{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T09:37:38Z","timestamp":1786441058722,"version":"build-2736575974"},"reference-count":46,"publisher":"MDPI AG","issue":"16","license":[{"start":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T00:00:00Z","timestamp":1786060800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"AgrifoodTEF project of the Digital Europe Programme","award":["GA #101100622"],"award-info":[{"award-number":["GA #101100622"]}]},{"award":["GA #101100622"],"award-info":[{"award-number":["GA #101100622"]}],"id":[{"id":"https:\/\/ror.org\/022z2ef35","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Identifying plant health conditions is an emerging precision-agriculture and food-security challenge, intensified by deploying deep-learning models on memory- and power-constrained edge devices. We present a TinyMLOps pipeline spanning model design, optimization, quantization, and deployment across diverse edge devices, evaluated under controlled laboratory conditions. Using a dataset derived from the PlantVillage benchmark, 39 fine-grained classes are aggregated into three superclasses: healthy leaf, unhealthy leaf, and no leaves. The resulting system therefore performs plant health-status classification and background filtering rather than diagnosing specific diseases. We train a MobileNet-based convolutional neural network jointly optimized for classification accuracy and computational efficiency, adopting state-of-the-art hyperparameter optimization (HPO) tools. Five models are selected, four from the Pareto Front and one as the biggest evaluated model during HPO, converted to LiteRT and ONNX, and evaluated at float32 and post-training int8 precision on a Raspberry Pi Zero 2 W and an STM32H743ZI microcontroller. At float32, LiteRT is 1.87\u20132.65\u00d7 faster than ONNX Runtime on the Raspberry Pi across all five models. Relative to their float32 LiteRT counterparts, the int8 LiteRT models are 2.83\u20133.67\u00d7 smaller on disk and 21.3\u201331.2% faster on the same board, at a cost in F1-score of between 0.0010 and 0.0068. On the microcontroller, only the two smallest models deploy at both precisions; for these, the fully quantized int8 variants are 4.3\u00d7 faster and 3.85\u00d7 smaller in MCU flash footprint than the float32 counterparts. The mid-range model fits the 2 MB flash and 1 MB RAM budget only when quantized, while the two largest models exceed it in every configuration tested.<\/jats:p>","DOI":"10.3390\/s26165029","type":"journal-article","created":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:00:43Z","timestamp":1786118443000},"page":"5029","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A TinyMLOps Pipeline for Coarse-Grained Plant Disease Classification in Precision Agriculture"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-4193-0470","authenticated-orcid":false,"given":"Hossein","family":"Aqasizade","sequence":"first","affiliation":[{"name":"Fondazione Bruno Kessler, 38123 Trento, Italy"},{"name":"Department of Information Engineering and Computer Science, University of Trento, 38123 Trento, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1685-0264","authenticated-orcid":false,"given":"Mattia","family":"Antonini","sequence":"additional","affiliation":[{"name":"Fondazione Bruno Kessler, 38123 Trento, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4426-8220","authenticated-orcid":false,"given":"Massimo","family":"Vecchio","sequence":"additional","affiliation":[{"name":"Fondazione Bruno Kessler, 38123 Trento, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5221-7752","authenticated-orcid":false,"given":"Fabio","family":"Antonelli","sequence":"additional","affiliation":[{"name":"Fondazione Bruno Kessler, 38123 Trento, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,7]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Lovell-Read, F.A., Parnell, S., Cunniffe, N.J., and Thompson, R.N. (2023). Using \u2019sentinel\u2019 plants to improve early detection of invasive plant pathogens. PLoS Comput. Biol., 19.","DOI":"10.1371\/journal.pcbi.1010884"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"20151478","DOI":"10.1098\/rspb.2015.1478","article-title":"Early detection surveillance for an emerging plant pathogen: A rule of thumb to predict prevalence at first discovery","volume":"282","author":"Parnell","year":"2015","journal-title":"Proc. R. Soc. B Biol. Sci."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Shekhar, S., Durgam, M., Khose, S.B., Pohshna, C., and Bhalekar, D.G. (2024). Advancement and Challenges of Implementing Artificial Intelligence of Things in Precision Agriculture. Artificial Intelligence Techniques in Smart Agriculture, Springer Nature.","DOI":"10.1007\/978-981-97-5878-4_13"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1007\/s10462-024-11100-x","article-title":"Deep learning and computer vision in plant disease detection: A comprehensive review of techniques, models, and trends in precision agriculture","volume":"58","author":"Upadhyay","year":"2025","journal-title":"Artif. Intell. Rev."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Antonini, M., Pincheira, M., Vecchio, M., and Antonelli, F. (2022). Tiny-MLOps: A framework for orchestrating ML applications at the far edge of IoT systems. Proceedings of the 2022 IEEE International Conference on Evolving and Adaptive Intelligent Systems (EAIS), IEEE.","DOI":"10.1109\/EAIS51927.2022.9787703"},{"key":"ref_6","unstructured":"Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., and Adam, H. (2017). MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. arXiv."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Akiba, T., Sano, S., Yanase, T., Ohta, T., and Koyama, M. (2019, January 4\u20138). Optuna: A Next-generation Hyperparameter Optimization Framework. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Anchorage, AK, USA.","DOI":"10.1145\/3292500.3330701"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"113317","DOI":"10.1016\/j.engappai.2025.113317","article-title":"Deep learning generalized hybrid models for multi-species crop disease classification with explainable insights","volume":"164","author":"Wadhwa","year":"2026","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"107682","DOI":"10.1016\/j.engappai.2023.107682","article-title":"Precision agriculture based on convolutional neural network in rice production nutrient management using machine learning genetic algorithm","volume":"130","author":"Sakthipriya","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"111773","DOI":"10.1016\/j.engappai.2025.111773","article-title":"A computer vision-based crop and weed segmentation using federated ensemble learning in diverse multi-crop fields","volume":"159","author":"Sivakumar","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Khan, A.T., Jensen, S.M., Khan, A.R., and Li, S. (2023). Plant disease detection model for edge computing devices. Front. Plant Sci., 14.","DOI":"10.3389\/fpls.2023.1308528"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Mohanty, S.P., Hughes, D.P., and Salath\u00e9, M. (2016). Using deep learning for image-based plant disease detection. Front. Plant Sci., 7.","DOI":"10.3389\/fpls.2016.01419"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"9237136","DOI":"10.34133\/2019\/9237136","article-title":"How convolutional neural networks diagnose plant disease","volume":"2019","author":"Toda","year":"2019","journal-title":"Plant Phenomics"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1016\/j.compeleceng.2019.04.011","article-title":"Identification of plant leaf diseases using a nine-layer deep convolutional neural network","volume":"76","author":"Geetharamani","year":"2019","journal-title":"Comput. Electr. Eng."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"55","DOI":"10.13164\/mendel.2022.1.055","article-title":"Color-aware two-branch dcnn for efficient plant disease classification","volume":"28","author":"Schuler","year":"2022","journal-title":"Mendel"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"112415","DOI":"10.1016\/j.engappai.2025.112415","article-title":"Towards efficient stream monitoring: A systematic approach for model selection and continuous improvement in Tiny Machine Learning applications","volume":"162","author":"Arratia","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Aqasizade, H., Antonini, M., Vecchio, M., and Antonelli, F. (2025). A TinyMLOps-Based Edge AI Approach for Early Detection of Emerging Plant Diseases. Proceedings of the 2025 IEEE International Workshop on Metrology for Industry 4.0 & IoT (MetroInd4. 0 & IoT), IEEE.","DOI":"10.1109\/MetroInd4.0IoT66048.2025.11122104"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1007\/s00607-024-01388-6","article-title":"InTec: Integrated things-edge computing: A framework for distributing machine learning pipelines in edge AI systems","volume":"107","author":"Larian","year":"2025","journal-title":"Computing"},{"key":"ref_19","unstructured":"Jenhani, Z., Bensalem, M., Dizdarevi\u0107, J., and Jukan, A. (2025). An Experimental Study of Split-Learning TinyML on Ultra-Low-Power Edge\/IoT Nodes. arXiv."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1656","DOI":"10.1109\/OJCOMS.2024.3373177","article-title":"Tinyml empowered transfer learning on the edge","volume":"5","author":"Hayajneh","year":"2024","journal-title":"IEEE Open J. Commun. Soc."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"90970","DOI":"10.1109\/ACCESS.2025.3567816","article-title":"Efficient Detection of Microplastics on Edge Devices with Tailored Compiler for TinyML Applications","volume":"13","author":"Cerioli","year":"2025","journal-title":"IEEE Access"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"L\u00ea, M.T., and Arbel, J. (2023, January 8\u201312). TinyMLOps for real-time ultra-low power MCUs applied to frame-based event classification. Proceedings of the 3rd Workshop on Machine Learning and Systems, Rome, Italy.","DOI":"10.1145\/3578356.3592586"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Leroux, S., Simoens, P., Lootus, M., Thakore, K., and Sharma, A. (2022). Tinymlops: Operational challenges for widespread edge ai adoption. Proceedings of the 2022 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), IEEE.","DOI":"10.1109\/IPDPSW55747.2022.00160"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Peltonen, E., and Dias, S. (2023, January 17). LinkEdge: Open-sourced MLOps integration with IoT edge. Proceedings of the 3rd Eclipse Security, AI, Architecture and Modelling Conference on Cloud to Edge Continuum, Ludwigsburg, Germany.","DOI":"10.1145\/3624486.3624496"},{"key":"ref_25","first-page":"1","article-title":"SensiX++: Bringing mlops and multi-tenant model serving to sensory edge devices","volume":"22","author":"Min","year":"2023","journal-title":"ACM Trans. Embed. Comput. Syst."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1007\/s12243-024-01041-5","article-title":"RIOT-ML: Toolkit for over-the-air secure updates and performance evaluation of TinyML models","volume":"80","author":"Huang","year":"2025","journal-title":"Ann. Telecommun."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Karras, A., Giannaros, A., Karras, C., Theodorakopoulos, L., Mammassis, C.S., Krimpas, G.A., and Sioutas, S. (2024). TinyML algorithms for big data management in large-scale IoT systems. Future Internet, 16.","DOI":"10.3390\/fi16020042"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"103281","DOI":"10.1016\/j.asej.2025.103281","article-title":"Safeguarding IoT consumer devices: Deep learning with TinyML driven real-time anomaly detection for predictive maintenance","volume":"16","author":"Katib","year":"2025","journal-title":"Ain Shams Eng. J."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1109\/MM.2024.3354323","article-title":"Advancing Tiny Machine Learning Operations: Robust model updates in the internet of intelligent vehicles","volume":"45","author":"Flores","year":"2024","journal-title":"IEEE Micro"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"108260","DOI":"10.1016\/j.engappai.2024.108260","article-title":"Fruit and vegetable disease detection and classification: Recent trends, challenges, and future opportunities","volume":"133","author":"Gupta","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"106034","DOI":"10.1016\/j.engappai.2023.106034","article-title":"A comparative study of deep learning and Internet of Things for precision agriculture","volume":"122","author":"Saranya","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"110401","DOI":"10.1016\/j.engappai.2025.110401","article-title":"Systematic review on machine learning and computer vision in precision agriculture: Applications, trends, and emerging techniques","volume":"148","author":"Kuan","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"112163","DOI":"10.1016\/j.engappai.2025.112163","article-title":"A lightweight and improved you only look once model using GhostWise convolution and attention mechanism for accurate plant disease detection","volume":"161","author":"Dikici","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Buslaev, A., Iglovikov, V.I., Khvedchenya, E., Parinov, A., Druzhinin, M., and Kalinin, A.A. (2020). Albumentations: Fast and Flexible Image Augmentations. Information, 11.","DOI":"10.3390\/info11020125"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Seilov, S., Nurzhaubayev, A., Baideldinov, M., Zhursinbek, B., Ashimgaliyev, M., and Zhumadillayeva, A. (2025). Hybrid Multi-Scale Neural Network with Attention-Based Fusion for Fruit Crop Disease Identification. J. Imaging, 11.","DOI":"10.3390\/jimaging11120440"},{"key":"ref_36","unstructured":"(2026, July 01). PlantVillage-AugNoLeaves\u2014AgrifoodTEF Data Space Catalogue. Available online: https:\/\/dataspace.agrifoodtef.eu\/asset\/did:op:3091fdcf83a05784416e585e4e45ea24afaf8c925a891921a3949acd98426f65."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1109\/4235.797969","article-title":"Multiobjective evolutionary algorithms: A comparative case study and the strength Pareto approach","volume":"3","author":"Zitzler","year":"1999","journal-title":"IEEE Trans. Evol. Comput."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"182","DOI":"10.1109\/4235.996017","article-title":"A fast and elitist multiobjective genetic algorithm: NSGA-II","volume":"6","author":"Deb","year":"2002","journal-title":"IEEE Trans. Evol. Comput."},{"key":"ref_39","first-page":"39","article-title":"Accelerating the Machine Learning Lifecycle with MLflow","volume":"41","author":"Zaharia","year":"2018","journal-title":"IEEE Data Eng. Bull."},{"key":"ref_40","unstructured":"Duplyakin, D., Ricci, R., Maricq, A., Wong, G., Duerig, J., Eide, E., Stoller, L., Hibler, M., Johnson, D., and Webb, K. (2019, January 10\u201312). The Design and Operation of CloudLab. Proceedings of theUSENIX Annual Technical Conference (ATC), Renton, WA, USA."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Aqasizade, H., Ataie, E., and Bastam, M. (2025). Kubernetes in action: Exploring the performance of kubernetes distributions in the cloud. Software: Practice and Experience, John Wiley & Sons Ltd.","DOI":"10.1002\/spe.70000"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"424","DOI":"10.5829\/ije.2025.38.02b.16","article-title":"An Empirical Study on Impact of Programming Languages on Performance of Open-source Serverless Platforms","volume":"38","author":"Ataie","year":"2025","journal-title":"Int. J. Eng."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1162\/evco.1994.2.3.221","article-title":"Muiltiobjective optimization using nondominated sorting in genetic algorithms","volume":"2","author":"Srinivas","year":"1994","journal-title":"Evol. Comput."},{"key":"ref_44","unstructured":"Google (2026, July 01). LiteRT Overview. Available online: https:\/\/ai.google.dev\/edge\/litert."},{"key":"ref_45","unstructured":"ONNX Runtime Developers (2026, July 01). ONNX Runtime. Available online: https:\/\/onnxruntime.ai\/."},{"key":"ref_46","unstructured":"Google (2026, July 01). Post-Training Integer Quantization. Available online: https:\/\/ai.google.dev\/edge\/litert\/models\/post_training_integer_quant."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/16\/5029\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T09:12:56Z","timestamp":1786439576000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/16\/5029"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,7]]},"references-count":46,"journal-issue":{"issue":"16","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["s26165029"],"URL":"https:\/\/doi.org\/10.3390\/s26165029","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,7]]}}}