-dimensional graph connectivity. Evaluated on a finely reconstructed UAV-based sorghum imagery dataset, RS-YOLO achieved a significant improvement of 2.7% in precision and 3.2% in recall over the baseline model, providing a structure-aligned, high-confidence input for the diagnostic process. Based on this perceptual foundation, the AIGA algorithm ultimately achieved a diagnostic precision of 96.11% and a recall of 91.48% without the need for negative sample annotations. This framework effectively severs the propagation chain of perceptual errors, providing a noise-robust and highly physically interpretable new paradigm for the automated inspection of field population structures. Full article

Soil salinization is one of the primary forms of land degradation in arid and semi-arid regions, severely constraining agricultural production in Xinjiang’s oases. Unmanned aerial vehicle (UAV) imagery provides an effective means for precise monitoring of soil salinization, with image spatial resolution being a key factor affecting assessment accuracy. However, traditional single-scale remote sensing monitoring methods rely solely on spectral and textural features at the leaf scale (0.1 m resolution captures leaf-scale characteristics), neglecting the contribution of multi-scale features (single-row canopy scale and single-membrane-covered area scale (6-row crop canopy)) to soil salinity. For instance, 0.5–1 m reflects single-row canopy scale, while 2 m reflects single-membrane-covered area scale. Therefore, this study developed a multi-scale UAV imagery and machine learning framework to enhance soil electrical conductivity prediction accuracy. This study focuses on oasis cotton fields in Shaya County, Xinjiang. Based on UAV multispectral imagery, we resampled data to generate eight datasets at different spatial resolutions: 0.1, 0.5, 1, 1.5, 2, 2.5, 5, and 10 m. For each resolution, we calculated 21 spectral indices and 48 texture features to construct a feature set. At both single and multispatial scales, spectral indices, texture features, and their spectral-texture fusion features were constructed. Combining these with Backpropagation Neural Network (BPNN), Random Forest Regression (RFR), and Extreme Gradient Boosting (XGBoost) models, a soil EC estimation framework was developed. The impact of three feature combination schemes on cotton field soil conductivity estimation using single-scale UAV imagery was compared. The accuracy of soil EC estimation for cotton fields was compared between multi-spatial scale and single-scale UAV image features. The optimal combination strategy for a multi-spatial scale and multiple features was determined. Results indicate that combining spectral and texture features yields the highest estimation accuracy for cotton field soil electrical conductivity in single-scale analysis. Multi-spatial scale image features outperform single-scale image features in estimating cotton field soil electrical conductivity accuracy. By comparing different feature combinations, when integrating 0.5 m spatial-scale spectra (S1, EVI, DVI, NDVI, Int1, SI) with 0.1 m texture features (RE1_ent, R_cor, RE1_cor, G_hom, B_mea, R_con, NIR_con), the XGBoost model achieved the optimal prediction accuracy ($R^2$ = 0.693, RMSE = 0.515 dS/m), outperforming the methods using multiple features at a single scale. This study developed a novel multi-scale image feature fusion technique to construct a machine learning model. This method describes the image characteristics of soil electrical conductivity at different geographical scales, providing a reference approach for the rapid and accurate prediction of soil electrical conductivity in arid regions. Full article

Accurate weed mapping in cereal fields requires pixel-level segmentation from unmanned aerial vehicle (UAV) imagery that remains reliable across fields, seasons, and illumination. Existing multispectral pipelines often depend on thresholded vegetation indices, which are brittle under radiometric drift and mixed crop–weed pixels, or on single-stream convolutional neural network (CNN) and Transformer backbones that ingest stacked bands and indices, where radiance cues and normalized index cues interfere and reduce sensitivity to small weed clusters embedded in crop canopy. We propose VISA (Vegetation Index and Spectral Attention), a two-stream segmentation network that decouples these cues and fuses them at native resolution. The radiance stream learns from calibrated five-band reflectance using local residual convolutions, channel recalibration, spatial gating, and skip-connected decoding, which preserve fine textures, row boundaries, and small weed structures that are often weakened after ratio-based index compression. The index stream operates on vegetation-index maps with windowed self-attention to model local structure efficiently, state-space layers to propagate field-scale context without quadratic attention cost, and Slot Attention to form stable region descriptors that improve discrimination of sparse weeds under canopy mixing. To support supervised training and deployment-oriented evaluation, we introduce BAWSeg, a four-year UAV multispectral dataset collected over commercial barley paddocks in Western Australia, providing radiometrically calibrated blue, green, red, red edge, and near-infrared orthomosaics, derived vegetation indices, and dense crop, weed, and other labels with leakage-free block splits. On BAWSeg, VISA achieves 75.6% mean Intersection over Union (mIoU) and 63.5% weed Intersection over Union (IoU) with 22.8 M parameters, outperforming a multispectral SegFormer-B1 baseline by 1.2 mIoU and 1.9 weed IoU. Under cross-plot and cross-year protocols, VISA maintains 71.2% and 69.2% mIoU, respectively. The full BAWSeg benchmark dataset, VISA code, trained model weights, and protocol files will be released upon publication. Full article

To improve cotton yield and water–nitrogen productivity in arid southern Xinjiang under climate change, field experiments conducted in 2024 (for calibration) and 2025 (for validation) were conducted in Tumushuke City to evaluate planting patterns and water–nitrogen regimes. The local conventional strategy M1T3R6 (600 mm irrigation and 825 kg N ha⁻¹) served as the control. Under the one-film–three-pipes–four-rows pattern (M1T3R4), three irrigation quotas (360, 450, and 540 mm) were combined with three N rates (495, 619, and 743 kg ha⁻¹), and the AquaCrop model was calibrated and validated. Using 40-year (1984–2023) meteorological data and SPEI-6, hydrological years were classified into four categories: wet (Y1), normal (Y2), dry (Y3), and extreme drought (Y4). Simulations assessed cotton yield (Y), water productivity (WP), and partial factor productivity of nitrogen (PFPN) under different managements, and NSGA-II with TOPSIS was used for multi-objective optimization. AquaCrop performed well for canopy cover, soil water, evapotranspiration, and yield (R² > 0.81; d > 0.85). Y, WP, and PFPN declined significantly with increasing drought severity. Compared with M1T3R6, M1T3R4 increased soil water and PFPN while reducing water and N inputs. Optimization for Y1–Y4 identified irrigation intervals of 529.9–599.1 mm and nitrogen intervals of 551.8–584.9 kg/ha, which increased yield by 8.85–21.82% while reducing irrigation by 8.33–14.15% and nitrogen by 58.6–78.1% relative to M1T3R6. Full article

To address the localization and mapping challenges for quadruped robots autonomously scouting under corn canopies, this paper proposes CK-SLAM, a SLAM algorithm integrating robot motion constraints and crop row features. The algorithm is implemented on the Jueying Mini quadruped robot, fusing data from 3D LiDAR, IMU, and joint sensors. First, an Invariant Extended Kalman Filter (InEKF) fuses multi-source motion information, dynamically adjusting observation noise via a foot contact probability model (derived from joint torque data) to achieve initial motion state estimation and reliable pose references for point cloud deskewing. Second, three feature extraction schemes are designed, inheriting line/plane features from LeGO-LOAM and adding an innovative crop plane feature extraction module, which uses grid filtering, differential evolution for crop row detection, and RANSAC plane fitting to capture corn plant structural features. Finally, a two-step Levenberg–Marquardt iteration realizes feature matching and pose optimization, with factor graph optimization fusing motion constraints and laser odometry for global trajectory and map refinement. CK-SLAM effectively adapts to gait-induced measurement noise and enhances feature matching stability under canopies. Experimental validation across four corn growth stages shows it achieves an average Absolute Pose Error (APE) RMSE of 2.0939 m (15.7%/56.4%/72.2% lower than A-LOAM/LeGO-LOAM/Point-LIO) and an average Relative Pose Error (RPE) RMSE of 0.0946 m, providing high-precision navigation support for automated field monitoring. Full article

Canopy configuration affects crop yields by optimizing radiation interception and/or use efficiency in greenhouses. Although tomato metrics have been reported, the effects of row spacing on growth, yield and radiation for different cultivars are not well documented. Here, we examined tomato growth, yield, radiation interception and use efficiency in a greenhouse with four row spacing patterns (T1: 50 cm, T2: 60 cm, T3: 70 cm and T4: 80 cm) and two tomato cultivars (Aomeila1618 and Zhefen202) over a two-year period. A constructed intermediate model was used to simulate tomato radiation interception. Although there were great differences in the genotypes between the two selected cultivars, 50 cm (T1) was the optimal row spacing to produce a larger leaf area per unit of land area, intercept more radiation and ultimately achieve higher yield than the other three row spacing patterns (T2, T3 and T4). The mean total radiation interception across years and cultivars was 559.43 MJ m⁻² in T1, 2.8–3.8% higher than in the other three row spacing patterns. Despite similar dry matter and RUE to Aomeila1618, Zhefen202 in the narrow strip used light more efficiently. These results will help to optimize canopy structures by taking cultivar-specific responses in RUE and growth traits into consideration for high-efficiency tomato production in greenhouses. Full article

Monitoring groundcover diversity in vineyards is a complex task, often limited by the time and expertise required for accurate botanical identification. Remote sensing technologies and AI-based tools are still underutilized in this context, particularly for classifying herbaceous vegetation in inter-row areas. In this study, we introduce a novel approach to classify the groundcover into one of nine categories, in order to simplify this task. Using UAV images to train a convolutional neural network through a deep learning methodology, this study evaluates the effectiveness of different backbone structures applied to a UNet network for the classification of pixels into nine classes of groundcover: vine canopy, bare soil, and seven distinct cover crop community types. Our results demonstrate that the UNet model, especially when using an EfficientNetB0 backbone, significantly improves classification performance, achieving 85.4% accuracy, 59.8% mean Intersection over Union (IoU), and a Jaccard index of 73.0%. Although this study demonstrates the potential of integrating remote sensing and deep learning for vineyard biodiversity monitoring, its applicability is limited by the small image coverage, as data were collected from a single vineyard and only one drone flight. Future work will focus on expanding the model’s applicability to a broader range of vineyard systems, soil types, and geographic regions, as well as testing its performance on lower-resolution multispectral imagery to reduce data acquisition costs and time, enabling large-scale and cost-effective monitoring. Full article

Agrivoltaics, an emerging approach that integrates solar energy generation with agricultural production, offers an effective solution to land-use conflicts by enabling the simultaneous production of clean energy and crops. However, the shading effect of photovoltaic (PV) modules significantly alters both the quantity and distribution of light within crop canopies, creating challenges in balancing power output with crop light requirements. This study employs the Rhino–Grasshopper parametric modeling platform, combined with Ladybug and PVsyst, to conduct batch simulations of 44 configuration schemes for an agrivoltaic system in Lianyungang, Jiangsu Province. Annual simulations of the light environment and energy generation were performed, and model accuracy was validated through field measurements using Daily Light Integral (DLI), light uniformity (coefficient of variation, CV), and annual energy yield as key indicators to assess the effects of different module layouts and tilt angles. The results reveal pronounced seasonal variations in the system’s light environment. The tilt angle exhibits a seasonal reversal pattern: higher tilt angles in winter and spring substantially reduce DLI (up to a 44% decrease under high ground coverage ratio, GCR, conditions), whereas moderate tilt angles in summer and autumn enhance light transmission, with low-GCR layouts enabling DLI values exceeding 30.6 mol·m⁻²·d⁻¹. Light uniformity was highest in the dual-row layout with 0.2 m spacing, maintaining a CV between 0.16 and 0.18. Energy yield peaked at a 30 tilt angle, showing a parabolic response pattern. Overall, this study proposes a photovoltaic module layout design method based on seasonal light distribution characteristics and the balance between agricultural and energy production goals. This method provides a scientific basis for structural layout planning and planting-model design in agrivoltaic systems and contributes to improving light-energy utilization efficiency and agricultural output, thereby achieving synergistic benefits between photovoltaic power generation and crop production. Full article

Sclerotinia sclerotiorum (Lib.) de Bary, the causal agent of Sclerotinia stem rot (SSR) or white mold, is a soil-borne hemibiotrophic fungus that causes substantial soybean yield losses worldwide. This pathogen infects over 400 plant species and persists in soil for extended periods through melanized sclerotia, which can survive under extreme environmental conditions. The wide host range, environmental adaptability, and longevity of sclerotia make SSR a persistent challenge in soybean production. No single management tactic provides reliable control, which underscores the importance of integrated pest management (IPM). Cultural practices such as crop rotation with non-hosts, optimized row spacing, adjusted seeding rates, and targeted irrigation are fundamental to reducing inoculum and modifying canopy microclimates to slow infection. Although genetic resistance remains partial, the deployment of cultivars with stable performance across environments contributes to disease suppression, particularly when combined with fungicide applications. However, fungicide efficacy is inconsistent and limited due to environmental concerns and potential resistance. Advances in disease modeling have improved the timing and precision of chemical control, while biological control agents and RNA interference approaches offer promising future options. This review synthesizes current IPM strategies for SSR and explores emerging alternatives to support sustainable soybean production. Full article

Row crops are regarded as a transitional type between continuous and discrete vegetation. Previous studies idealized row crops as periodic hedgerows with rectangular cross-sections. However, these models relied on oversimplified assumptions, failing to capture the intrinsic heterogeneity of canopy or its dynamic evolution over the life cycle. In 2020, we proposed a row crop model with a gradual decrease in leaf area volume density (LAVD) from the center of the row to the edge, partially overcoming these limitations. Building on this previous model, this paper introduces the leaf shape factor proposed by Mõttus et al. into the model. Three control parameters, a leaf width control parameter (β), leaf length control parameter (ψ), and leaf azimuth control parameter (e), are proposed to regulate the spatial distribution of LAVD. Additionally, an empirical exponential function from Watanabe et al. is adopted to describe the leaf zenith angle distribution, enabling the realistic calculation of the G-function and Γ-function in conjunction with leaf azimuth distribution. The LAVD is formulated at three hierarchical scales: individual scale, row scale, and scene scale. The model delivers two key advancements: enabling pronounced spatial heterogeneity and high tunability of the LAVD, and accurately simulating row crops throughout the life cycle, which bridges the row structure and continuous stages of row crops. Radiative transfer simulations are conducted to derive the bidirectional reflectance distribution function (BRDF), which is validated against the discrete anisotropic radiative transfer (DART) model. Comparisons across three growth stages demonstrated good consistency. Furthermore, this paper investigates the sensitivity of the BRDF to three control parameters (β, ψ, and e). The results indicate that changes in three parameters significantly affect the reflectance in the darkspot direction, leading to a maximum error of 22.6%. In carrying out remote sensing applications such as parameter inversion and yield estimation for row crops, the new model is recommended for more accurate BRDF simulations. Full article

Navigation line extraction is vital for visual navigation with agricultural machinery. The current methods primarily utilize plant canopy detection frames to extract feature points for navigation line fitting. However, this approach is highly susceptible to environmental changes, causing position instability and reduced extraction accuracy. To address this problem, this study aims to develop a robust navigation line extraction method that overcomes canopy-based feature instability. We propose extracting feature points from root detection frames for navigation line fitting. Compared to canopy points, root feature point positions remain more stable under natural interference and less prone to fluctuations. A dataset of corn crop row images under multiple growth environments was collected. Based on YOLOv8n (You Only Look Once version 8, nano model), we proposed the RS-LineNet lightweight model and introduced a root subordination relationship filtering algorithm to further improve detection precision. Compared with the YOLOv8n model, RS-LineNet achieves 4.2% higher precision, 16.2% improved recall, and an 11.8% increase in mean average precision (mAP₅₀), while reducing the model weight and parameters to 32% and 23% of the original. Navigation lines extracted under different environments exhibit an 0.8° average angular error, which is 3.1° lower than canopy-based methods. On Jetson TX2, the frame rate exceeds 12 FPS, meeting practical application requirements. Full article

Precise monitoring of vegetative growth is essential for assessing crop responses to environmental changes. Conventional methods of geometric characterization of plants such as RGB imaging, multispectral sensing, and manual measurements often lack precision or scalability for growth monitoring of rice. LiDAR offers high-resolution, non-destructive 3D canopy characterization, yet applications in rice cultivation across different growth stages remain underexplored, while LiDAR has shown success in other crops such as vineyards. This study addresses that gap by using LiDAR for geometric characterization of rice plants at early, middle, and late growth stages. The objective of this study was to characterize rice plant geometry such as plant height, canopy volume, row distance, and plant spacing using the proximal LiDAR sensing technique at three different growth stages. A commercial LiDAR sensor (model: VPL−16, Velodyne Lidar, San Jose, CA, USA) mounted on a wheeled aluminum frame for data collection, preprocessing, visualization, and geometric feature characterization using a commercial software solution, Python (version 3.11.5), and a custom algorithm. Manual measurements compared with the LiDAR 3D point cloud data measurements, demonstrating high precision in estimating plant geometric characteristics. LiDAR-estimated plant height, canopy volume, row distance, and spacing were 0.5 ± 0.1 m, 0.7 ± 0.05 m³, 0.3 ± 0.00 m, and 0.2 ± 0.001 m at the early stage; 0.93 ± 0.13 m, 1.30 ± 0.12 m³, 0.32 ± 0.01 m, and 0.19 ± 0.01 m at the middle stage; and 0.99 ± 0.06 m, 1.25 ± 0.13 m³, 0.38 ± 0.03 m, and 0.10 ± 0.01 m at the late growth stage. These measurements closely matched manual observations across three stages. RMSE values ranged from 0.01 to 0.06 m and r² values ranged from 0.86 to 0.98 across parameters, confirming the high accuracy and reliability of proximal LiDAR sensing under field conditions. Although precision was achieved across growth stages, complex canopy structures under field conditions posed segmentation challenges. Further advances in point cloud filtering and classification are required to reliably capture such variability. Full article