{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T17:12:18Z","timestamp":1782493938199,"version":"3.54.5"},"reference-count":28,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,1,23]],"date-time":"2025-01-23T00:00:00Z","timestamp":1737590400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100013437","name":"Ohio Soybean Council","doi-asserted-by":"publisher","award":["OSC 22-R-34"],"award-info":[{"award-number":["OSC 22-R-34"]}],"id":[{"id":"10.13039\/100013437","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000105","name":"Office of Advanced Cyberinfrastructure","doi-asserted-by":"publisher","award":["OAC-2112606"],"award-info":[{"award-number":["OAC-2112606"]}],"id":[{"id":"10.13039\/100000105","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100004376","name":"Nationwide","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100004376","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100024787","name":"Hatch","doi-asserted-by":"publisher","award":["NC1195"],"award-info":[{"award-number":["NC1195"]}],"id":[{"id":"10.13039\/501100024787","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:sec><jats:title>Introduction<\/jats:title><jats:p>Advancements in machine learning (ML) algorithms that make predictions from data without being explicitly programmed and the increased computational speeds of graphics processing units (GPUs) over the last decade have led to remarkable progress in the capabilities of ML. In many fields, including agriculture, this progress has outpaced the availability of sufficiently diverse and high-quality datasets, which now serve as a limiting factor. While many agricultural use cases appear feasible with current compute resources and ML algorithms, the lack of reusable hardware and software components, referred to as cyberinfrastructure (CI), for collecting, transmitting, cleaning, labeling, and training datasets is a major hindrance toward developing solutions to address agricultural use cases. This study focuses on addressing these challenges by exploring the collection, processing, and training of ML models using a multimodal dataset and providing a vision for agriculture-focused CI to accelerate innovation in the field.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>Data were collected during the 2023 growing season from three agricultural research locations across Ohio. The dataset includes 1 terabyte (TB) of multimodal data, comprising Unmanned Aerial System (UAS) imagery (RGB and multispectral), as well as soil and weather sensor data. The two primary crops studied were corn and soybean, which are the state's most widely cultivated crops. The data collected and processed from this study were used to train ML models to make predictions of crop growth stage, soil moisture, and final yield.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The exercise of processing this dataset resulted in four CI components that can be used to provide higher accuracy predictions in the agricultural domain. These components included (1) a UAS imagery pipeline that reduced processing time and improved image quality over standard methods, (2) a tabular data pipeline that aggregated data from multiple sources and temporal resolutions and aligned it with a common temporal resolution, (3) an approach to adapting the model architecture for a vision transformer (ViT) that incorporates agricultural domain expertise, and (4) a data visualization prototype that was used to identify outliers and improve trust in the data.<\/jats:p><\/jats:sec><jats:sec><jats:title>Discussion<\/jats:title><jats:p>Further work will be aimed at maturing the CI components and implementing them on high performance computing (HPC). There are open questions as to how CI components like these can best be leveraged to serve the needs of the agricultural community to accelerate the development of ML applications in agriculture.<\/jats:p><\/jats:sec>","DOI":"10.3389\/frai.2024.1496066","type":"journal-article","created":{"date-parts":[[2025,1,23]],"date-time":"2025-01-23T06:56:28Z","timestamp":1737615388000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Cyberinfrastructure for machine learning applications in agriculture: experiences, analysis, and vision"],"prefix":"10.3389","volume":"7","author":[{"given":"Lucas","family":"Waltz","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sushma","family":"Katari","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chaeun","family":"Hong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adit","family":"Anup","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Julian","family":"Colbert","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anirudh","family":"Potlapally","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Taylor","family":"Dill","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Canaan","family":"Porter","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"John","family":"Engle","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christopher","family":"Stewart","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hari","family":"Subramoni","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Scott","family":"Shearer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Raghu","family":"Machiraju","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Osler","family":"Ortez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Laura","family":"Lindsey","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arnab","family":"Nandi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sami","family":"Khanal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,1,23]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1109\/MCG.2021.3107875","article-title":"The role of interactive visualization in fostering trust in AI","volume":"41","author":"Beauxis-Aussalet","year":"2021","journal-title":"IEEE Comput. Graph. Appl"},{"key":"B2","author":"Burwood-Taylor","year":"2023","journal-title":"BREAKING: Alphabet brings agtech startup out of stealth with data from 10% of world's farmland, 3 major customers"},{"key":"B3","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1109\/MM.2021.3134743","article-title":"Democratizing data-driven agriculture using affordable hardware","volume":"42","author":"Chandra","year":"2022","journal-title":"IEEE Micro"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.24260\/alalbab.v1i1.18","author":"Collins","year":"2001","journal-title":"Good to great: why some companies make the leap ..., others don't"},{"key":"B5","doi-asserted-by":"publisher","first-page":"929","DOI":"10.2135\/cropsci1971.0011183X001100060051x","article-title":"Stage of development descriptions for soybeans, Glycine max (L.) Merrill 1","volume":"11","author":"Fehr","year":"1971","journal-title":"Crop Sci"},{"key":"B6","doi-asserted-by":"publisher","first-page":"3234","DOI":"10.1145\/3394486.3403375","author":"Gadiraju","year":"2020"},{"key":"B7","doi-asserted-by":"publisher","first-page":"1217","DOI":"10.1002\/agj2.21353","article-title":"Artificial intelligence in farming: Challenges and opportunities for building trust","volume":"116","author":"Gardezi","year":"2024","journal-title":"Agron. J."},{"key":"B8","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1109\/TPAMI.2022.3152247","article-title":"A survey on vision transformer","volume":"45","author":"Han","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"B9","doi-asserted-by":"publisher","first-page":"487","DOI":"10.2134\/agronj1963.00021962005500050024x","article-title":"Growth Stages of Corn (Zea mays, L.) 1","volume":"55","author":"Hanway","year":"1963","journal-title":"Agron. J"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.17632\/tywbtsjrjv.1","author":"J A. P.","year":"2019","journal-title":"Data for: Identification of plant leaf diseases using a 9-layer deep convolutional neural network."},{"key":"B11","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1145\/3131214.3131220","article-title":"Experiences deploying an always-on farm network","volume":"21","author":"Kapetanovic","year":"2017","journal-title":"GetMobile: Mob. Comput. Commun."},{"key":"B12","doi-asserted-by":"publisher","first-page":"3783","DOI":"10.3390\/rs12223783","article-title":"Remote sensing in agriculture\u2014accomplishments, limitations, and opportunities","volume":"12","author":"Khanal","year":"2020","journal-title":"Remote Sens."},{"key":"B13","volume-title":"Advances in Neural Information Processing Systems, Volume 25","author":"Krizhevsky","year":"2012"},{"key":"B14","first-page":"56","author":"Lindsey","year":"2017"},{"key":"B15","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1016\/S0168-1923(97)00027-0","article-title":"Growing degree-days: one equation, two interpretations","volume":"87","author":"McMaster","year":"1997","journal-title":"Agric. For. Meteorol"},{"key":"B16","unstructured":"New croissant metadata format helps standardize mL datasets\n          \n          2024"},{"key":"B17","unstructured":"Nielsen\n              R. L.\n            \n          \n          Hybrid maturity decisions for delayed planting\n          \n          2022"},{"key":"B18","doi-asserted-by":"publisher","first-page":"4429","DOI":"10.1002\/agj2.20812","article-title":"Data from a public-industry partnership for enhancing corn nitrogen research","volume":"113","author":"Ransom","year":"2021","journal-title":"Agron. J"},{"key":"B19","doi-asserted-by":"publisher","first-page":"2669","DOI":"10.1002\/agj2.20974","article-title":"Cultivating trust in technology-mediated sustainable agricultural research","volume":"114","author":"Raturi","year":"2022","journal-title":"Agron. J."},{"key":"B20","volume-title":"The Lean Startup: How Today's Entrepreneurs Use Continuous Innovation to Create Radically Successful Businesses","author":"Ries","year":"2011"},{"key":"B21","first-page":"596","author":"Sohn","year":"2020"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-22155-2","author":"Taheri","year":"2023","journal-title":"Edge Intelligence: From Theory to Practice"},{"key":"B23","first-page":"32","volume-title":"Ohio Agronomy Guide, Volume 472 of Bulletin","author":"Thomison","year":"2017"},{"key":"B24","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1016\/j.future.2019.04.020","article-title":"The role of big data analytics in industrial internet of things","volume":"99","author":"Ur Rehman","year":"2019","journal-title":"Future Gener. Comput. Syst"},{"key":"B25","volume-title":"Advances in Neural Information Processing Systems, Volume 30","author":"Vaswani","year":"2017"},{"key":"B26","author":"Waltz","year":"2024"},{"key":"B27","first-page":"670","author":"Wang","year":"1993"},{"key":"B28","doi-asserted-by":"publisher","first-page":"791","DOI":"10.1007\/s00778-022-00775-9","article-title":"Data collection and quality challenges in deep learning: a data-centric AI perspective","volume":"32","author":"Whang","year":"2023","journal-title":"VLDB J"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2024.1496066\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,23]],"date-time":"2025-01-23T06:56:35Z","timestamp":1737615395000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2024.1496066\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,23]]},"references-count":28,"alternative-id":["10.3389\/frai.2024.1496066"],"URL":"https:\/\/doi.org\/10.3389\/frai.2024.1496066","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,23]]},"article-number":"1496066"}}