Artificial Intelligence in Agriculture最新文献

{"title":"Integrating 3D detection networks and dynamic temporal phenotyping for wheat yield classification and prediction","authors":"Honghao Zhou ,&nbsp;Bingxi Qin ,&nbsp;Qing Li ,&nbsp;Wenlong Su ,&nbsp;Shaowei Liang ,&nbsp;Haijiang Min ,&nbsp;Jingrong Zang ,&nbsp;Shichao Jin ,&nbsp;Dong Jiang ,&nbsp;Jiawei Chen","doi":"10.1016/j.aiia.2025.12.001","DOIUrl":"10.1016/j.aiia.2025.12.001","url":null,"abstract":"<div><div>Automated phenotyping of wheat growth stages from 3D point clouds is still limited. The study presents a concise framework that reconstructs multi-view UAS imagery into 3D point clouds (jointing to maturity) and performs plot-level phenotyping. A novel 3D wheat plot detection network—integrating spatial–channel coordinated attention and area attention modules—improves depth-direction feature recognition, and a point-cloud-density-based row segmentation algorithm enables planting-row-scale plot delineation. A supporting software system facilitates 3D visualization and automated extraction of phenotypic parameters. We introduce a dynamic phenotypic index of five temporal metrics (growth stage, slow growth stage, height/area reduction stage, maximum height/area difference stage, and height/area change rate) for growth-stage classification and yield prediction using static and time-series models. Experiments show strong agreement between predicted and measured plot heights (R² = 0.937); the detection net achieved AP_3D = 94.15 % and AP_BEV = 95.35 % in “easy” mode; and a Bi-LSTM incorporating dynamic traits reached 82.37 % prediction accuracy for leaf area and yield, a 6.14 % improvement over static-trait models. This workflow supports high-throughput 3D phenotyping and reliable yield estimation for precision agriculture.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"16 1","pages":"Pages 603-618"},"PeriodicalIF":12.4,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145747432","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"PlaneSegNet: A deep learning network with plane attention for plant point cloud segmentation in agricultural environments","authors":"Xin Yang ,&nbsp;Chenyi Xu ,&nbsp;Yan Wang,&nbsp;Ruixia Feng,&nbsp;Jinshi Yu,&nbsp;Zichen Su,&nbsp;Teng Miao,&nbsp;Tongyu Xu","doi":"10.1016/j.aiia.2025.10.015","DOIUrl":"10.1016/j.aiia.2025.10.015","url":null,"abstract":"<div><div>Accurately extracting plant point clouds from complex agricultural environments is essential for high-throughput phenotyping in smart farming. However, existing methods face significant challenges when processing large-scale agricultural point clouds owing to high noise levels, dense spatial distribution, and blurred structural boundaries between plant and non-plant regions. To address these issues, this study proposes PlaneSegNet, a voxel-based semantic segmentation network that incorporates an innovative plane attention module. This module aggregates projection features from the XZ and YZ planes, enhancing the model's ability to detect vertical geometric variations and thereby improving segmentation performance in boundary regions. Extensive experiments across representative agricultural scenarios at multiple scales, including open-field populations, greenhouse cultivation environments, and large-scale rural landscapes, demonstrate that PlaneSegNet significantly outperforms traditional geometry-based approaches and deep-learning models in plant and non-plant separation. By directly generating high-quality plant-only point clouds, PlaneSegNet significantly reduces reliance on manual pre-processing, offering a practical and generalisable solution for automated plant extraction across a wide range of agricultural applications. The dataset and source code used in this study are publicly available at <span><span>https://github.com/yangxin6/PlaneSegNet</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"16 1","pages":"Pages 284-299"},"PeriodicalIF":12.4,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145465552","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Maize phenological stage recognition via coordinated UAV and UGV multi-view sensing and deep learning","authors":"Jibo Yue ,&nbsp;Haikuan Feng ,&nbsp;Yiguang Fan ,&nbsp;Yang Liu ,&nbsp;Chunjiang Zhao ,&nbsp;Guijun Yang","doi":"10.1016/j.aiia.2025.12.004","DOIUrl":"10.1016/j.aiia.2025.12.004","url":null,"abstract":"<div><div>Crop phenological stages, marked by key events such as germination, leaf emergence, flowering, and senescence, are critical indicators of crop development. Accurate, dynamic monitoring of these stages is essential for crop breeding management. This study introduces a novel multi-view sensing strategy based on coordinated unmanned aerial vehicles (UAVs) and unmanned ground vehicles (UGVs), designed to capture diverse canopy perspectives for phenological stage recognition in maize. Our approach integrates multiple data streams from top-down and internal-horizontal views, acquired via UAV and UGV platforms, and consists of three main components: (i) Acquisition of maize canopy height data, top-of-canopy (TOC) digital images, canopy multispectral images, and inside-of-canopy (IOC) digital images using a UAV- and UGV-based multi-view system; (ii) Development of a multi-modal deep learning framework, MSRNet (maize-phenological stages recognition network), which fuses physiological features from the UAV and UGV sensor modalities, including canopy height, vegetation indices, TOC maize leaf images, and IOC maize cob images; (iii) Comparative evaluation of MSRNet against conventional machine learning and deep learning models. Across 12 phenological stages (V2–R6), MSRNet achieved 84.5 % overall accuracy, outperforming conventional machine learning and single-modality deep learning benchmarks by 3.8–13.6 %. Grad-CAM visualizations confirmed dynamic, stage-specific attention, with the network automatically shifting focus from TOC leaves during vegetative growth to IOC reproductive organs during grain filling. This integrated UAV and UGV strategy, coupled with the dynamic feature selection capability of MSRNet, provides a comprehensive, interpretable workflow for high-throughput maize phenotyping and precision breeding.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"16 1","pages":"Pages 643-657"},"PeriodicalIF":12.4,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145924243","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"CTGNN: UAV-satellite cross-domain transfer learning for monitoring oat growth in China’s key production areas","authors":"Pengpeng Zhang ,&nbsp;Bing Lu ,&nbsp;Jiali Shang ,&nbsp;Changwei Tan ,&nbsp;Shuchang Sun ,&nbsp;Zhuo Xu ,&nbsp;Junyong Ge ,&nbsp;Yadong Yang ,&nbsp;Huadong Zang ,&nbsp;Zhaohai Zeng","doi":"10.1016/j.aiia.2025.12.006","DOIUrl":"10.1016/j.aiia.2025.12.006","url":null,"abstract":"<div><div>Modern agricultural production necessitates real-time, precise monitoring of crop growth status to optimize management decisions. While remote sensing technologies offer multi-scale observational capabilities, conventional crop monitoring models face two critical limitations: (1) the independent retrieval of individual physiological traits, which overlooks the dynamic coupling between structural and physiological traits, and (2) inadequate cross-platform model transferability (e.g., from UAV images to satellite images), hindering the scaling of field-level precision to regional applications. To address these challenges, we proposed a deep learning-based framework, Cross-Task Growth Neural Network (CTGNN). This framework employed a dual-stream architecture to process spectral features for Leaf Area Index (LAI) and Soil Plant Analysis Development (SPAD), while using cross-trait attention mechanisms to capture their interactions. We further assessed the knowledge transfer capabilities of the model by comparing two transfer learning strategies—Transfer Component Analysis (TCA) and Domain-Adversarial Neural Networks (DANN)—in facilitating the adaptation of UAV-derived (1.3 cm/pixel) data to satellite-scale (3 m/pixel) monitoring. Validation using UAV-satellite synergetic datasets from extensively field-tested oat cultivars in China's Bashang Plateau demonstrates that CTGNN significantly reduces the prediction errors for LAI and SPAD compared with independent trait models, with RMSE reductions of 6.4–14.4 % and 10.5–15.6 %, respectively. In a cross-domain transfer learning scenario, the CTGNN model with the DANN strategy requires only 5 % of satellite-labeled data for fine-tuning to achieve regional-scale monitoring (LAI: R2 = 0.769; SPAD: R2 = 0.714). This framework provides a novel approach for the collaborative inversion of multiple crop growth traits, while its UAV-satellite cross-scale transfer capability facilitates optimal decision-making in oat variety breeding and cultivation technique dissemination, particularly in arid and semi-arid regions.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"16 1","pages":"Pages 630-642"},"PeriodicalIF":12.4,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145924150","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Advancing lightweight and efficient detection of tomato main stems for edge device deployment","authors":"Guohua Gao,&nbsp;Lifa Fang,&nbsp;Zihua Zhang,&nbsp;Jiahao Li","doi":"10.1016/j.aiia.2025.10.016","DOIUrl":"10.1016/j.aiia.2025.10.016","url":null,"abstract":"<div><div>Automated pruning and defoliation of tomato plants are essential in modern cultivation systems for optimizing canopy structure, enhancing air circulation, and increasing yield. However, detecting main stems in the field faces significant challenges, like complex background interference, limited field of view, dense foliage occlusion, and curved stems. To address those challenges while ensuring hardware friendliness, computational efficiency, and real-time response, this study proposes a lightweight tomato main stem detection, optimisation, and deployment scheme. First, an efficient semi-automatic rotated bounding box annotation strategy is employed to segment the visible main stem segments, thus improving the adaptability to curved stems. Second, the lightweight network, YOLOR-Slim, is constructed to significantly reduce model complexity while maintaining detection performance through automated iterative pruning at the group-level of channel importance and a hybrid feature-based and logic-based knowledge distillation mechanism. Finally, an efficient and real-time main stem detection is achieved by deploying the model on inference engines and embedded platforms with various types and quantization bits. Experimental results showed that YOLOR-Slim achieved 87.5 % mAP@50, 1.9G Flops, 1.4 M parameters, and 7.4 ms inference time (pre-processing, inference, and post-processing) on the workstation, representing reductions of 2.8 %, 10.0 M, and 27.5G compared to the original model. After conversion with TensorRT, the inference time on Jetson Nano reached 57.6 ms, validating the operational efficiency and deployment applicability on edge devices. The YOLOR-Slim strikes a balance between inference speed, computational resources usage, and detection accuracy, providing a reliable perceptual foundation for automated pruning tasks in precision agriculture.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"16 1","pages":"Pages 458-479"},"PeriodicalIF":12.4,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145579034","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"End-to-end detection of cough and snore based on ResNet18-TF for breeder laying hens: A field study","authors":"Haoyan Ma ,&nbsp;Peiguang Xin ,&nbsp;Juncheng Ma ,&nbsp;Xiao Yang ,&nbsp;Ruohan Zhang ,&nbsp;Chao Liang ,&nbsp;Yu Liu ,&nbsp;Fei Qi ,&nbsp;Chaoyuan Wang","doi":"10.1016/j.aiia.2025.11.002","DOIUrl":"10.1016/j.aiia.2025.11.002","url":null,"abstract":"<div><div>Cough and snore are the most representative vocalizations for chicken respiratory diseases, which severely restrict poultry health due to highly contagious and lethal characteristics. Nighttime inspection by veterinarians is the foremost solution to identify bird respiratory symptoms during production. However, it is subjective, time-consuming, and labor-intensive. This study proposed a novel end-to-end model (ResNet18-TF) based on ResNet18 and a Time-Frequency Attention Mechanism (TFBlock) to automatically recognize chicken cough and snore using data collected in a commercial layer breeder house. In addition, a comparative analysis was conducted to evaluate the performance of different input features. The results revealed that LogFbank features exhibited superiority over MFCC features in the task of chicken sound recognition. By incorporating first-order and second-order delta features into LogFbank, the combination of ‘LogFbank+ΔLogFbank+ΔΔLogFbank’ further improved model recognition accuracy by 2.34 %. Additionally, the TFBlock structure enhanced the model's performance for recognizing coughs and snores. Specifically, the F1-score of MobileViTv3-TF, EfficientNetV2-TF, and ResNet18-TF models were increased by 1.30 %, 0.88 %, and 1.84 %, respectively, compared to their respective counterparts without TFBlock. ResNet18-TF achieved the highest accuracy, precision, recall, and F1-score, with 94.37 %, 94.59 %, 94.56 %, and 94.57 %, respectively. The generalization of ResNet18-TF in real production systems was validated, with precision and recall for detecting abnormal sounds (coughs and snores) reaching 92.97 % and 87.53 %, respectively. The proposed end-to-end model does not require denoising or endpoint detection processes, constructing an efficient and user-friendly pipeline of abnormal sound detection, which is highly suitable for practical deployment in poultry production systems.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"16 1","pages":"Pages 412-422"},"PeriodicalIF":12.4,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145527920","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Improved YOLOv8 for multi-colored apple fruit instance segmentation and 3D localization","authors":"Jiaren Zhou,&nbsp;Mengyan Chen,&nbsp;Man Zhang,&nbsp;Zhao Zhang,&nbsp;Yao Zhang,&nbsp;Minjuan Wang","doi":"10.1016/j.aiia.2025.10.013","DOIUrl":"10.1016/j.aiia.2025.10.013","url":null,"abstract":"<div><div>Robotic apple harvesting requires precise instance segmentation and 3D localization, especially for multi-colored apples under complex orchard conditions with occlusions and variable lighting. Current deep learning methods lack robustness and accuracy for such scenarios, limiting automation. This study proposes improved YOLOv8-based models to enhance segmentation of multi-colored apples, combined with a high-precision 3D localization pipeline to advance practical robotic harvesting. To address these issues, this study collected apple images in three colors from two locations, creating a dataset of 5171 images. Four enhanced YOLOv8-based models—RA-YOLO, GA-YOLO, YA-YOLO, and MCA-YOLO—were proposed for segmenting red, green, yellow, and mixed multi-colored apples. RA-YOLO integrates the GD mechanism and EMBConv structure based on EfficientNet's MBConv. GA-YOLO replaces standard convolutions with dynamic serpentine convolution and adds the P6 layer for large object detection. YA-YOLO utilizes deformable convolution (DCNv2) and introduces the new attention mechanism MPCA. MCA-YOLO combines the P6 layer, DCNv2, and EMBConv structure, merging the strengths of other models. RA-YOLO, GA-YOLO, and YA-YOLO achieved mAP values of 95.2 %, 96.4 %, and 95.4 %, respectively, for single-colored apple instance segmentation, surpassing baseline models and those in existing literature. MCA-YOLO achieved mAP values of 95.6 %, 96.6 %, and 94.6 % for single-colored apples and 95.6 % for mixed multi-colored apples. Ablation experiments validated the necessity of each module. Finally, a high-precision 3D localization and shaping pipeline was developed, achieving an average localization error of 2.636 mm and a shaping error of 0.768 mm, enabling millimeter-level localization and sub-millimeter-level shaping for apple harvesting optimization.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"16 1","pages":"Pages 381-396"},"PeriodicalIF":12.4,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145527910","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Hyperspectral estimation of leaf chlorophyll content in wine grape using transfer learning and three-dimensional radiation transfer model","authors":"Qifan Chen ,&nbsp;Zhiwen Mi ,&nbsp;Qifan Wang ,&nbsp;Fahu Xu ,&nbsp;Yulin Fang ,&nbsp;Rui Wang ,&nbsp;Yuyang Song ,&nbsp;Baofeng Su","doi":"10.1016/j.aiia.2025.11.001","DOIUrl":"10.1016/j.aiia.2025.11.001","url":null,"abstract":"<div><div>Accurate and timely monitoring of leaf chlorophyll content (LCC) in wine grapes is essential for assessing their photosynthetic status, optimizing management and planting practices, and improving both yield and quality. Traditional physically-based and empirically-based estimation methods often exhibit uncertainties, and they are inadequately adapted to nonlinear relationships. In this study, a UAV hyperspectral deep learning network (VitiChlNet) for estimating LCC of wine grapes was constructed. The estimation and mapping of LCC of wine grapes of different varieties and growth stages were realized by combining the three-dimensional radiation transfer model (3D RTM) and deep transfer learning (TL) techniques. Firstly, 80,000 canopy reflectance data under different canopy structures and observation conditions were simulated using the LESS model, the simulation dataset was then pre-trained using VitiChlNet. Finally, the model was fine-tuned using the TL technique based on the measured UAV hyperspectral and LCC data. The performance of VitiChlNet was compared to empirically-based and physically-based approaches. Specifically, three machine learning (ML) empirical models, XGBoost, LightGBM, and ridge regression, were developed using five different spectral feature construction strategies: full-spectrum, vegetation indices (VIs), competitive adaptive reweighted sampling (CARS), successive projections algorithm (SPA), and uninformative variable elimination (UVE). Meanwhile, a look-up table (LUT) inversion strategy based on the LESS model was constructed. Furthermore, LCC mapping was conducted for various wine grape varieties across different growth stages. The results demonstrated that VitiChlNet outperformed other methods, exhibiting superior LCC estimation performance (R² = 0.69), and is less affected by factors such as nitrogen concentration and different interyears. The application of the TL technique enhanced LCC estimation accuracy and effectively addressed the small sample generalization problem. This study may provide a viable strategy for large-scale monitoring of LCC in wine grapes, which is of substantial significance for planting management practices.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"16 1","pages":"Pages 423-438"},"PeriodicalIF":12.4,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145527921","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Dual attention guided context-aware feature learning for residual unfilled grains detection on threshed rice panicles","authors":"Yuhao Zhou ,&nbsp;Xiao Feng ,&nbsp;Shuqi Tang ,&nbsp;Jinpeng Yang ,&nbsp;Shaobin Chen ,&nbsp;Xiangbao Meng ,&nbsp;Zhanpeng Liang ,&nbsp;Ruijun Ma ,&nbsp;Long Qi","doi":"10.1016/j.aiia.2025.11.005","DOIUrl":"10.1016/j.aiia.2025.11.005","url":null,"abstract":"<div><div>Accurate detection of residual unfilled grains on threshed rice panicles is a critical step in determining a reliable grain-setting rate, and holds significant potential for the development of high-quality rice strains. Recent deep learning-based techniques have been actively explored for discerning various types of objects. However, this detection task is challenging, as many objects are densely occluded by branches or other unfilled grains. Additionally, some unfilled grains are closely adjacent and exhibit small sizes, further complicating the detection process. To address these challenges, this paper proposes a novel Channel-global Spatial-local Dual Attention (CSDA) module, aimed at enhancing feature correlation learning and contextual information embedding. Specifically, the channel- and spatial-wise attention are deployed on two parallel branches, and incorporated with the global and local representation learning paradigm, respectively. Furthermore, we integrate the CSDA module with the backbone of an object detector, and refine the loss function and detection head using the Focaler-SIoU and tiny object prediction head. This enables the object detector to effectively differentiate residual unfilled grains from occlusions, and at the meantime, focusing on the subtle differences between closely adjacent and small-sized unfilled grains. Experimental results show that our work achieves superior detection performance versus other competitors with an [email protected] of 95.3 % (outperforming rivals by 1.5–32.6 %) and a frame rate of 154 FPS (outperforming rivals by 12–132 FPS), enjoying substantial potentials for practical applications.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"16 1","pages":"Pages 514-528"},"PeriodicalIF":12.4,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145623316","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Smart agriculture technology: Real-time generation method of local soil property distribution maps based on WGAN-GPM","authors":"Xiaoshuang Zhang ,&nbsp;Li Yang ,&nbsp;Dongxing Zhang ,&nbsp;Tao Cui ,&nbsp;Xiantao He ,&nbsp;Kailiang Zhang ,&nbsp;Zhaohui Du ,&nbsp;Zhimin Li ,&nbsp;Hongsheng Li ,&nbsp;Tianpu Xiao","doi":"10.1016/j.aiia.2025.10.014","DOIUrl":"10.1016/j.aiia.2025.10.014","url":null,"abstract":"<div><div>With the advancement of smart agriculture, precision variable-rate seeding requires high-resolution soil information. However, existing methods still fall short in generating localized soil property maps in real time, limiting inter-row seeding control for wide-span planters. To address this challenge, this paper proposes the Local Soil property distribution maps Generation Network (LSGN), based on the Wasserstein Generative Adversarial Network with Gradient Penalty and Mean squared error (WGAN-GPM). This proposed model integrates a Vision Transformer (ViT) encoder with convolutional and deconvolutional Residual Networks (ResNet), significantly improving feature extraction from discrete soil property data and enhancing the reconstruction accuracy of localized soil maps. The model adopts a two-stage training strategy. First, it performs self-supervised pre-training using local soil property maps with neighborhood information, enabling the network to learn spatial correlations and improve boundary prediction. Second, the pretrained weights are transferred into a WGAN-GPM adversarial training framework, which combines Wasserstein distance, gradient penalty, and Mean Squared Error (MSE) loss to jointly optimize the generator and discriminator. This ensures both pixel-level accuracy and distributional consistency. Compared to standard Generative Adversarial Networks (GANs), the WGAN-GPM-trained LSGN prediction reduces Relative Error Average (REA) by over 1.02 %, RMSE by over 0.16, and Kullback–Leibler Divergence (KLD) by over 1.76 × 10⁻⁴, while increasing Peak Signal-to-Noise Ratio (PSNR) by over 2.43. LSGN achieves REA values of 0.41 %, 1.19 %, and 1.80 % for planting widths of four, six, and eight rows, respectively, outperforming traditional generative models. Field cross-validation further shows that, relative to Kriging interpolation, LSGN reduces boundary region prediction errors by up to 2.42 % and central region errors by 0.97 %. Overall, the REA in local distribution maps decreases by more than 1.5 %, and RMSE is reduced by over 0.4. This study demonstrates that LSGN enables real-time high-precision soil mapping, providing a practical solution for precision seeding.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"16 1","pages":"Pages 300-315"},"PeriodicalIF":12.4,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145465551","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}