Smart agricultural technology最新文献

{"title":"Recognition of rice seedling counts in UAV remote sensing images via the YOLO algorithm","authors":"Shengxi Chen ,&nbsp;Wenli Li ,&nbsp;Du Chen ,&nbsp;Zhao Xie ,&nbsp;Song Zhang ,&nbsp;Fulang Cen ,&nbsp;Xiaoyun Huang ,&nbsp;Lei Tu ,&nbsp;Zhenran Gao","doi":"10.1016/j.atech.2025.101107","DOIUrl":"10.1016/j.atech.2025.101107","url":null,"abstract":"<div><div>Accurate identification of rice seedling numbers is essential for breeding, replanting, and yield prediction. Traditional manual counting methods are inefficient and prone to error. The integration of high-resolution drone imagery with the feature extraction capabilities of deep learning offers a novel approach for identifying rice seedlings using advanced computational techniques. This study employed drone-captured images of rice seedlings taken at heights of 12 m and 15 m from two locations—Anshun City and Qianxinan Prefecture in Guizhou Province—to construct datasets containing 100, 150, and 200 images, and compared the performance of YOLOv8n, YOLOv9t, and YOLOv10n in recognizing rice seedling numbers. The results show that at a flight height of 12 m and using a dataset of 200 images, model performance was optimal, achieving mAP@50 values of 0.964, 0.936, and 0.944 for YOLOv8n, YOLOv9t, and YOLOv10n, respectively. Among these, YOLOv8n demonstrated the highest prediction accuracy for rice seedlings, with an R² value of 0.889, RMSE of 3.225, and rRMSE of 0.032. This research demonstrates that the combination of drone imagery and deep learning models enables effective large-scale counting of rice seedlings, presenting an innovative approach to rice phenotypic analysis.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"12 ","pages":"Article 101107"},"PeriodicalIF":6.3,"publicationDate":"2025-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144313876","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":"Regression-based artificial intelligence length and weight estimation for sustainable prawn aquaculture","authors":"Najeebah Az-Zahra Tashim ,&nbsp;Tiong Hoo Lim ,&nbsp;Wafiq Zariful ,&nbsp;Pengcheng Liu","doi":"10.1016/j.atech.2025.101089","DOIUrl":"10.1016/j.atech.2025.101089","url":null,"abstract":"<div><div>The need for sustainable aquaculture practices has become very important to ensure sufficient production in addressing the increasing global demand for seafood. In this context, accurately assessing the size and weight of prawns is pivotal for efficient farming and resource utilization, allowing farmers to make informed decisions and productions. The integration of advanced AI algorithms into aquaculture practices holds great promise for fostering sustainability, thereby enhancing the overall productivity and resilience of prawn farming in the face of growing global challenges. This paper compares different length-weight regression techniques to estimate the weight of prawns and proposed a novel Regression-based Artificial Intelligence Biomass Estimation (RAIBE) systems for prawn aquaculture. RAIBE leverages deep learning and regression models to estimate the weight from images captured from a mobile device. The proposed methodology employs YOLOv8 with Segmentation for precise prawn identification. A unique biomarker is applied to estimate the length information. Subsequently, a polynomial based regression model is selected to correlate prawn length with actual weights, utilising comprehensive datasets collected under real-world farm conditions. As many different regression approaches have been proposed for the length-weight relationship, four commonly used approaches have been analysed. Results from extensive statistical analysis revealed that the modified polynomial regression with correction factor provides the best weight prediction. The integration of these techniques has equipped farmers with a reliable tool for predicting prawn weight during the sampling process, thereby minimizing stress on the prawns, and optimizing the segregation process.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"12 ","pages":"Article 101089"},"PeriodicalIF":6.3,"publicationDate":"2025-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144272012","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":"Evaluation of real-time stereo vision-controlled variable rate sprayer performance in grapevine shoot detections and spray application","authors":"Hongyoung Jeon,&nbsp;Heping Zhu","doi":"10.1016/j.atech.2025.101101","DOIUrl":"10.1016/j.atech.2025.101101","url":null,"abstract":"<div><div>The use of plant protection products (PPP) for plant protection can be substantially reduced by applying PPP on plants only. A novel variable–rate sprayer with a stereo vision system to apply PPP only to grapevines was developed for vineyard applications. The stereo vision system was evaluated as a grapevine shoot detection sensor under various conditions in average grapevine shoot lengths (4.1–29.1 cm), travel speeds (3.2–8.0 km h^-1) and outdoor illuminations (12,718 – 67,912.0 lx). A real-time variable–rate sprayer prototype with two air assistance levels at the air outlet (low (air speed of 5.9 m s^-1) and high (11.3 m s^-1)) tested for its spray performance against a conventional sprayer. The results show that the stereo vision system detected 95.1 % to 99.8 % of grapevine shoots in average under various conditions, and no influences of the shoot size, outdoor illuminations, and travel speeds on the shoot detection were observed under the test conditions. The prototype sprayer had up to approximately 2.8 times more spray deposit averages compared to the conventional sprayer, which was a significant increase (<em>p</em> &lt; 0.05). Insignificant increases of spray deposit on grapevine shoots next to the sprayer, and spray drift to an adjacent row were observed from spray applications with low and high air assistance. A similar trend was observed in spray coverage data. These results demonstrate that the novel stereo vision real-time variable rate sprayer is feasible for vineyard applications.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"12 ","pages":"Article 101101"},"PeriodicalIF":6.3,"publicationDate":"2025-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144307339","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":"Predicting indoor temperature of solar green house by machine learning algorithms: A comparative analysis and a practical approach","authors":"Wenhe Liu ,&nbsp;Tao Han ,&nbsp;Cong Wang ,&nbsp;Feng Zhang ,&nbsp;Zhanyang Xu","doi":"10.1016/j.atech.2025.101096","DOIUrl":"10.1016/j.atech.2025.101096","url":null,"abstract":"<div><div>This study focuses on a solar greenhouse located at the experimental base of Shenyang Agricultural University in Shenyang, Liaoning Province, to develop multi-step temperature prediction models based on machine learning algorithms. The research employs five algorithms: Random Forest (RF), Multiple Linear Regression (MLR), Support Vector Regression (SVR), Long Short-Term Memory Recurrent Neural Network (LSTM), and Gated Recurrent Unit (GRU) for temperature prediction. Experimental data were collected from meteorological stations inside and outside the solar greenhouse. The innovative aspect of this study lied in its systematic evaluation of temperature predictions across various time steps. Twenty-one prediction horizons, ranging from 15 min to 1440 min, were selected and the performance of the five predictive models was assessed using K-fold cross-validation for each time step. Results demonstrated that the GRU (Gated Recurrent Unit) model outperformed all other algorithms across all 21 prediction horizons, with short-term prediction (15 min) achieving an R² of 0.991 and long-term prediction (1440 min) maintaining an R² of 0.992 (as shown in Table 1). This performance significantly exceeded that of LSTM, Random Forest (RF), Support Vector Regression (SVR), and Multiple Linear Regression (MLR), with GRU reducing the root mean squared error (RMSE) by 12.3 %–27.5 % compared to LSTM in long-term predictions. The RF and SVR models demonstrated good performance for short-term predictions, but showed slight accuracy degradation as the prediction horizon extended. The MLR model performed adequately for short-term predictions (within 30 min), but exhibited poor performance for longer time steps (R² &lt; 0.9). GRU, by virtue of its more concise gating mechanism (featuring only update gates and reset gates), not only ensured high precision but also significantly improved training efficiency compared to LSTM. This research not only compared the performance of different machine learning algorithms in solar greenhouse temperature prediction but also explored the applicability of each algorithm across various prediction horizons. The findings provide a theoretical foundation and technical support for intelligent control and precise management of solar greenhouses.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"12 ","pages":"Article 101096"},"PeriodicalIF":6.3,"publicationDate":"2025-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144307338","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":"Enhancing coconut yield potential: A climate-smart land suitability analysis using machine learning","authors":"Lekshmi G.S. ,&nbsp;Aryadevi Remanidevi Devidas ,&nbsp;Raji Pushpalatha ,&nbsp;Byju Gangadharan ,&nbsp;Hariprasad K.M.","doi":"10.1016/j.atech.2025.101087","DOIUrl":"10.1016/j.atech.2025.101087","url":null,"abstract":"<div><div>Coconuts (Cocos nucifera L.) play a critical role in Kerala's agricultural landscape, serving as a cornerstone of agricultural income and significantly contributing to the state's economy. Despite their economic importance, variations in land and climate conditions across the region lead to inconsistencies in coconut yield and productivity, limiting the full potential of coconut farming. This study aims to enhance coconut cultivation in Kerala by i) comparing various machine learning (ML) and deep learning (DL) models to identify the optimal model for soil suitability prediction; ii) developing a climate model to assess climate suitability; and iii) integrating both soil suitability and climate suitability models to classify the study regions into suitability categories—highly suitable, moderately suitable, less suitable, and not suitable, for coconut farming. Using a dataset from the Soil Survey Department, the XGBoost algorithm was applied to classify soil suitability in the study area (Thiruvananthapuram, Kerala, India). Climate suitability was assessed using the MaxEnt model. Finally, GIS tools were used to combine these results into a comprehensive suitability map. For soil suitability prediction, we tested various machine learning and deep learning models, ultimately selecting XGBoost as the optimal model due to its near-perfect accuracy of 100%. The MaxEnt model enhanced the assessment of climate suitability with an accuracy of 67.7%, providing insights into optimal farming conditions. This study presents an integrated land and climate suitability model for coconut farming, demonstrating the effectiveness of ML and DL models for soil suitability analysis. This approach offers a robust framework for improving coconut cultivation and can be applied to other regions and crops.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"12 ","pages":"Article 101087"},"PeriodicalIF":6.3,"publicationDate":"2025-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144272015","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":"SeeTree - a modular, open-source system for tree detection and orchard localization","authors":"Jostan Brown,&nbsp;Cindy Grimm,&nbsp;Joseph R. Davidson","doi":"10.1016/j.atech.2025.101074","DOIUrl":"10.1016/j.atech.2025.101074","url":null,"abstract":"<div><div>Accurate localization is an important functional requirement for precision orchard management. However, there are few off-the-shelf commercial solutions available to growers. In this paper, we present SeeTree, a modular, open source embedded system for tree trunk detection and orchard localization that is deployable on any vehicle. Building on our prior work on vision-based in-row localization using particle filters, SeeTree includes several new capabilities. First, it provides capacity for full orchard localization including out-of-row headland turning. Second, it includes the flexibility to integrate either visual, GNSS, or wheel odometry in the motion model. During field experiments in a commercial orchard, the system converged to the correct location 99% of the time over 800 trials, even when starting with large uncertainty in the initial particle locations. When turning out of row, the system correctly tracked 99% of the turns (860 trials representing 43 unique row changes). To help support adoption and future research and development, we make our dataset, design files, and source code freely available to the community.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"12 ","pages":"Article 101074"},"PeriodicalIF":6.3,"publicationDate":"2025-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144271565","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":"Comparative analysis and evaluation of YOLO generations for banana bunch detection","authors":"Preety Baglat ,&nbsp;Ahatsham Hayat ,&nbsp;Sheikh Shanawaz Mostafa ,&nbsp;Fábio Mendonça ,&nbsp;Fernando Morgado-Dias","doi":"10.1016/j.atech.2025.101100","DOIUrl":"10.1016/j.atech.2025.101100","url":null,"abstract":"<div><div>This study focuses on improving the automation of banana harvesting decisions for farmers with artificial intelligence assistance. Traditionally, experienced harvesters manually inspect fields to determine the optimal harvesting time, a process that is both labor-intensive and increasingly unsustainable due to a shortage of skilled workers. To address this challenge, this work proposes a computer vision-based approach for detecting banana bunches in images captured by mobile phones, as a preliminary step towards a comprehensive harvesting decision pipeline. To achieve this, a dataset was collected with 2179 photos of multiple Cavendish banana bunches in different light and exposure conditions, and a comparative analysis of You Only Look Once (YOLO) object detection models was conducted, from version 1 to 12, to identify the most accurate and efficient solution for banana bunch detection, ensuring compatibility with mobile-based applications. Among all models evaluated, YOLOv12n achieved the most balanced performance on five-fold cross-validation, with 93 % Average Precision (AP^50test), 51 % AP^50–95test, and 5.1 ms latency, making it well-suited for real-time deployment on resource-constrained edge devices.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"12 ","pages":"Article 101100"},"PeriodicalIF":6.3,"publicationDate":"2025-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144289077","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":"Orange yield estimation using object tracking and 3D reconstruction","authors":"Amna Hassan ,&nbsp;Rafia Mumtaz ,&nbsp;Vasile Palade ,&nbsp;Arslan Amin ,&nbsp;Zahid Mahmood ,&nbsp;Noorullah Khan ,&nbsp;Muhammad Noman ,&nbsp;Muhammad Imran ,&nbsp;Santichai Wicha","doi":"10.1016/j.atech.2025.101088","DOIUrl":"10.1016/j.atech.2025.101088","url":null,"abstract":"<div><div>The labor-intensive nature of agriculture, particularly in tasks such as yield estimation of fruits, is a significant challenge. Yield estimation is crucial for the better management of the resources and for taking adequate measures for the transportation, storage, and export of the fruits. It also helps the farmers to estimate the total pricing of the yield. However, counting fruits directly on trees for yield estimation presents an obstacle due to their dispersed nature and often dense foliage. Therefore, we propose that reasonably accurate fruit yield estimation can be automated with a handheld camera. The dataset is curated by capturing and annotating 1451 images of orange trees. The dataset is augmented and processed in different ways to evaluate the performance of YOLOv8 for the detection of oranges. Then the Byte tracker is deployed to track oranges in consecutive video frames. Further, we have classified the fruits into two categories, ripe and unripe using MobileVit. The 2D fruits detected by YOLOv8 are projected to a 3D space for a more detailed analysis of the scene. Subsequently, the clustering algorithm is applied to the 3D projections of the detected objects to estimate per tree yield. On images, YOLOv8 nano has achieved a precision of 78.2% and recall of 69.7% on the test set. Moreover, for ripeness stage classification, MobileVit has achieved an accuracy of 97.8% and 86.7% on a test set containing 2 classes and 3 classes, respectively. Testing our proposed solution on videos shows that the algorithm is achieving good results on trees with less leaf occlusion. This paper demonstrates that preprocessing techniques can aid the detection model to achieve high detection rates. Furthermore, per tree yield of an orange orchard can be estimated by using video input. This offers an automated solution to the laborious task of fruit yield estimation in agricultural settings, that can help to optimize orange production.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"12 ","pages":"Article 101088"},"PeriodicalIF":6.3,"publicationDate":"2025-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144272016","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":"Development of an electromechanical device for real-time detection of litter moisture in commercial broiler","authors":"Glauber da Rocha Balthazar ,&nbsp;Robson Mateus Freitas Silveira ,&nbsp;Marcos Vinicius Amato da Cruz ,&nbsp;Iran José Oliveira da Silva","doi":"10.1016/j.atech.2025.101103","DOIUrl":"10.1016/j.atech.2025.101103","url":null,"abstract":"<div><div>Broiler litter quality is a critical factor in industrial broiler production systems, as it affects the environment and animal welfare. The litter is composed of thermal insulating materials such as wood shavings, peanut shells and, rice, among others, with the ability to absorb animal excreta. Its condition can impact environmental quality. Depending on its condition, it may increase the levels of gases and dust in the aviary, and may cause pododermatitis, compromising paw quality. Effective management requires analyzing litter quality by measuring moisture content. This article presents the development of an electronic sensor for detecting chicken litter moisture using microcontrollers and rapid prototyping sensors. The construction method involved three stages: prototyping a minimum viable product (MVP), conducting field tests to evaluate the sensor's humidity detection capability when integrated with a pre-existing robot, and mathematical modeling to determine the most suitable sensor for detecting litter humidity. This process utilized Technical Standard NBR 6457 to calibrate the equation for adjusting the detected humidity level. The findings confirmed the successful development of a calibrated electronic sensor for measuring litter humidity. This device was tested in a commercial poultry farm, producing a humidity map over a six-week production cycle.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"12 ","pages":"Article 101103"},"PeriodicalIF":6.3,"publicationDate":"2025-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144298871","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 preliminary model for determining a soil quality index including biological data implemented through a QR code application","authors":"Simone Figorilli ,&nbsp;Loredana Canfora ,&nbsp;Andrea Manfredini ,&nbsp;Simona Violino ,&nbsp;Lavinia Moscovini ,&nbsp;Federico Pallottino ,&nbsp;Francesca Antonucci ,&nbsp;Corrado Costa ,&nbsp;Ewa M. Furmanczyk ,&nbsp;Wioletta Popińska ,&nbsp;Antonio Gerardo Pepe ,&nbsp;Eligio Malusà","doi":"10.1016/j.atech.2025.101106","DOIUrl":"10.1016/j.atech.2025.101106","url":null,"abstract":"<div><div>Soil plays a central role in delivering several ecosystem services. However, its complex nature, the spatial variability and the timescale of soil processes make it challenging to quantify shifts in soil quality as a result of agronomical practices. A comprehensive indicator that includes parameters from different categories of soil properties, allowing an easy interpretation of soil quality by farmers and land managers, is thus needed. In this context, a class-modelling approach based on the Data-Driven Soft Independent Model of Class Analogy (DD-SIMCA) was tested to develop a soil quality index based on physical, chemical and biological parameters. Three models were built on a dataset composed by physical, chemical and biological soil parameters, which was created basing on ranges of values common to agricultural soils. The algorithm was thus applied to a real dataset obtained from about 9800 soil samples. The models showed very high performance (sensitivity = 1), allowing to classify the samples into quality groups. The model output was incorporated into a coloured QR-code, which allowed to express the quality of a soil sample with a colorimetric scale based on a soil quality index. A preliminary version of the tool is available for further testing and validation through a web platform (<span><span>https://agritechlab.crea.gov.it/model/ddsimcasoil/ddsimcasoil.html</span><svg><path></path></svg></span>).</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"12 ","pages":"Article 101106"},"PeriodicalIF":6.3,"publicationDate":"2025-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144280780","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}