Smart agricultural technology最新文献

{"title":"Efficient detection and counting method for maize seedling plots","authors":"Feiyun Wang ,&nbsp;Hanlu Jiang ,&nbsp;Jincan Wu ,&nbsp;Fupeng Li ,&nbsp;Bo Zhao ,&nbsp;Wenhua Mao ,&nbsp;Chengxu Lv ,&nbsp;Liming Zhou ,&nbsp;Qingzhong Xu","doi":"10.1016/j.atech.2025.100914","DOIUrl":"10.1016/j.atech.2025.100914","url":null,"abstract":"<div><div>To efficiently detect and count maize seedlings in complex field conditions, this study first developed a sample dataset under diverse backgrounds and lighting scenarios and introduced a data augmentation technique called “M_AUG.” YOLOv5s was selected as the base model, enhanced with the Swin Transformer (Swin TR)to improve feature extraction across various scales and complex environments. The model also incorporated multi-scale attention (EMA)to enhance the representation of small samples and positive/negative samples, along with the Asymptotic Feature Pyramid Network (AFPN)to integrate seedling features at different levels. The results showed that the proposed SEA-YOLOv5 achieved mAP_0.5 of 98.6 %, mAP_0.5–0.95 of 73.2 %. and F1 of 97.1 %, with the parameters count of 5.55 million and a weight size of 11.7 MB. Compared to YOLOv5, SEA-YOLOv5 improved mAP_0.5 by 5.8 %, mAP_0.5–0.95 by 9.9 %, and F1 by 5.4 %, while reducing the parameter count by 1.46 million and weight size by 2.7 MB. SEA-YOLOv5 was compared with YOLOv7, YOLOv8s, Faster R-CNN, RetinaNet, YOLOv10s, DNE-YOLO, and YOLOv11s, and the results indicated that SEA-YOLOv5 outperformed the comparison models in overall performance. Upon deploying SEA-YOLOv5 on the Jetson Orin NX and conducting seedling detection and counting trials across eight plots, the model achieved a miss rate of just 0.63 % and a frame rate of 74.6 FPS. Thus, it can be concluded that the SEA-YOLOv5 model developed in this study provides high accuracy, a compact design, and strong portability, making it well-suited for real-time detection and counting applications in the field.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"11 ","pages":"Article 100914"},"PeriodicalIF":6.3,"publicationDate":"2025-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143792797","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":"Application of flow field visualization technology in analysing the influence of nutrient solution flow on hydroponic lettuce growth","authors":"Bateer Baiyin ,&nbsp;Yue Xiang ,&nbsp;Yang Shao ,&nbsp;Jung Eek Son ,&nbsp;Kotaro Tagawa ,&nbsp;Satoshi Yamada ,&nbsp;Mina Yamada ,&nbsp;Qichang Yang","doi":"10.1016/j.atech.2025.100933","DOIUrl":"10.1016/j.atech.2025.100933","url":null,"abstract":"<div><div>Nutrient solution flow is important for the growth and root morphology of lettuce in hydroponics, requiring precise regulation to optimise yield and quality. However, the mechanisms involved remain poorly understood. We examined the influence of varying nutrient solution flow rates on lettuce growth, root morphology, and nitrogen uptake. We assessed lettuce performance at five growth stages, measuring shoot and root dry and fresh weights, root morphology, and nitrogen uptake. Particle image velocimetry was employed to visualise the flow field, providing a deeper understanding of how flow patterns impact the root environment. In the early growth stage, lettuce under no flow conditions exhibited higher shoot and root biomass. However, moderate flow consistently outperformed other conditions as growth progressed, demonstrating significantly higher fresh and dry weights. High flow initially suppressed growth, highlighting the detrimental effects of excessively fast flow rates. No flow initially promoted root development, while moderate flow enhanced root growth later in the lifecycle. Nitrogen uptake analysis showed that moderate flow achieved the highest efficiency, while high flow increased nitrogen uptake flux in later stages. PIV visualisation revealed that moderate flow delivered uniform flow vectors and moderate velocity, enhancing nutrient ion contact with roots and uptake efficiency. In contrast, high flow resulted in chaotic flow vectors, high vorticity, and potential root damage, reducing uptake efficiency. Under no flow conditions, nutrient ion transport relied solely on diffusion, limiting nutrient availability during rapid growth and maturation. In conclusion, moderate flow was optimal for promoting lettuce growth and root development.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"11 ","pages":"Article 100933"},"PeriodicalIF":6.3,"publicationDate":"2025-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143823841","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":"A review of machine learning approaches for predicting lettuce yield in hydroponic systems","authors":"Sabrina Sharmin ,&nbsp;Md. Tazel Hossan ,&nbsp;Mohammad Shorif Uddin","doi":"10.1016/j.atech.2025.100925","DOIUrl":"10.1016/j.atech.2025.100925","url":null,"abstract":"<div><div>Accurate and timely yield prediction of hydroponically grown lettuce is essential for financial planning, strategic decision-making, and enhancing farmers' profitability. In controlled hydroponic environments, this prediction remains challenging, mainly due to complex factors influencing growth. Machine Learning (ML) offers advanced methods to address these challenges. This review analyzes ML techniques for forecasting lettuce yield in hydroponic systems, starting with an overview of global trends in lettuce production. It then explores core ML methodologies, key model characteristics, and application-specific features that contribute to yield prediction. A comparative analysis of existing ML models also highlights their strengths and limitations. Current challenges, such as data integration and prediction accuracy, are discussed alongside potential improvements through remote sensing, monitoring, and feature optimization. This paper concludes by proposing a framework aimed at efficient yield prediction in hydroponics, offering insights for future research and applications in agricultural technology.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"11 ","pages":"Article 100925"},"PeriodicalIF":6.3,"publicationDate":"2025-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143792796","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":"Adapting an agroecosystem model to account for cover crop management in the Midwest USA","authors":"Anna Orfanou ,&nbsp;Gregg R. Sanford ,&nbsp;Randall D. Jackson ,&nbsp;Matthew D. Ruark ,&nbsp;Claudio Gratton ,&nbsp;Dimitrios Pavlou ,&nbsp;Spyridon Mourtzinis ,&nbsp;Shawn P. Conley ,&nbsp;Christopher J. Kucharik","doi":"10.1016/j.atech.2025.100930","DOIUrl":"10.1016/j.atech.2025.100930","url":null,"abstract":"<div><div>Agroecosystem modeling tools can provide insights into cover crop performance under varying environmental and management combinations. This study aims to (1) simulate winter cereal rye cover crops in Agro-IBIS, a process-based terrestrial ecosystem model and (2) evaluate Agro-IBIS performance in predicting aboveground biomass (AGB) of winter cereal rye cover crops. To achieve this, the winter wheat plant functional type (PFT) in Agro-IBIS was adapted to represent winter cereal rye as a cool-season winter annual grass cover crop. We adjusted the specific leaf area (SLA), maximum Rubisco activity at 15 °C (V_c_,max), growing degree days (GDD) base temperature, GDD upper threshold, and planting and termination dates as indicated by observed data. Model performance was evaluated using observed data from continuous maize and maize-soybean rotation systems in southern Wisconsin. The model effectively represented interannual variability of winter cereal rye cover crop AGB that was measured in southern Wisconsin in continuous maize and maize-soybean rotation systems. This demonstrated the efficacy of Agro-IBIS in representing establishment success, cold-hardening, spring green-up, and AGB accumulation of winter cereal rye cover crops in conventional annual grain cropping systems. Environmental drivers like growing season length, accumulated GDDs, precipitation amount, and solar radiation were key drivers of cover crop AGB production, which is generally represented by Agro-IBIS. This suggests the model would be an accurate tool to use when investigating the impact of climate change or increased weather variability on the success of cover crops across the Midwest and beyond.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"11 ","pages":"Article 100930"},"PeriodicalIF":6.3,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143843320","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":"Soil moisture sensor location-allocation using spatial association of surface moisture data","authors":"Dipankar Mandal ,&nbsp;Raj Khosla ,&nbsp;Louis Longchamps ,&nbsp;Deepak Joshi","doi":"10.1016/j.atech.2025.100929","DOIUrl":"10.1016/j.atech.2025.100929","url":null,"abstract":"<div><div>Balancing cost and performance is typically required when deploying a soil moisture sensor array. The sensor array's performance is essentially dependent on the appropriate placement of the sensors, which is fundamentally a location-allocation problem. In this study, a novel approach based on spatial association of surface soil moisture (SASM) is presented. It proposes selecting a sub-sample of sensor locations that best represent the spatial distribution of soil moisture while maximizing the variance in soil moisture with the minimum number of sample sites. This approach was tested at two sites with maize cultivated fields in Colorado. Neutron probe readings were collected at 15 cm depth across 41 and 31 locations throughout the entire crop growing season in two maize fields in Colorado. The number of soil sensors were optimized in a range of 17–19 with optimum site configuration for all different data acquisition dates. A global measure of spatial association (GMSA) analysis indicated consistency in spatial pattern between reduced number of sub-samples and original samples. Strategic sensor placement, driven by insights into soil-water dynamics patterns and intrinsic field properties, is essential for informed decision-making in water management within an irrigated maize field.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"11 ","pages":"Article 100929"},"PeriodicalIF":6.3,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143792798","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":"Harnessing machine learning for grain mycotoxin detection","authors":"Rakiba Rayhana ,&nbsp;Jatinder S. Sangha ,&nbsp;Yuefeng Ruan ,&nbsp;Zheng Liu","doi":"10.1016/j.atech.2025.100923","DOIUrl":"10.1016/j.atech.2025.100923","url":null,"abstract":"<div><div>Detecting mycotoxins such as deoxynivalenol, aflatoxins, and zearalenone in grains is crucial for ensuring crop safety and maintaining consumer health, both for humans and animals. These toxins pose serious health risks, affect the marketability of grains in international markets, and influence their economic value. Hence, this paper reviews the use of machine learning (ML) in detecting and managing grain mycotoxins to transform grain safety measures. The review will cover the common mycotoxins in grains, their adverse effects, and techniques for detecting mycotoxin data. It describes the latest ML models for detecting or predicting these toxins. The paper evaluates the effectiveness of these ML techniques, identifies research gaps, and suggests potential solutions. Overall, this review establishes a comprehensive baseline for future research on grain mycotoxin detection, assessing the extent to which various ML methodologies have been explored. This paper aims to create a foundational understanding for readers about the state-of-the-art techniques in ML. This area will further advance readers' knowledge of detecting and managing mycotoxins in grains.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"11 ","pages":"Article 100923"},"PeriodicalIF":6.3,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143758950","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":"Dilated inception U-Net with attention for crop pest image segmentation in real-field environment","authors":"Congqi Zhang ,&nbsp;Yunlong Zhang ,&nbsp;Xinhua Xu","doi":"10.1016/j.atech.2025.100917","DOIUrl":"10.1016/j.atech.2025.100917","url":null,"abstract":"<div><div>Automatic pest image segmentation (PIS) plays a vital role in pest detection and recognition. However, it remains a difficult issue due to the various irregular pest images and low contrast between pests and their surroundings. A dilated Inception U-Net with attention (DIAU-Net) is constructed for PIS. It is a U-shape encoder–decoder multi-scale convolution model, consisting dilated residual Inception (DRI), multi-scale feature fusion (MSFF), and multi-scale dilated attention (MSDA), where DRI instead of the convolution is employed to capture the multi-scale local features, MSFF is added into the bottleneck layer to extract the semantic information, and MSDA instead of skip connection is used to fuse the extracted low-level features and high-level features. Experimental results on a crop pest image dataset validate that DIAU-Net based PIS method outperforms other state-of-the-art PIS methods, with Dice score of 93.12 % compared to 82.35 % for the U-Net based method. The proposed method can provide valuable support for the detection, identification and severity estimation of crop pests in real field environment.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"11 ","pages":"Article 100917"},"PeriodicalIF":6.3,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143784001","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":"GAN-based motion blur elimination as a preprocessing step for enhanced AI-driven computer-aided camera monitoring in poultry and free-range farming in low-resource settings","authors":"Shwetha V ,&nbsp;Maddodi B S ,&nbsp;Sheikh Adil ,&nbsp;Vijaya Laxmi ,&nbsp;Sakshi Shrivastava","doi":"10.1016/j.atech.2025.100915","DOIUrl":"10.1016/j.atech.2025.100915","url":null,"abstract":"<div><div>Accurately determining poultry gender ratios is essential for assessing the economic value of free-range farming, particularly in resource-limited settings. Traditional and manual methods for gender identification are often labor-intensive, time-consuming, and prone to errors, especially in the early stages of poultry development. To address these challenges, this study introduces an automated approach that uses advanced machine learning techniques. Specifically, we propose a classification framework that integrates Convolutional Neural Networks (CNNs) with Generative Adversarial Networks (GANs) to enhance the accuracy of poultry gender identification. Our framework incorporates a novel GAN-based motion blur elimination method, which is broadly applicable to detect and classify moving subjects, including poultry. The proposed approach demonstrates a 98% accuracy in distinguishing between male and female birds at early growth stages by analyzing key features such as crown pixel measurements, feather gap analysis, and leg measurements. Furthermore, we conduct a comprehensive comparison of four segmentation models—UNet, ResUNet, ResUNet+, and a novel GAN-enhanced UNet—under varying motion blur conditions (80%, 50%, 30%, and 10%). Our results highlight the superiority of ResUNet+ over conventional models, achieving a peak Dice Coefficient of 91.2%, an Intersection over Union (IoU) of 86.7%, and the highest segmentation accuracy at reduced blur levels. These findings underscore the efficacy of deep learning-based approaches in advancing poultry gender classification while improving image quality in dynamic environments.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"11 ","pages":"Article 100915"},"PeriodicalIF":6.3,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143768250","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":"A real-time crop lodging recognition method for combine harvesters based on machine vision and modified DeepLab V3+","authors":"Cong Yao,&nbsp;Dawei Lv,&nbsp;Hua Li,&nbsp;Jieyi Fu,&nbsp;Chao Li,&nbsp;Xiaojun Gao,&nbsp;Daolong Hong","doi":"10.1016/j.atech.2025.100926","DOIUrl":"10.1016/j.atech.2025.100926","url":null,"abstract":"<div><div>To minimize the losses during the harvest of lodged crops, an effective recognition method of crop lodging is particularly important for combine harvesters. This study presents a method for real-time monitoring of crop lodging using machine vision and semantic segmentation, offering an alternative to traditional manual inspection techniques. Firstly, the DeepLab V3+ model was applied to the recognition of lodging areas, with modifications made to meet the harvesting requirements. Xception served as the backbone network during training to improve accuracy, while MobileNet V2 was adopted during deployment to balance accuracy with computational efficiency. Next, a RealSense depth camera was installed on the combine harvester cabin to enable image data collection and crop height recognition. Finally, a ROS (Robot Operation System) framework was designed and implemented on a Jetson Nano board to integrate lodging area recognition with crop height measurement. Experimental results demonstrated that the proposed method achieved a recognition pixel accuracy (PA) of 93.83% and a mean intersection over union (mIoU) of 85.3% for lodging areas, and 93.77% PA and 83.97% mIoU for non-lodging areas. Crop height recognition errors below 4%, meeting the standards required for real-time recognition. In general, this solution proved to be cost-effective, easy to deploy, and highly accurate, making it well suited for practical application in harvesters and offering valuable insight to reduce harvest losses.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"11 ","pages":"Article 100926"},"PeriodicalIF":6.3,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143817376","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":"Industrial tomato yield prediction using machine learning models","authors":"Christoforos-Nikitas Kasimatis ,&nbsp;Evangelos Psomakelis ,&nbsp;Nikolaos Katsenios ,&nbsp;Marilena Papatheodorou ,&nbsp;Dimitrios Apostolou ,&nbsp;Aspasia Efthimiadou","doi":"10.1016/j.atech.2025.100920","DOIUrl":"10.1016/j.atech.2025.100920","url":null,"abstract":"<div><div>Tomato is steadily the most produced and consumed vegetable in the world during the last decade. The wide availability of data produced by the worldwide industrial tomato cultivation efforts, in combination with the power of machine learning algorithms, allows the identification of patterns and hidden variable correlations that allows the creation of accurate prediction models. These models can be used to accurately predict the yield of cultivations under various conditions and environments. In the present study, a machine learning platform was developed, able to predict the yield of industrial tomato crops during their cultivation period, based on historical data (yield, the hybrid cultivated and the environmental conditions of the area). These data were extracted from 302 different fields in six regions of western Peloponnese, Greece. They include data from 2019 to 2021 with 26 different tomato hybrids being cultivated during three cultivation periods, one per year. A correlation study was conducted on the dataset confirming that most of the variables are correlated to some degree to the crop yield. In order to find the optimal algorithm for this dataset, 12 different algorithms were tested and ranked using 14 different metrics. In addition, a hyper-parameter optimization process ensured that each tested algorithm is optimized for the dataset under examination. The presented solution is using the Ridge algorithm as it was deemed the most appropriate. The model was tested on open field cultivations, predicting the yield of tomato crops within the cultivation period, using real time weather data for 11 fields during the 2022 cultivation period. The observed prediction error ranged from just 6 up to 6,674 kg/ha, which was considered as acceptable by the producers. The uniqueness of the presented study lies in the fact that the model was both trained and tested in open field cultivations using in-season environmental data.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"11 ","pages":"Article 100920"},"PeriodicalIF":6.3,"publicationDate":"2025-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143768249","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}