Yun Yang , Jinxin Wang , Lulu Li , Haofei Yang , Yu Quan , Jason Jia Shun Liao , Wei Ouyang , Gang Yu , Li Ling
{"title":"Unleashing the power of receptor-based assay on high-throughput detection: Assessing the feasibility of enzyme-linked immunosorbent assay on large-scale antibiotic monitoring","authors":"Yun Yang , Jinxin Wang , Lulu Li , Haofei Yang , Yu Quan , Jason Jia Shun Liao , Wei Ouyang , Gang Yu , Li Ling","doi":"10.1016/j.emcon.2025.100511","DOIUrl":"10.1016/j.emcon.2025.100511","url":null,"abstract":"<div><div>Antibiotics are detected in aquatic environments with heterogeneity in their occurrence and associated risk levels. Thus, high spatiotemporal resolution monitoring in a large scale is essential to better cope with their risks. Mass spectrometry (MS) techniques are sensitive and precise, yet complex, expensive, and time-consuming for antibiotic detection. The enzyme-linked immunosorbent assay (ELISA) is among a mature receptor-based assays that offer a cost-effective alternative and are particularly notable for their high throughput analytical capabilities. However, its high throughput power on environmental monitoring is underutilized. ELISA is remarkably rapid (3800–37,000 tests per day), inexpensive ($1.8 per test, capital costs ranging from $35,000 to $270,000), and ready-to-use (97 commercial kits available) for detecting frequently reported antibiotics. Adopting solid phase extraction decreases their limits of detection to as low as 0.125 ng/L. Their quantification results are robust as they also generally agreed well with those of MS methods. A conservative way at present is to use ELISA for initial screening of large numbers of samples, with subsequent quantification of a small proportion of “positive” samples through MS methods. Yet, the applicability of ELISA can be further improved, such as developing a standardized quantification procedure for ELISA and microfluid chip-based ELISA kits and instruments.</div></div>","PeriodicalId":11539,"journal":{"name":"Emerging Contaminants","volume":"11 3","pages":"Article 100511"},"PeriodicalIF":5.3,"publicationDate":"2025-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143891603","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Enhancing maize LAI estimation accuracy using unmanned aerial vehicle remote sensing and deep learning techniques","authors":"Zhen Chen , Weiguang Zhai , Qian Cheng","doi":"10.1016/j.aiia.2025.04.008","DOIUrl":"10.1016/j.aiia.2025.04.008","url":null,"abstract":"<div><div>The leaf area index (LAI) is crucial for precision agriculture management. UAV remote sensing technology has been widely applied for LAI estimation. Although spectral features are widely used for LAI estimation, their performance is often constrained in complex agricultural scenarios due to interference from soil background reflectance, variations in lighting conditions, and vegetation heterogeneity. Therefore, this study evaluates the potential of multi-source feature fusion and convolutional neural networks (CNN) in estimating maize LAI. To achieve this goal, field experiments on maize were conducted in Xinxiang City and Xuzhou City, China. Subsequently, spectral features, texture features, and crop height were extracted from the multi-spectral remote sensing data to construct a multi-source feature dataset. Then, maize LAI estimation models were developed using multiple linear regression, gradient boosting decision tree, and CNN. The results showed that: (1) Multi-source feature fusion, which integrates spectral features, texture features, and crop height, demonstrated the highest accuracy in LAI estimation, with the R<sup>2</sup> ranging from 0.70 to 0.83, the RMSE ranging from 0.44 to 0.60, and the rRMSE ranging from 10.79 % to 14.57 %. In addition, the multi-source feature fusion demonstrates strong adaptability across different growth environments. In Xinxiang, the R<sup>2</sup> ranges from 0.76 to 0.88, the RMSE ranges from 0.35 to 0.50, and the rRMSE ranges from 8.73 % to 12.40 %. In Xuzhou, the R<sup>2</sup> ranges from 0.60 to 0.83, the RMSE ranges from 0.46 to 0.71, and the rRMSE ranges from 10.96 % to 17.11 %. (2) The CNN model outperformed traditional machine learning algorithms in most cases. Moreover, the combination of spectral features, texture features, and crop height using the CNN model achieved the highest accuracy in LAI estimation, with the R<sup>2</sup> ranging from 0.83 to 0.88, the RMSE ranging from 0.35 to 0.46, and the rRMSE ranging from 8.73 % to 10.96 %.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"15 3","pages":"Pages 482-495"},"PeriodicalIF":8.2,"publicationDate":"2025-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143898806","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":"Mapping of soil sampling sites using terrain and hydrological attributes","authors":"Tan-Hanh Pham , Kristopher Osterloh , Kim-Doang Nguyen","doi":"10.1016/j.aiia.2025.04.007","DOIUrl":"10.1016/j.aiia.2025.04.007","url":null,"abstract":"<div><div>Efficient soil sampling is essential for effective soil management and research on soil health. Traditional site selection methods are labor-intensive and fail to capture soil variability comprehensively. This study introduces a deep learning-based tool that automates soil sampling site selection using spectral images. The proposed framework consists of two key components: an extractor and a predictor. The extractor, based on a convolutional neural network (CNN), derives features from spectral images, while the predictor employs self-attention mechanisms to assess feature importance and generate prediction maps. The model is designed to process multiple spectral images and address the class imbalance in soil segmentation.</div><div>The model was trained on a soil dataset from 20 fields in eastern South Dakota, collected via drone-mounted LiDAR with high-precision GPS. Evaluation on a test set achieved a mean intersection over union (mIoU) of 69.46 % and a mean Dice coefficient (mDc) of 80.35 %, demonstrating strong segmentation performance. The results highlight the model's effectiveness in automating soil sampling site selection, providing an advanced tool for producers and soil scientists. Compared to existing state-of-the-art methods, the proposed approach improves accuracy and efficiency, optimizing soil sampling processes and enhancing soil research.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"15 3","pages":"Pages 470-481"},"PeriodicalIF":8.2,"publicationDate":"2025-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143887644","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":"Thermal Nitridation Deoxygenation and Biotribological Properties of Zr2.5Nb","authors":"Liuwang Zhang, Jiangchuan Xu, Hao Liu, Yong Luo","doi":"10.1049/bsb2.70005","DOIUrl":"https://doi.org/10.1049/bsb2.70005","url":null,"abstract":"<p>Zirconium and its alloys are considered to be materials for artificial joints because of their excellent biocompatibility. In this study, we proposed the introduction of high-purity iron beads as external deoxidisers to inhibit the oxidation of Zr2.5Nb during thermal nitriding and investigated the biotribological properties of this alloy after deoxidation. Zr2.5Nb samples were subjected to deoxidation thermal nitriding at 900°C and 1000°C for 4 h. The main phase on the surface was ZrN, which was accompanied by a minor phase of unsaturated zirconium oxides (ZrO<sub>0.33</sub>, ZrO<sub>0.27</sub>). The thickness of the ZrN ceramic layer increased from 5.26 ± 0.37 μm to 7.78 ± 0.19 μm. During electrochemical friction–corrosion test, the open-circuit potential (OCP) and coefficient of friction (COF) values for the sample prepared at 900°C were −809.8 mV and 0.3015, and those for the sample prepared at 1000°C were −682.3 mV and 0.3168. The samples that underwent deoxidation thermal nitriding exhibited better friction–corrosion resistance and a lower friction coefficient than the original sample. Additionally, the volume wear loss was reduced by 50.53% and 62.27%, also demonstrating the superior biotribological properties achieved through deoxidation thermal nitriding.</p>","PeriodicalId":52235,"journal":{"name":"Biosurface and Biotribology","volume":"11 1","pages":""},"PeriodicalIF":1.6,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/bsb2.70005","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143857136","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Spatial distribution of microplastic pollution and its relation to pollution index-based water quality status in Progo River, Indonesia","authors":"Prieskarinda Lestari, Bayu Dwi Apri Nugroho, Hanggar Ganara Mawandha, Chandra Setyawan, Eka Riskawati, Anggraeni Intan Maharani, Brillian Ravi Alvriano, Dhanny Riski Hutama, Nashita Andjani Ludmila Saraswita","doi":"10.1016/j.emcon.2025.100510","DOIUrl":"10.1016/j.emcon.2025.100510","url":null,"abstract":"<div><div>Progo River, one of the largest rivers on Java Island, serves as the primary source of clean water and irrigation for Central Java and the Special Region of Yogyakarta, Indonesia. Despite its importance, the Progo ranks among the top 20 global plastic-polluted rivers. Therefore, the objectives of this study were 1) to investigate spatial distribution and characteristics of microplastic (MP) pollution in the Progo River, and 2) to examine MP relation to the Nemerow Pollution Index (NPI) based water quality status, 15 physicochemical biological water quality parameters, flow velocity and anthropogenic factors, marking the first comprehensive effort in Indonesia. Water and MP samples were collected simultaneously from eight sampling locations. MP abundance in the Progo River ranged from 75.02 to 435.53 particles/m<sup>3</sup>. The MP characteristics were predominantly large, transparent, film-shaped particles, and identified variably as LDPE, PET, PP, PS, PAA, cellophane. The Pearson Correlation Test results revealed positive correlations between MP abundance and nine water quality parameters (TSS, turbidity, salinity, BOD, COD, phosphate, nitrate, detergent, Cd) and flow velocity. The other six parameters (pH, temperature, TDS, DO, total coliforms, Pb) and two anthropogenic factors (population number and density) were negatively correlated with MP abundance. Notably, DO exhibited a strong and significant negative correlation with MP abundance (<em>r = -0.770, p = 0.043</em>). NPI scores (2.10–16.02) revealed slight to heavy polluted levels in the Progo River and were positively correlated with MP abundance (<em>r=0.336, p=0.461</em>). Multiple Linear Regression analysis (<em>R</em><sup><em>2</em></sup> = <em>0.639</em>) identified flow velocity, BOD, COD, turbidity, total coliform, and population number as significant predictors of MP distribution. These findings emphasize the impact of MP pollution on river water quality status, highlighting the need of a novel approach to incorporate MP pollution in periodic water quality assessment to address ecological risks.</div></div>","PeriodicalId":11539,"journal":{"name":"Emerging Contaminants","volume":"11 3","pages":"Article 100510"},"PeriodicalIF":5.3,"publicationDate":"2025-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143882356","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Recognition of Fine Textures Using Friction and EEG Methods","authors":"Shousheng Zhang, Wei Tang","doi":"10.1049/bsb2.70006","DOIUrl":"https://doi.org/10.1049/bsb2.70006","url":null,"abstract":"<p>Tactile perception is essential for humans to recognise objects. This study systematically investigated the tribological behaviour of the finger and physiological response of the brain related to the width recognition of tactile perception using subjective evaluation, friction and electroencephalography methods. The results show that the texture feeling, recognition accuracy of the texture and proportion of deformation friction increased with the texture width. The average width recognition threshold of the fine texture was 45.4 μm. The load index, maximum amplitude of the vibration signal, entropy, longest vertical line and P300 amplitude were positively correlated with the texture width. P300 latency was negatively correlated with the texture width. When the texture width exceeded the width recognition thresholds of tactile perception, the main frequency of the vibration signals increased to the optimal perceptual range of the Pacinian corpuscle. The nonlinear features of the vibration signal increased, and the vibration system transitioned from a homogenous state to a disrupted state. Moreover, the activation intensity and area of the brain and the speed of tactile recognition increased. The study demonstrated that the mechanical stimuli of friction and vibration generated in the touching of fine textures having various widths affected the subjective evaluation and brain response.</p>","PeriodicalId":52235,"journal":{"name":"Biosurface and Biotribology","volume":"11 1","pages":""},"PeriodicalIF":1.6,"publicationDate":"2025-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/bsb2.70006","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143831360","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yi Zhang , Yu Zhang , Meng Gao , Xinjie Wang , Baisheng Dai , Weizheng Shen
{"title":"Multimodal behavior recognition for dairy cow digital twin construction under incomplete modalities: A modality mapping completion network approach","authors":"Yi Zhang , Yu Zhang , Meng Gao , Xinjie Wang , Baisheng Dai , Weizheng Shen","doi":"10.1016/j.aiia.2025.04.005","DOIUrl":"10.1016/j.aiia.2025.04.005","url":null,"abstract":"<div><div>The recognition of dairy cow behavior is essential for enhancing health management, reproductive efficiency, production performance, and animal welfare. This paper addresses the challenge of modality loss in multimodal dairy cow behavior recognition algorithms, which can be caused by sensor or video signal disturbances arising from interference, harsh environmental conditions, extreme weather, network fluctuations, and other complexities inherent in farm environments. This study introduces a modality mapping completion network that maps incomplete sensor and video data to improve multimodal dairy cow behavior recognition under conditions of modality loss. By mapping incomplete sensor or video data, the method applies a multimodal behavior recognition algorithm to identify five specific behaviors: drinking, feeding, lying, standing, and walking. The results indicate that, under various comprehensive missing coefficients (λ), the method achieves an average accuracy of 97.87 % ± 0.15 %, an average precision of 95.19 % ± 0.4 %, and an average F1 score of 94.685 % ± 0.375 %, with an overall accuracy of 94.67 % ± 0.37 %. This approach enhances the robustness and applicability of cow behavior recognition based on multimodal data in situations of modality loss, resolving practical issues in the development of digital twins for cow behavior and providing comprehensive support for the intelligent and precise management of farms.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"15 3","pages":"Pages 459-469"},"PeriodicalIF":8.2,"publicationDate":"2025-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143873553","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":"Occurrence of micropollutants and enterobacteria in Ticino Valley: an insight of water contamination in an agricultural area with highly anthropogenic impact","authors":"Aurora Piazza , Francesca Merlo , Aseel AbuAlshaar , Francesca Piscopiello , Federica Maraschi , Alice Bernini , Melissa Spalla , Michela Sturini , Roberta Migliavacca , Giorgio Pilla , Antonella Profumo","doi":"10.1016/j.emcon.2025.100509","DOIUrl":"10.1016/j.emcon.2025.100509","url":null,"abstract":"<div><div>This study investigates the groundwater quality of an aquifer located in medium-populated area of the Ticino Valley with strong agricultural vocation. Two monitoring campaigns were carried out according to the phases of rice cultivation (pre- and post-flooding) on the subsurface and surface irrigation network, Ticino River and wastewater effluents, highlighting a diffuse contamination. The isotopic analyses evidenced mixing phenomena, with both contributions from local rainfall and irrigation network. Combining chemical and microbiological approaches, the anthropogenic impact was evaluated by analysing a selection of traditional and emerging pollutants, such as pesticides, antibiotics and hormones, and assessing the extent of enterobacterial contamination and potential antibiotic resistance genes. Most of the investigated contaminants were found in concentrations from 0.1 ng/L to 632 ng/L, with the exception of Glyphosate and AMPA up to 5 and 20 μg/L, respectively. Even at these low concentrations, contamination of water resources is a serious issue because long-term exposure to such pollutants may cause detrimental effects. The most frequently detected pesticide was the fungicide Tricyclazole, while glucocorticoid Dexamethasone was the most frequent steroid hormone. Noteworthy is the ubiquity of Trimethoprim and a recurrent presence of fluoroquinolones. The occurrence of antibiotics at most sites, although at very low levels, is of environmental and public health concern, as they exert a selective pressure on bacterial populations, allowing the development of antibiotic resistant microbes, as highlighted by microbiological investigations. Indeed, a high microbial load was found in both campaigns, in particular in those sampling sites close to wastewater treatment plants, with the β-lactams and quinolones classes of antibiotics as the most affected by the phenomenon of resistance.</div></div>","PeriodicalId":11539,"journal":{"name":"Emerging Contaminants","volume":"11 3","pages":"Article 100509"},"PeriodicalIF":5.3,"publicationDate":"2025-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143847815","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Wang Dai , Kebiao Mao , Zhonghua Guo , Zhihao Qin , Jiancheng Shi , Sayed M. Bateni , Liurui Xiao
{"title":"Joint optimization of AI large and small models for surface temperature and emissivity retrieval using knowledge distillation","authors":"Wang Dai , Kebiao Mao , Zhonghua Guo , Zhihao Qin , Jiancheng Shi , Sayed M. Bateni , Liurui Xiao","doi":"10.1016/j.aiia.2025.03.009","DOIUrl":"10.1016/j.aiia.2025.03.009","url":null,"abstract":"<div><div>The rapid advancement of artificial intelligence in domains such as natural language processing has catalyzed AI research across various fields. This study introduces a novel strategy, the AutoKeras-Knowledge Distillation (AK-KD), which integrates knowledge distillation technology for joint optimization of large and small models in the retrieval of surface temperature and emissivity using thermal infrared remote sensing. The approach addresses the challenges of limited accuracy in surface temperature retrieval by employing a high-performance large model developed through AutoKeras as the teacher model, which subsequently enhances a less accurate small model through knowledge distillation. The resultant student model is interactively integrated with the large model to further improve specificity and generalization capabilities. Theoretical derivations and practical applications validate that the AK-KD strategy significantly enhances the accuracy of temperature and emissivity retrieval. For instance, a large model trained with simulated ASTER data achieved a Pearson Correlation Coefficient (PCC) of 0.999 and a Mean Absolute Error (MAE) of 0.348 K in surface temperature retrieval. In practical applications, this model demonstrated a PCC of 0.967 and an MAE of 0.685 K. Although the large model exhibits high average accuracy, its precision in complex terrains is comparatively lower. To ameliorate this, the large model, serving as a teacher, enhances the small model's local accuracy. Specifically, in surface temperature retrieval, the small model's PCC improved from an average of 0.978 to 0.979, and the MAE decreased from 1.065 K to 0.724 K. In emissivity retrieval, the PCC rose from an average of 0.827 to 0.898, and the MAE reduced from 0.0076 to 0.0054. This research not only provides robust technological support for further development of thermal infrared remote sensing in temperature and emissivity retrieval but also offers important references and key technological insights for the universal model construction of other geophysical parameter retrievals.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"15 3","pages":"Pages 407-425"},"PeriodicalIF":8.2,"publicationDate":"2025-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143837982","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}
Hao Fu , Xueguan Zhao , Haoran Tan , Shengyu Zheng , Changyuan Zhai , Liping Chen
{"title":"Effective methods for mitigate the impact of light occlusion on the accuracy of online cabbage recognition in open fields","authors":"Hao Fu , Xueguan Zhao , Haoran Tan , Shengyu Zheng , Changyuan Zhai , Liping Chen","doi":"10.1016/j.aiia.2025.04.002","DOIUrl":"10.1016/j.aiia.2025.04.002","url":null,"abstract":"<div><div>To address the low recognition accuracy of open-field vegetables under light occlusion, this study focused on cabbage and developed an online target recognition model based on deep learning. Using Yolov8n as the base network, a method was proposed to mitigate the impact of light occlusion on the accuracy of online cabbage recognition. A combination of cabbage image filters was designed to eliminate the effects of light occlusion. A filter parameter adaptive learning module for cabbage image filter parameters was constructed. The image filter combination and adaptive learning module were embedded into the Yolov8n object detection network. This integration enabled precise real-time recognition of cabbage under light occlusion conditions. Experimental results showed recognition accuracies of 97.5 % on the normal lighting dataset, 93.1 % on the light occlusion dataset, and 95.0 % on the mixed dataset. For images with a light occlusion degree greater than 0.4, the recognition accuracy improved by 9.9 % and 13.7 % compared to Yolov5n and Yolov8n models. The model achieved recognition accuracies of 99.3 % on the Chinese cabbage dataset and 98.3 % on the broccoli dataset. The model was deployed on an Nvidia Jetson Orin NX edge computing device, achieving an image processing speed of 26.32 frames per second. Field trials showed recognition accuracies of 96.0 % under normal lighting conditions and 91.2 % under light occlusion. The proposed online cabbage recognition model enables real-time recognition and localization of cabbage in complex open-field environments, offering technical support for target-oriented spraying.</div></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":"15 3","pages":"Pages 449-458"},"PeriodicalIF":8.2,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143855790","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}