{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T18:53:47Z","timestamp":1771268027402,"version":"3.50.1"},"reference-count":24,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T00:00:00Z","timestamp":1761868800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100019465","name":"Arab\u2013German Young Academy of Sciences and Humanities","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100019465","id-type":"DOI","asserted-by":"crossref"}]},{"name":"the German Federal Ministry of Research, Technology and Space","award":["01DL25001"],"award-info":[{"award-number":["01DL25001"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["MAKE"],"abstract":"<jats:p>Federated learning (FL) provides a privacy-preserving approach for training machine learning models across distributed datasets; however, its deployment in environmental monitoring remains underexplored. This paper uses the WHIN dataset, comprising 144 weather stations across Indiana, to establish a benchmark for FL in soil moisture prediction. The work presents three primary contributions: the design of lightweight CNNs optimized for edge deployment, a comprehensive robustness assessment of FL under non-IID and adversarial conditions, and the development of a large-scale, reproducible agricultural FL benchmark using the WHIN network. The paper designs and evaluates lightweight (\u223c0.8 k parameters) and heavy (\u223c9.4 k parameters) convolutional neural networks (CNNs) under both centralized and federated settings, supported by ablation studies on feature importance and model architecture. Results show that lightweight CNNs achieve near-heavy CNN performance (MAE = 7.8 cbar vs. 7.6 cbar) while reducing computation and communication overhead. Beyond accuracy, this work systematically benchmarks robustness under adversarial and non-IID conditions, providing new insights for deploying federated models in agricultural IoT.<\/jats:p>","DOI":"10.3390\/make7040132","type":"journal-article","created":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T13:22:36Z","timestamp":1762176156000},"page":"132","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Federated Learning for Soil Moisture Prediction: Benchmarking Lightweight CNNs and Robustness in Distributed Agricultural IoT Networks"],"prefix":"10.3390","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-6979-3101","authenticated-orcid":false,"given":"Salma","family":"Zakzouk","sequence":"first","affiliation":[{"name":"School of Engineering and Applied Sciences, Nile University, Giza 12588, Egypt"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8223-4625","authenticated-orcid":false,"given":"Lobna A.","family":"Said","sequence":"additional","affiliation":[{"name":"Nanoelectronics Integrated Systems Center (NISC), Nile University, Giza 12588, Egypt"}]}],"member":"1968","published-online":{"date-parts":[[2025,10,31]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"717","DOI":"10.5194\/essd-11-717-2019","article-title":"Evolution of the ESA CCI Soil Moisture Climate Data Records and Their Underlying Merging Methodology","volume":"11","author":"Gruber","year":"2019","journal-title":"Earth Syst. Sci. Data"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"e2023WR035194","DOI":"10.1029\/2023WR035194","article-title":"A deep learning approach based on physical constraints for predicting soil moisture in unsaturated zones","volume":"59","author":"Wang","year":"2023","journal-title":"Water Resour. Res."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Acharya, U., Daigh, A.L., and Oduor, P.G. (2021). Machine learning for predicting field soil moisture using soil, crop, and nearby weather station data in the Red River Valley of the North. Soil Syst., 5.","DOI":"10.3390\/soilsystems5040057"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Rakib, M., Mohammed, A.A., Diggins, D.C., Sharma, S., Sadler, J.M., Ochsner, T., and Bagavathi, A. (2024, January 6\u201310). MIS-ME: A Multi-Modal Framework for Soil Moisture Estimation. Proceedings of the 2024 IEEE 11th International Conference on Data Science and Advanced Analytics (DSAA), San Diego, CA, USA.","DOI":"10.1109\/DSAA61799.2024.10722779"},{"key":"ref_5","first-page":"122","article-title":"Iot-based automated management irrigation system using soil moisture data and weather forecasting adopting machine learning technique","volume":"3","year":"2023","journal-title":"Sohag Eng. J."},{"key":"ref_6","unstructured":"Sungmin, O., and Orth, R. (2020). Global soil moisture from in-situ measurements using machine learning\u2014SoMo. ml. arXiv."},{"key":"ref_7","first-page":"1","article-title":"A comprehensive study of deep learning for soil moisture prediction","volume":"2023","author":"Wang","year":"2023","journal-title":"Hydrol. Earth Syst. Sci. Discuss."},{"key":"ref_8","unstructured":"Zhang, T., Zhou, Q., Yang, S., and Li, J. (2021). Soil moisture estimation using convolutional neural networks with multi-source remote sensing data. Remote Sens., 13."},{"key":"ref_9","first-page":"100880","article-title":"Machine learning enabled IoT system for soil nutrients monitoring and crop recommendation","volume":"14","author":"Islam","year":"2023","journal-title":"J. Agric. Food Res."},{"key":"ref_10","unstructured":"Deforce, B., Baesens, B., and Asensio, E.S. (2024). Time-Series Foundation Models for Forecasting Soil Moisture Levels in Smart Agriculture. arXiv."},{"key":"ref_11","unstructured":"Yu, Y., Filippi, P., and Bishop, T.F. (2025). Field-scale soil moisture estimated from Sentinel-1 SAR data using a knowledge-guided deep learning approach. arXiv."},{"key":"ref_12","unstructured":"Xie, J., Yao, B., and Jiang, Z. (2024). Physics-constrained Active Learning for Soil Moisture Estimation and Optimal Sensor Placement. arXiv."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"e2021GL096847","DOI":"10.1029\/2021GL096847","article-title":"A multiscale deep learning model for soil moisture integrating satellite and in situ data","volume":"49","author":"Liu","year":"2022","journal-title":"Geophys. Res. Lett."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"\u017dalik, K.R., and \u017dalik, M. (2023). A review of federated learning in agriculture. Sensors, 23.","DOI":"10.3390\/s23239566"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Dong, Y., Werling, B., Cao, Z., and Li, G. (2024). Implementation of an in-field IoT system for precision irrigation management. Front. Water, 6.","DOI":"10.3389\/frwa.2024.1353597"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Chen, S., Long, G., Shen, T., and Jiang, J. (2023). Prompt federated learning for weather forecasting: Toward foundation models on meteorological data. arXiv.","DOI":"10.24963\/ijcai.2023\/393"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"e12684","DOI":"10.1111\/coin.12684","article-title":"UReslham: Radar reflectivity inversion for smart agriculture with spatial federated learning over geostationary satellite observations","volume":"40","author":"Jin","year":"2024","journal-title":"Comput. Intell."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1227","DOI":"10.1109\/OJCS.2025.3590102","article-title":"Optimizing Federated Learning with Aggregation Strategies: A Comprehensive Survey","volume":"6","author":"Khan","year":"2025","journal-title":"IEEE Open J. Comput. Soc."},{"key":"ref_19","first-page":"107743","article-title":"Federated learning-based crop yield prediction using multi-source agricultural data","volume":"207","author":"Shao","year":"2023","journal-title":"Comput. Electron. Agric."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1915","DOI":"10.1007\/s11831-023-10032-z","article-title":"Review of Lightweight Deep Convolutional Neural Networks","volume":"31","author":"Chen","year":"2024","journal-title":"Arch. Comput. Methods Eng."},{"key":"ref_21","unstructured":"Wabash Heartland Innovation Network (WHIN) (2025, July 15). WHIN Weather Network Data (Current Conditions). One-Month Sample Dataset from over 140 Weather Stations; Available Free for Educators, Students, and Researchers. Available online: https:\/\/data.whin.org\/data\/current-conditions."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1016\/j.jhydrol.2013.11.061","article-title":"On the spatio-temporal dynamics of soil moisture at the field scale","volume":"516","author":"Vereecken","year":"2014","journal-title":"J. Hydrol."},{"key":"ref_23","unstructured":"Cohen, J. (1988). Statistical Power Analysis for the Behavioral Sciences, Lawrence Erlbaum Associates. [2nd ed.]."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1037\/a0024338","article-title":"Effect size estimates: Current use, calculations, and interpretation","volume":"141","author":"Fritz","year":"2012","journal-title":"J. Exp. Psychol. Gen."}],"container-title":["Machine Learning and Knowledge Extraction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-4990\/7\/4\/132\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T05:22:40Z","timestamp":1762233760000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-4990\/7\/4\/132"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,31]]},"references-count":24,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["make7040132"],"URL":"https:\/\/doi.org\/10.3390\/make7040132","relation":{},"ISSN":["2504-4990"],"issn-type":[{"value":"2504-4990","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,31]]}}}