Smart agricultural technology最新文献

{"title":"A graph convolutional network approach for hyperspectral image analysis of blueberries physiological traits under drought stress","authors":"Md. Hasibur Rahman ,&nbsp;Savannah Busby ,&nbsp;Sajid Hanif ,&nbsp;Md Mesbahul Maruf ,&nbsp;Faraz Ahmad ,&nbsp;Sushan Ru ,&nbsp;Alvaro Sanz-Saez ,&nbsp;Jingyi Zheng ,&nbsp;Tanzeel U. Rehman","doi":"10.1016/j.atech.2024.100743","DOIUrl":"10.1016/j.atech.2024.100743","url":null,"abstract":"<div><div>Blueberries are extremely susceptible to drought due to their shallow root systems and limited water regulation capabilities. Climate change exacerbates drought stress in major blueberry production regions, which affect key physiological traits, such as leaf water content (LWC), photosynthesis (A), stomatal conductance (g_s), electron transport rate (ETR), photosystem II efficiency (φPSII) and transpiration rate (E). Current phenotyping methods for measuring these physiological traits are time-consuming and labor-intensive as well as limited by the need for specialized equipment. To address this, a high-throughput phenotyping (HTPP) platform integrated with hyperspectral camera and a novel graph convolutional network (GCN)-based model, Plant-GCN, was developed to predict physiological traits of blueberry plants under drought stress. Spectral reflectance obtained from the hyperspectral images were transformed into a graph representation, with each plant represented as a node, spectral reflectance as node features, and edges defined by spectral similarities. The Plant-GCN model utilizes graph convolutional layers that aggregate information from neighboring nodes, effectively capturing complex interactions in the spectral signature and enhancing the prediction of physiological traits. Plant-GCN achieved a coefficient of determination (R²) of 0.89 for LWC, 0.94 for A, 0.89 for g_s, 0.92 for ETR, 0.93 for φPSII and 0.89 for E on the test dataset. The performance of the proposed Plant-GCN model was compared with multilayer perceptron (MLP), partial least squares regression (PLSR), support vector regression (SVR), and random forest (RF), and it consistently outperformed all these models as well as data published in other reports. The high-throughput phenotyping system enabled efficient large-scale data collection, while the Plant-GCN model captured long-range spectral relationships significantly improved the prediction of physiological traits. The high predictability of the models could facilitate the screening of blue-berry cultivars for the specified traits allowing the selection and breeding of new drought tolerant cultivars in the future.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"10 ","pages":"Article 100743"},"PeriodicalIF":6.3,"publicationDate":"2024-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143181121","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":"SmartSolos expert: An expert system for Brazilian soil classification","authors":"Glauber José Vaz ,&nbsp;Luís de França da Silva Neto ,&nbsp;Jayme Garcia Arnal Barbedo","doi":"10.1016/j.atech.2024.100735","DOIUrl":"10.1016/j.atech.2024.100735","url":null,"abstract":"<div><div>We have developed an expert system for Brazilian soil classification according to the official taxonomic system in Brazil. It assists in improving soil data quality, which is important for sustainable agriculture. A rule-based expert system is an appropriate approach for addressing this problem, and SmartSolos Expert is the first one based on the Brazilian soil classification system considering all the classes from the 1st to the 4th level, involving more than a thousand classes. We developed the expert system, made it available through a web Application Programming Interface, and specified a schema for input and output data. Since it always returns accurate classification, it has been used to identify inconsistencies, curate Brazilian soil data, and examine possibilities for improvements to the Brazilian Soil Classification System.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"10 ","pages":"Article 100735"},"PeriodicalIF":6.3,"publicationDate":"2024-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143182105","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":"Accelerated sub-image search for variable-size patches identification based on virtual time series transformation and segmentation","authors":"Mogens Plessen","doi":"10.1016/j.atech.2024.100736","DOIUrl":"10.1016/j.atech.2024.100736","url":null,"abstract":"<div><div>This paper addresses two tasks: (i) fixed-size objects such as hay bales are to be identified in an aerial image for a given reference image of the object, and (ii) variable-size patches such as areas on fields requiring spot spraying or other handling are to be identified in an image for a given small-scale reference image. Both tasks are related. The second differs in that identified sub-images similar to the reference image are further clustered before patches contours are determined by solving a traveling salesman problem. Both tasks are complex in that the exact number of similar sub-images is not known a priori. The main discussion of this paper is presentation of an acceleration mechanism for sub-image search that is based on a transformation of an image to multivariate time series along the RGB-channels and subsequent segmentation to reduce the 2D search space in the image. Two variations of the acceleration mechanism are compared to exhaustive search on diverse synthetic and real-world images. Quantitatively, proposed method results in solve time reductions of up to 2 orders of magnitude, while qualitatively delivering comparative results, thereby highlighting the effect of the acceleration mechanism. Proposed method is neural network-free and does not use any image pre-processing.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"10 ","pages":"Article 100736"},"PeriodicalIF":6.3,"publicationDate":"2024-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143182770","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":"Adaptive high-quality sampling for winter wheat early mapping: A novel cascade index and machine learning approach","authors":"Zhijan Zhang ,&nbsp;Chenyu Li ,&nbsp;Jie Deng ,&nbsp;Jocelyn Chanussot ,&nbsp;Danfeng Hong","doi":"10.1016/j.atech.2024.100725","DOIUrl":"10.1016/j.atech.2024.100725","url":null,"abstract":"<div><div>Precise and timely mapping of winter wheat is essential for food security. Current methods are limited by insufficient training data and a lack of long-term early mapping verification. This research proposes a framework that uses a cascade index to generate high-quality training samples for winter wheat mapping automatically. By considering the phenological characteristics of winter wheat and similar crops, the cascade index method screens and acquires these samples. Combined with a random forest model, mapping was conducted in Henan Province and the Agricultural Statistics District (ASD) 2020 area in the U.S. In Henan, early mapping from 2018 to 2022 assessed differences between model transfer and current-year samples. Results showed that using October-April imagery based on model migration achieved an overall accuracy (OA) of over 90%, while October-February imagery based on current-year samples also exceeded 90%. In some years, early mapping using only October-December data also achieved over 90% OA. These findings demonstrate the proposed model's viability for large-scale early winter wheat mapping using satellite imagery. Furthermore, this method demonstrates adaptability, mapping results achieving over 93.69% OA when transferred to the United States.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"10 ","pages":"Article 100725"},"PeriodicalIF":6.3,"publicationDate":"2024-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143182774","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":"Understanding dairy livestock farmers’ intention to adopt sociocultural dynamics for food security using the theory of planned behaviour","authors":"Paresh Kumar Sarma ,&nbsp;Mohammad Jahangir Alam ,&nbsp;Samiha Sarwar ,&nbsp;Sadika Haque ,&nbsp;Golam Rabbani ,&nbsp;Ismat Ara Begum ,&nbsp;Andrew M. McKenzie","doi":"10.1016/j.atech.2024.100711","DOIUrl":"10.1016/j.atech.2024.100711","url":null,"abstract":"<div><div>This study examines the impact of socio-cultural dynamics (SCD) on food and nutrition security in dairy farming households. Recognizing the role of cultural practices, social networks, and access to resources in shaping food security, we emphasize the need to incorporate these factors into interventions for dairy farming. Using a systematic random sampling technique, we surveyed 400 households in the Rajbari District of Bangladesh in 2024 and analyzed the data using the Theory of Planned Behavior (TPB) and the Partial Least Square-Structural Equation Model (PLS-SEM model). The results revealed a positive association between the intention to adopt socio-cultural dynamics and food and nutritional security. Therefore, enhancing intention, expanding community and social networks, and improving perceived behavioral control can positively impact the food and nutrition security (FNS) status of dairy farming households. This study underscores the importance of integrating socio-cultural considerations into interventions aimed at improving food and nutrition security in dairy farming communities. It demonstrates that incorporating local socio-cultural practices can enhance food and nutrition security by considering cultural beliefs, social networks, and perceived behavioral control. To effectively address food security in livestock farming households, it is crucial to understand the complex socio-cultural dynamics that shape their practices. Policymakers can tailor interventions to meet the unique needs of these communities by acknowledging and respecting their cultural values and beliefs. This approach will encourage community engagement and incentivize sustainable practices. Key strategies to integrate socio-cultural dynamics and promote food and nutrition security in dairy farming communities include emphasizing cultural sensitivity, building social networks, and collaborating with stakeholders.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"10 ","pages":"Article 100711"},"PeriodicalIF":6.3,"publicationDate":"2024-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143181125","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":"Efficient federated transfer learning-based network anomaly detection for cooperative smart farming infrastructure","authors":"Lopamudra Praharaj ,&nbsp;Deepti Gupta ,&nbsp;Maanak Gupta","doi":"10.1016/j.atech.2024.100727","DOIUrl":"10.1016/j.atech.2024.100727","url":null,"abstract":"<div><div>Precision agriculture has emerged as a vital solution to meet the food demands of the growing global population. However, the high upfront costs of sensors, data analytics tools, and automation often pose challenges for small-scale farms, limiting their ability to adopt these advanced practices. Cooperative Smart Farming (CSF) provides a practical solution to address the evolving needs of modern farming, making precision agriculture more accessible and affordable for small-scale farms. These cooperatives are formal enterprises collectively financed, managed, and operated by member farms, working together for shared benefits. Though it benefits small-scale farmers, all member farms can embrace advanced technologies through collective investment and data sharing by joining cooperatives. As Smart Agriculture grows, CSFs are poised to be essential in building a more sustainable, resilient, and profitable agriculture for all member farms. However, CSFs face increased cybersecurity risks as technology reliance grows. Cyberattacks on one farm can disrupt the entire network, threatening data integrity and decision-making. Federated Learning (FL)-based anomaly detection has been proposed to address this, allowing farms to detect threats locally and share only model updates. However, cooperatives' data sharing and interconnected nature introduce challenges in developing the anomaly detection model. This model must detect threats early and take preventive actions, as delays could result in successful attacks on other smart farms in the network. Additionally, if more smart farms join the cooperative, the model gradient updates can still be transmitted to the server quickly without overwhelming communication channels and causing delays.</div><div>To address these challenges, in this research, we develop an efficient Federated Transfer Learning FTL based network anomaly detection model for the CSF environment. We also use a dynamic low-rank compression algorithm to reduce the communication latency. To evaluate this proposed approach, we first set up two independent smart farming testbeds incorporating various sensors commonly used in smart farming. We then launch different cyberattacks in each smart farm and collected two network datasets. For proof of concept, we implement and assess the robustness of our proposed model based on metrics such as identifying anomalies, memory consumption, training time, and accuracy using two network datasets. The experiments demonstrated that our proposed model achieves higher accuracy and requires less training time than traditional FL algorithms, enabling early and efficient attack detection in CSF and minimizing the impact of cyberattacks on member farms.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"10 ","pages":"Article 100727"},"PeriodicalIF":6.3,"publicationDate":"2024-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143183261","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":"Cropland observatory nodes (CRONOS): Proximal, integrated soil-plant-atmosphere monitoring systems","authors":"D. Cole Diggins ,&nbsp;Andres Patrignani ,&nbsp;Erik S. Krueger ,&nbsp;William G. Brown ,&nbsp;Tyson E. Ochsner","doi":"10.1016/j.atech.2024.100737","DOIUrl":"10.1016/j.atech.2024.100737","url":null,"abstract":"<div><div>Soil-plant-atmosphere conditions in crop fields can differ substantially from those at the nearest weather station, creating uncertainty in crop management decisions and scientific analyses. To reduce this uncertainty, CRopland Observatory NOdeS (CRONOS) were developed to monitor soil water content, green canopy cover (GCC), and atmospheric conditions in crop fields. Here we evaluate the accuracy and reliability of first-generation CRONOS systems and compare CRONOS data to data from the nearest permanent weather station. CRONOS stations were installed in three winter wheat (<em>Triticum aestivum</em>) fields across Oklahoma, USA. Each was equipped with a cosmic-ray neutron sensor to measure soil water content, a camera to monitor GCC, and an all-in-one weather station. Validation sampling showed that CRONOS stations accurately determined field-scale average soil water content, with a mean absolute difference (MAD) of 0.025 cm³cm^-3 and a Nash-Sutcliffe Efficiency (NSE) of 0.742. Greater discrepancies existed between CRONOS GCC estimates and field-scale average GCC, with an MAD of 11% and NSE of 0.67. There was generally strong agreement between CRONOS atmospheric data and data from a collocated, high quality weather station, with NSE values ≥ 0.95 for measurements of air temperature and atmospheric pressure, but slightly poorer agreement for precipitation, solar radiation, relative humidity, and wind speed (NSE values ≥ 0.73). The reliability of the CRONOS cameras needs to be improved because 43% of the scheduled images were missing or unsuitable for GCC analysis, but the reliability of the other sensors was high with ≥ 98% valid observations. Overall, CRONOS stations show good potential to improve monitoring of the soil-plant-atmosphere continuum in cropland.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"10 ","pages":"Article 100737"},"PeriodicalIF":6.3,"publicationDate":"2024-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143182769","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":"CFD analysis of aeroponic nutrient spray characteristics for enhanced plant nourishment in sustainable agriculture","authors":"Aeswin Lawrance,&nbsp;K. Vishnu Ram,&nbsp;R. Harish","doi":"10.1016/j.atech.2024.100733","DOIUrl":"10.1016/j.atech.2024.100733","url":null,"abstract":"<div><div>This paper presents a detailed Computational Fluid Dynamics (CFD) analysis of nutrient spray flow characteristics from an aeroponic nozzle for enhancing plant nourishment in sustainable agriculture systems. The study investigates the flow development, velocity distribution, and multiphase turbulent characteristics of the nutrient spray emitted from the nozzle and its interaction with plant roots. The impact of nozzle diameter on nutrient spray performance is examined. Additionally, critical parameters such as the angular orientation of the nozzle and the Reynolds number are also investigated. The nutrient spray mist emitted from dual nozzles shows significant liquid fraction development as it progresses towards the plant roots. Initially, the mist is emitted uniformly, and as it evolves, the jets merge, increasing in intensity and covering a wider area, thereby enhancing nutrient concentration around the roots. Velocity analysis reveals high initial velocities near the nozzle, with increasing magnitude along the spray path but lower velocities near the roots due to no-slip boundary conditions. The merging jets create a unified stream, generating turbulent flow with multiple vortices that enhance nutrient dispersion throughout the aeroponic system. Findings indicate that reducing nozzle diameter significantly increases both spray velocity and turbulent kinetic energy. A notable increase is observed when the diameter is reduced from 40 mm to 25 mm, resulting in a 69.45% increase in spray velocity and a 58.18% increase in turbulent kinetic energy. Higher angles and Reynolds numbers lead to increased spray velocity and kinetic energy, with the highest values observed at a 55^∘ orientation. Specifically, increasing the nozzle angle from 35^∘ to 50^∘ boosts the spray velocity by 31.42% and the turbulent kinetic energy by 37.51%. This research provides valuable insights into the optimal design of aeroponic nozzles, highlighting the importance of nozzle diameter, angular orientation, and Reynolds number in maximizing nutrient delivery efficiency. The findings contribute to the advancement of sustainable agriculture by improving the design and performance of aeroponic systems for enhanced plant nourishment.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"10 ","pages":"Article 100733"},"PeriodicalIF":6.3,"publicationDate":"2024-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143183126","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":"Smart UAV-assisted rose growth monitoring with improved YOLOv10 and Mamba restoration techniques","authors":"Fan Zhao ,&nbsp;Zhiyan Ren ,&nbsp;Jiaqi Wang ,&nbsp;Qingyang Wu ,&nbsp;Dianhan Xi ,&nbsp;Xinlei Shao ,&nbsp;Yongying Liu ,&nbsp;Yijia Chen ,&nbsp;Katsunori Mizuno","doi":"10.1016/j.atech.2024.100730","DOIUrl":"10.1016/j.atech.2024.100730","url":null,"abstract":"<div><div>Recent advances in unmanned aerial vehicles (UAVs) technology and deep learning have revolutionized agricultural monitoring, yet challenges remain in processing low-resolution field imagery for precision floriculture. Here, we presented an innovative approach combining state-of-the-art super-resolution reconstruction (SRR) and object detection for accurate rose growth monitoring in large-scale greenhouse environments. We introduced MambaIR, a novel SRR algorithm based on selective state-space models, which significantly outperforms existing methods in enhancing low-resolution UAV imagery (PSNR: 28.34 dB, SSIM: 77.07 %). We also developed ROSE-YOLO, an improved object detection model tailored for rose identification, achieving 95.3 % mean average precision (mAP) on high-resolution images. The synergy between MambaIR and ROSE-YOLO enables 94.4 % mAP on reconstructed super-resolution images, nearly matching high-resolution performance. Through comprehensive experiments and Grad-CAM visualizations, we demonstrated our method's superior focus on key rose features and identify an optimal super-resolution magnification factor balancing detail enhancement and computational efficiency. This integrated approach overcomes resolution limitations in UAV-based agricultural monitoring, offering a scalable and accurate solution for rose growth assessment. Our method reduces technical barriers, offering a scalable and cost-effective solution for greenhouse monitoring by addressing low-resolution imagery challenges and enhancing decision-making processes. This research lays the groundwork for broader applications of UAV and AI technologies in sustainable agriculture. The findings pave the way for advanced, data-driven precision agriculture, integrating deep learning with remote sensing methodologies to improve floriculture management.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"10 ","pages":"Article 100730"},"PeriodicalIF":6.3,"publicationDate":"2024-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143182163","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":"Developing a robust yield prediction model for potatoes (Solanum tuberosum L.) using multi-faceted and multi-year data","authors":"Alfadhl Y. Alkhaled,&nbsp;Yi Wang","doi":"10.1016/j.atech.2024.100734","DOIUrl":"10.1016/j.atech.2024.100734","url":null,"abstract":"<div><div>Robust yield prediction models can help farmers with fertilization decisions to maintain yield while reducing impact of crop production on the environment. For potatoes, the No No 1 consumed underground crop that need high nitrogen (N) fertilizer input, accurate yield prediction during the growing season will help reduce over-use of N fertilizer and mitigate groundwater contamination issues. This multi-year study collected hyperspectral imagery (400 – 2500 nm) across different potato (<em>Solanum tuberosum</em> L.) growth stages and seasons under varied nitrogen (N) treatments. It developed random forest (RF) models to predict final tuber yield using different model inputs, including genotype (G) (cultivar), management (M) practices (N treatment), environmental (E) factors (soil temperature and precipitation), and hyperspectral data that was obtained by smart agriculture technologies (T). Our findings revealed that: 1) the top 45 (approximately ⁓ 10 % of total bands: coefficient of determination: <em>R²</em> = 0.575) bands generated from feature selection of RF could result in similar yield prediction accuracy as when using all 474 narrow-bands from the hyperspectral images, and these selected spectral signatures were distributed across the visible (VIS), near-infrared (NIR), and short-wave infrared (SWIR) regions; 2) for plants under the higher N rate, lower reflectance in the VIS region (due to more chlorophyll accumulation), higher reflectance in the NIR region (due to more dense plant canopy), and lower reflectance in the SWIR (due to higher water content) were observed; 3) The model that included multi-faceted inputs, suggesting the G × E × M × T interactions, produced highly satisfying performance (<em>R²</em> = 0.716) in comparison to the models that incorporated less inputs (using single input). Specifically, models using single input showed a performance range of <em>R²</em> = 0.009–0.728 for individual years and <em>R²</em> = 0.481–0.616 for combined years. Models incorporating two inputs demonstrated improved performance with <em>R²</em> = 0.011–0.751 for individual years and <em>R²</em> = 0.308–0.766 for combined years. Notably, models with multiple inputs achieved the highest performance, with <em>R²</em> = 0.154–0.834 for individual years and <em>R²</em> = 0.647–0.716 for combined years. 4) All years of data are needed to develop a robust and generalized potato yield prediction model. In conclusion, this study highlights the need to use a holistic approach that considers multiple facets (varietal choice, environmental conditions, management practice such as N supply, and smart agriculture technologies) of the crop production systems across different growing seasons to develop robust yield prediction models for potatoes.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"10 ","pages":"Article 100734"},"PeriodicalIF":6.3,"publicationDate":"2024-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143182103","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}