Smart agricultural technology最新文献

{"title":"Development of a cloud-based IoT system for livestock health monitoring using AWS and python","authors":"Harini Shree Bhaskaran ,&nbsp;Miriam Gordon ,&nbsp;Suresh Neethirajan","doi":"10.1016/j.atech.2024.100524","DOIUrl":"10.1016/j.atech.2024.100524","url":null,"abstract":"<div><p>The agriculture industry is currently facing significant challenges in effectively monitoring the health of livestock. Traditional methods of health monitoring are often labor-intensive, inefficient, and insufficiently responsive to the needs of modern farming. As the number of IoT devices in agriculture proliferates, issues of scalability and computational load have become prominent, necessitating efficient and scalable solutions. This research introduces a cloud-based architecture aimed at enhancing livestock health monitoring. This system is designed to track critical health indicators such as movement patterns, body temperature, and heart rate, utilizing AWS for robust data handling and Python for data processing and real-time analytics. The proposed system incorporates Narrow Band IoT (Nb IoT) technology, which is optimized for low-bandwidth, long-range communication, making it suitable for rural and remote farming locations. The architecture's scalability allows for the effective management of varying numbers of IoT devices, which is essential for adapting to changing herd sizes and farm scales. Preliminary experiments conducted to assess the system's performance have demonstrated its durability and effectiveness, indicating a successful integration of AWS IoT Cloud services with the deployed IoT devices. Furthermore, the study explores the implementation of predictive analytics to facilitate proactive health management in livestock. By predicting potential health issues before they become apparent, the system can offer significant improvements in animal welfare and farm efficiency. The integration of cloud computing and IoT not only meets the growing technological needs of modern agriculture but also sets a new benchmark in the development of sustainable farming practices. The findings from this research could have broad implications for the future of livestock management, potentially leading to widespread adoption of technology-driven health monitoring systems in agriculture. This would help in optimizing the health management of livestock globally, thereby enhancing productivity and sustainability in the agricultural sector.</p></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"9 ","pages":"Article 100524"},"PeriodicalIF":6.3,"publicationDate":"2024-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2772375524001291/pdfft?md5=9ae812e43563363d78e1563c7874898c&pid=1-s2.0-S2772375524001291-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141997183","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":"Hyperspectral image reconstruction for predicting chick embryo mortality towards advancing egg and hatchery industry","authors":"Md. Toukir Ahmed ,&nbsp;Md Wadud Ahmed ,&nbsp;Ocean Monjur ,&nbsp;Jason Lee Emmert ,&nbsp;Girish Chowdhary ,&nbsp;Mohammed Kamruzzaman","doi":"10.1016/j.atech.2024.100533","DOIUrl":"10.1016/j.atech.2024.100533","url":null,"abstract":"<div><p>As the demand for food surges and the agricultural sector undergoes a transformative shift towards sustainability and efficiency, the need for precise and proactive measures to ensure the health and welfare of livestock becomes paramount. In the egg and hatchery industry, hyperspectral imaging (HSI) has emerged as a cutting-edge, non-destructive technique for fast and accurate egg quality analysis, including detecting chick embryo mortality. However, the high cost and operational complexity compared to conventional RGB imaging are significant bottlenecks in the widespread adoption of HSI technology. To overcome these hurdles and unlock the full potential of HSI, a promising solution is hyperspectral image reconstruction from standard RGB images. This study aims to reconstruct hyperspectral images from RGB images for non-destructive early prediction of chick embryo mortality. Initially, the performance of different image reconstruction algorithms, such as HRNET, MST++, Restormer, and EDSR were compared to reconstruct the hyperspectral images of the eggs in the early incubation period. Later, the reconstructed spectra were used to differentiate live from dead embryos eggs using the XGBoost and Random Forest classification methods. Among the reconstruction methods, HRNET showed impressive reconstruction performance with MRAE of 0.0955, RMSE of 0.0159, and PSNR of 36.79 dB. This study motivated the idea that harnessing imaging technology integrated with smart sensors and data analytics has the potential to improve automation, enhance biosecurity, and optimize resource management towards sustainable agriculture 4.0.</p></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"9 ","pages":"Article 100533"},"PeriodicalIF":6.3,"publicationDate":"2024-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2772375524001382/pdfft?md5=1d6d69c1b4d4426333f4a0df82d33520&pid=1-s2.0-S2772375524001382-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141997185","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":"Development and implementation of a raspberry Pi-based IoT system for real-time performance monitoring of an instrumented tractor","authors":"Vijay Mahore,&nbsp;Peeyush Soni,&nbsp;Prakhar Patidar,&nbsp;Harsh Nagar,&nbsp;Arjun Chouriya,&nbsp;Rajendra Machavaram","doi":"10.1016/j.atech.2024.100530","DOIUrl":"10.1016/j.atech.2024.100530","url":null,"abstract":"<div><p>The tractor serves as a crucial power source in agricultural operations. However, the tractor's power often remains underutilized due to a mismatch between the tractor and implement, considering specific field conditions. To enhance system output, it becomes vital to acquire data on performance-related parameters for the tractor-implement combination. In this study we develop a real-time Instrumented Tractor Performance Monitoring System (ITPMS) using the Internet-of-Things (IoT). This system consists of a Raspberry Pi, a GPS sensor, a proximity sensor, a rotary potentiometer, and a three-point hitch dynamometer. The rotary potentiometer measures tillage depth, while the three-point hitch dynamometer used to measure data on draft force. Proximity sensors are installed on a two-wheel drive (2WD) tractor to measure forward speed and drive-wheel slip. We establish a dedicated web server using a Google® Firebase® project to store data from all sensors through Raspberry Pi. Additionally, we design a web interface and a mobile application to provide real-time data generated from the sensors. Field experiments were done to evaluate and monitor the performance parameters of the tractor-implement combination utilising the developed ITPMS. The results demonstrate that the system effectively monitors the performance parameters necessary for tractor-implement combination. Furthermore, the system's capability to update data to the IoT server in real-time is validated. Overall, the development and implementation of this Raspberry Pi based IoT system, provides a reliable and efficient solution for real-time performance monitoring of instrumented tractors.</p></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"9 ","pages":"Article 100530"},"PeriodicalIF":6.3,"publicationDate":"2024-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2772375524001357/pdfft?md5=6081ec8bb670ddf38bff895433e2db2a&pid=1-s2.0-S2772375524001357-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141963550","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 computer vision and machine learning in morphological characterization of Adansonia digitata fruits","authors":"Franklin X. Dono ,&nbsp;Bernard N. Baatuuwie ,&nbsp;Felix K. Abagale ,&nbsp;Peter Borgen Sørensen","doi":"10.1016/j.atech.2024.100528","DOIUrl":"10.1016/j.atech.2024.100528","url":null,"abstract":"<div><p>Measuring fruit mass and volume is a time-consuming and tedious task that can affect production planning. This study developed a computer vision system to estimate the volume and mass of baobab fruits from single-view images captured from inexpensive and readily available cameras such as those in smartphones. The baobab fruits were collected from two study fields within the savanna ecological zone. Their images were captured, and subsequently, they were detected and segmented with over 97 % accuracy. The segmented images were binarized, and two-dimensional (2D) features such as the segmented area, centroid, bounding box, equivalent diameter, and major diameter were extracted from them. The volumes of the fruits were estimated from the 2D features using random forest, linear, polynomial, and radial support vector machine models. All the models achieved high goodness of fit; however, the random forest model delivered the best performance, with an <em>R</em>² value of 99.8 %. The relationship between mass and volume was a quadratic equation (mass = 38.23 + 0.25 × volume + 4.49e−05 × volume²) and had an <em>R²</em> value of 92 %. Correlations were validated via plots and statistical tests, and credible intervals of point estimates were determined from the posterior distributions of their samples. This highlights the potential of artificial intelligence methods to be applied in a less constrained environmental setting for ecological research and agricultural management. Commercial companies producing baobab powder and seed oil should apply these models for effective production planning. To enhance the model, it would be beneficial to gain a better understanding of how climate gradients affect the morphological characteristics of baobab fruits.</p></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"9 ","pages":"Article 100528"},"PeriodicalIF":6.3,"publicationDate":"2024-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2772375524001333/pdfft?md5=28c0bd462ab75be057a6e0439591686c&pid=1-s2.0-S2772375524001333-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141978359","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":"Stimulating awareness of Precision Farming through gamification: The Farming Simulator case","authors":"Tetiana Pavlenko ,&nbsp;Dimitrios Argyropoulos ,&nbsp;Matthieu Arnoult ,&nbsp;Thomas Engel ,&nbsp;Yiorgos Gadanakis ,&nbsp;Hans W. Griepentrog ,&nbsp;Jacob Kambuta ,&nbsp;Tamisan Latherow ,&nbsp;Alistair J. Murdoch ,&nbsp;Richard Tranter ,&nbsp;Dimitrios S. Paraforos","doi":"10.1016/j.atech.2024.100529","DOIUrl":"10.1016/j.atech.2024.100529","url":null,"abstract":"<div><p>Precision Farming (PF) provides different solutions to assist the decision-making process on farms. Current PF technologies such as variable rate site-specific applications can bring financial benefits to farmers as well as environmental advantages. Increasing scientific research and an expanding number of PF products are supporting a growing interest in PF applications. However, the actual implementation of these technologies on farms in many cases remains low. Therefore, there is a need to disseminate and transfer knowledge about the positive aspects of PF. One of the ways to facilitate the adoption process of PF technologies is education and training among farmers and other interested stakeholders. This paper presents a case study using the computer game Farming Simulator as an educational tool for raising awareness about the topic in an engaging and enjoyable way. Two distinct downloadable content (DLC) versions were developed and implemented in the versions 2019 and 2022 of the game, respectively, each with a range of PF functionalities (automatic steering, variable rate applications, yield mapping among others). The PF DLCs have received positive feedback from students and scientists but also the general public. The growing number of downloads (3,661,069 in total for both DLC versions as of 15th November 2023) demonstrates the effectiveness of computer games as an educational tool to educate and inform stakeholders (farmers, scientists, students, and the general public) about agricultural challenges and the potential of PF as a solution.</p></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"9 ","pages":"Article 100529"},"PeriodicalIF":6.3,"publicationDate":"2024-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2772375524001345/pdfft?md5=ad458eeb92a594eed7a96ba8983898b8&pid=1-s2.0-S2772375524001345-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142002019","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":"Deep learning methods for enhanced stress and pest management in market garden crops: A comprehensive analysis","authors":"Mireille Gloria Founmilayo Odounfa ,&nbsp;Charlemagne D.S.J. Gbemavo ,&nbsp;Souand Peace Gloria Tahi ,&nbsp;Romain L. Glèlè Kakaï","doi":"10.1016/j.atech.2024.100521","DOIUrl":"10.1016/j.atech.2024.100521","url":null,"abstract":"<div><p>Various deep learning methods are employed to detect stress and diseases in market garden crops, as well as to assess their severity. This study aims to comprehensively analyze these techniques and identify potential research avenues. The diversity of deep learning techniques was explored through a literature review based on the PRISMA guidelines. Research equations were defined, resulting in a sample of <span><math><mn>1</mn><mo>,</mo><mn>422</mn></math></span> publications, of which 72 were deemed usable and considered in the final analysis. For classification tasks, hybrid CNN models were the most widely used (19.2%). Commonly utilized models included VGG16 (10%), InceptionV3 (6.1%), DCNN (5%), and YoloV5 (5%). In object detection tasks, Fast R-CNN was used six times, followed by YoloV5 (three occurrences) and YoloV3 (two occurrences). In segmentation tasks, Mask R-CNN accounted for 28.67% of the models, while DeepLabV3+ accounted for 24.98%. Assessing disease severity in market garden crops is complex due to the unique criteria for each plant disease and the presence of multiple diseases across different crop types. To address this complexity, establishing a standardized method is crucial. Further research is essential to enhance the application of deep learning techniques in the study of market garden crops. This includes gathering extensive datasets that encompass various scenarios of crop diseases and considering the impact of climate variations on stress manifestation.</p></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"9 ","pages":"Article 100521"},"PeriodicalIF":6.3,"publicationDate":"2024-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2772375524001266/pdfft?md5=11f8833021e6b2a9c9d7b21ec215d816&pid=1-s2.0-S2772375524001266-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141962900","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":"Implementation of laser-light backscattering imaging for authentication of the geographic origin of Indonesia region citrus","authors":"Muhammad Achirul Nanda ,&nbsp;S. Rosalinda ,&nbsp;Rahmat Budiarto ,&nbsp;Inna Novianty ,&nbsp;Taufik Ibnu Salim ,&nbsp;Pradeka Brilyan Purwandoko ,&nbsp;Dimas Firmanda Al Riza","doi":"10.1016/j.atech.2024.100527","DOIUrl":"10.1016/j.atech.2024.100527","url":null,"abstract":"<div><p>Citrus fruit (<em>Citrus nobilis</em> Lour.) from the Indonesian region is reported to have high economic value due to attractive nutritional, nutraceutical, and sensory attributes. However, authenticating the geographic origins is challenging because of adulteration and similarity in visual appearance. Therefore, this study aimed to develop an effective method based on laser-light backscattering imaging (LLBI) for authentication of the geographic origin of the region citrus. A total of 200 citrus samples were collected from Medan, Malang, Jember, and Banyuwangi regions, which were the four main citrus-producing areas in Indonesia. Approximately three different laser wavelengths, namely 450, 532, and 648 nm were beamed to produce the backscattering image. Furthermore, a combination of the gray-level co-occurrence matrix (GLCM) method and support vector machine (SVM) algorithm was applied to extract texture features and build a classification model, respectively. In this context, three kernel functions, such as linear, radial basis function, and polynomial, were compared in authenticating the geographic origin of citrus. The results showed that the proposed technique achieved 96.667 % accuracy and 3.333 % apparent error for authentication of the geographic origin. The proposed LLBI technique applied a laser wavelength of 450 nm and a polynomial kernel function as the best combination to produce reliable predictive power. This study held valuable implications for advancing sensing technology devices to authenticate geographic origin, specifically citrus fruit.</p></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"9 ","pages":"Article 100527"},"PeriodicalIF":6.3,"publicationDate":"2024-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2772375524001321/pdfft?md5=2be978ede4331958edb87904719057d3&pid=1-s2.0-S2772375524001321-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141963079","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":"Real-time precision spraying application for tobacco plants","authors":"Muhammad Arsalan ,&nbsp;Ahmar Rashid ,&nbsp;Khurram Khan ,&nbsp;Abid Imran ,&nbsp;Faheem Khan ,&nbsp;Muhammad Azeem Akbar ,&nbsp;Hammad M. Cheema","doi":"10.1016/j.atech.2024.100497","DOIUrl":"10.1016/j.atech.2024.100497","url":null,"abstract":"<div><p>This paper introduces a precision agriculture application aimed at mitigating the excessive utilization of agricultural chemicals, including pesticides and fungicides during crop spraying. The prevailing spraying techniques face two principle challenges: first, the indiscriminate dispensation of chemicals irrespective of plant size and requirements and second, the farmer's exposure to health hazards. To tackle these issues, a detection and segmentation model employing both YOLOv5 and YOLOv6 architectures is proposed and a comparative assessment of their accuracies within the same model category is conducted. The training dataset originates from a subset of the TobSet dataset, while the evaluation of the trained models is executed using publicly accessible aerial videos/images from available repository. The best detection accuracy achieved for the tobacco plant model size is observed with YOLOv6s and the YOLOv5-segmentation model, yielding accuracies of 95% and 94.8%, respectively. Additional performance metrics such as precision, recall, area under the PR-curve, inference time, and NMS per image are also compared between the two models. The YOLOv5-segmentation model excels by outperforming the YOLOv6s model in precision, recall score, and area under the PR-curve whereas slightly extended inference time and NMS per image duration are noted for the YOLOv5-segmentation model and the speed performance is comparable for the two models. Subsequently, the evaluation of these two models is conducted on the drone videos, which were recorded during drone traversal at a speed of 2 km/hr. The results demonstrate superiority of YOLOv5-segmentation model over the YOLOv6s model, with detection accuracies of 98.1% and 97.3%, respectively. These findings indicate the potential of integrating YOLOv5 segmentation models in precision spraying applications and contribute in improving the overall agricultural practices.</p></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"8 ","pages":"Article 100497"},"PeriodicalIF":6.3,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2772375524001023/pdfft?md5=94fc464b49049dc4477a72101693e032&pid=1-s2.0-S2772375524001023-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141696648","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":"SSC and pH prediction and maturity classification of grapes based on hyperspectral imaging","authors":"","doi":"10.1016/j.atech.2024.100457","DOIUrl":"10.1016/j.atech.2024.100457","url":null,"abstract":"<div><p>Soluble solids content (SSC) and pH of red globe grapes are crucial measures of quality. In this paper, we used hyperspectral imaging technology to achieve nondestructive detection and distribution visualization of SSC and pH of red globe grapes. First, the hyperspectral images of samples were collected. Then, CARS, SPA, GA, IRIV were used to extract feature variables from raw spectral (RAW) information. The PLSR prediction models of samples were developed. By comparing the different prediction models, RAW-IRIV-PLSR was selected as the optimal model. Finally, the SSC and pH of the samples were calculated to obtain a grayscale image and perform a pseudo-color transformation to visualize the distribution of SSC and pH. By studying the classification of the maturity of samples, it was concluded that the best discriminant classification model of maturity was RAW-IRIV-ELM. Hyperspectral also provided a new method for maturity stage classification of red globe grapes.</p></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"8 ","pages":"Article 100457"},"PeriodicalIF":6.3,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2772375524000625/pdfft?md5=c27b68967e55c6c0187a19808ab6cac4&pid=1-s2.0-S2772375524000625-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141039736","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":"DeepQC: A deep learning system for automatic quality control of in-situ soil moisture sensor time series data","authors":"Lahari Bandaru ,&nbsp;Bharat C Irigireddy ,&nbsp;Koutilya PVNR ,&nbsp;Brian Davis","doi":"10.1016/j.atech.2024.100514","DOIUrl":"10.1016/j.atech.2024.100514","url":null,"abstract":"<div><p>Amidst changing climate, real-time soil moisture monitoring is vital for the development of in-season decision support tools to help farmers manage weather-related risks in agriculture. Precision Sustainable Agriculture (PSA) recently established a real-time soil moisture monitoring network across the central, Midwest, and eastern U.S., but continuous field-scale sensor observations often come with data gaps and anomalies. To maintain the data quality and continuity needed for developing decision tools, a quality control system is necessary.</p><p>The International Soil Moisture Network (ISMN) introduced the Flagit module for anomaly detection in soil moisture time series observations. However, under certain conditions, Flagit's threshold and spectral based quality control approaches may underperform in identifying anomalies. Recently, deep learning methods have been successfully applied to detect time series anomalies in time series data in various disciplines. However, their use in agriculture for anomaly detection in time series datasets has not been yet investigated. This study focuses on developing a Bi-directional Long Short-Term Memory (LSTM) model, referred to as DeepQC, to identify anomalies in soil moisture time series data. Manual flagged PSA observations were used for training, validation, and testing the model, following an 80:10:10 split. The study then compared the DeepQC and Flagit-based estimates to assess their relative performance.</p><p>Flagit correctly flagged 95.8 % of the correct observations and 50.3 % of the anomaly observations, indicating its limitations in identifying anomalies, particularly at sites consists of more than 30 % anomalies. On the other hand, the DeepQC correctly flagged 89.8 % of the correct observations and 99.5 % of the anomalies, with overall accuracy of 95.6 %, in significantly less time, demonstrating its superiority over Flagit approach. Importantly, the performance of the DeepQC remained consistent regardless of the number of anomalies in site observations. Given the promising results obtained with the DeepQC, future studies will focus on implementing and finetuning this model on national and global soil moisture networks.</p></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"8 ","pages":"Article 100514"},"PeriodicalIF":6.3,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2772375524001199/pdfft?md5=4a06655ff87f5ebdc29ea1c311526dc4&pid=1-s2.0-S2772375524001199-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141848625","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}