{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T18:11:08Z","timestamp":1764785468604,"version":"3.37.3"},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2024,9,2]],"date-time":"2024-09-02T00:00:00Z","timestamp":1725235200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,9,2]],"date-time":"2024-09-02T00:00:00Z","timestamp":1725235200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100020259","name":"Instituto de F\u00edsica de Cantabria","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100020259","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Earth Sci Inform"],"published-print":{"date-parts":[[2024,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>The increasing generation of data in different areas of life, such as the environment, highlights the need to explore new techniques for processing and exploiting data for useful purposes. In this context, artificial intelligence techniques, especially through deep learning models, are key tools to be used on the large amount of data that can be obtained, for example, from weather radars. In many cases, the information collected by these radars is not open, or belongs to different institutions, thus needing to deal with the distributed nature of this data. In this work, the applicability of a personalized federated learning architecture, which has been called <jats:italic>adapFL<\/jats:italic>, on distributed weather radar images is addressed. To this end, given a single available radar covering 400 km in diameter, the captured images are divided in such a way that they are disjointly distributed into four different federated clients. The results obtained with <jats:italic>adapFL<\/jats:italic> are analyzed in each zone, as well as in a central area covering part of the surface of each of the previously distributed areas. The ultimate goal of this work is to study the generalization capability of this type of learning technique for its extrapolation to use cases in which a representative number of radars is available, whose data can not be centralized due to technical, legal or administrative concerns. The results of this preliminary study indicate that the performance obtained in each zone with the <jats:italic>adapFL<\/jats:italic> approach allows improving the results of the federated learning approach, the individual deep learning models and the classical Continuity Tracking Radar Echoes by Correlation approach.<\/jats:p>","DOI":"10.1007\/s12145-024-01438-9","type":"journal-article","created":{"date-parts":[[2024,9,2]],"date-time":"2024-09-02T07:02:15Z","timestamp":1725260535000},"page":"5561-5584","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Personalized federated learning for improving radar based precipitation nowcasting on heterogeneous areas"],"prefix":"10.1007","volume":"17","author":[{"given":"Judith","family":"S\u00e1inz-Pardo D\u00edaz","sequence":"first","affiliation":[]},{"given":"Mar\u00eda","family":"Castrillo","sequence":"additional","affiliation":[]},{"given":"Juraj","family":"Bartok","sequence":"additional","affiliation":[]},{"given":"Ignacio Heredia","family":"Cach\u00e1","sequence":"additional","affiliation":[]},{"given":"Irina Malkin","family":"Ond\u00edk","sequence":"additional","affiliation":[]},{"given":"Ivan","family":"Martynovskyi","sequence":"additional","affiliation":[]},{"given":"Khadijeh","family":"Alibabaei","sequence":"additional","affiliation":[]},{"given":"Lisana","family":"Berberi","sequence":"additional","affiliation":[]},{"given":"Valentin","family":"Kozlov","sequence":"additional","affiliation":[]},{"given":"\u00c1lvaro","family":"L\u00f3pez Garc\u00eda","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,9,2]]},"reference":[{"key":"1438_CR1","unstructured":"Abadi M, Agarwal A, Barham P et\u00a0al (2015) TensorFlow: large-scale machine learning on heterogeneous systems. https:\/\/www.tensorflow.org\/, software available from tensorflow.org"},{"key":"1438_CR2","unstructured":"Agrawal S, Barrington L, Bromberg C et\u00a0al (2019) Machine learning for precipitation nowcasting from radar images. 1912.12132"},{"key":"1438_CR3","doi-asserted-by":"publisher","unstructured":"Agrawal S, Sarkar S, Aouedi O et al (2022) Federated learning for intrusion detection system: concepts, challenges and future directions. Comput Commun 195:346\u2013361. https:\/\/doi.org\/10.1016\/j.comcom.2022.09.012, https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0140366422003516","DOI":"10.1016\/j.comcom.2022.09.012"},{"key":"1438_CR4","unstructured":"AI4EOSC project (2024) AI4EOSC website. https:\/\/ai4eosc.eu\/. Accessed 19 Feb 2024"},{"key":"1438_CR5","doi-asserted-by":"crossref","unstructured":"Chen L, Cao Y, Ma L et\u00a0al (2020) A deep learning-based methodology for precipitation nowcasting with radar. Earth and Space Science 7(2):e2019EA000812","DOI":"10.1029\/2019EA000812"},{"issue":"9","key":"1438_CR6","first-page":"1641","volume":"38","author":"J Cuomo","year":"2021","unstructured":"Cuomo J, Chandrasekar V (2021) Use of deep learning for weather radar nowcasting. J Atmos Oceanic Tech 38(9):1641\u20131656","journal-title":"J Atmos Oceanic Tech"},{"key":"1438_CR7","unstructured":"Fan H, Ling H (2018) Siamese cascaded region proposal networks for real-time visual tracking. 1812.06148"},{"key":"1438_CR8","unstructured":"Goodfellow I, Pouget-Abadie J, Mirza M et\u00a0al (2014) Generative adversarial nets. In: Ghahramani Z, Welling M, Cortes C et\u00a0al (eds) Advances in Neural Information Processing Systems, vol\u00a027. Curran Associates, Inc., https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2014\/file\/5ca3e9b122f61f8f06494c97b1afccf3-Paper.pdf"},{"key":"1438_CR9","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1016\/j.patcog.2017.10.013","volume":"77","author":"J Gu","year":"2018","unstructured":"Gu J, Wang Z, Kuen J et al (2018) Recent advances in convolutional neural networks. Pattern Recogn 77:354\u2013377. https:\/\/doi.org\/10.1016\/j.patcog.2017.10.013","journal-title":"Pattern Recogn"},{"key":"1438_CR10","first-page":"1","volume":"2023","author":"D Han","year":"2023","unstructured":"Han D, Shin Y, Im J et al (2023) Key factors for quantitative precipitation nowcasting using ground weather radar data based on deep learning. Geoscientific Model Development Discussions 2023:1\u201343","journal-title":"Geoscientific Model Development Discussions"},{"key":"1438_CR11","doi-asserted-by":"publisher","unstructured":"Han L, Zhao Y, Chen H et\u00a0al (2022) Advancing radar nowcasting through deep transfer learning. IEEE Transactions on Geoscience and Remote Sensing 60:1\u2013https:\/\/doi.org\/10.1109\/TGRS.2021.3056470","DOI":"10.1109\/TGRS.2021.3056470"},{"issue":"3","key":"1438_CR12","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1016\/j.jhydrol.2010.08.024","volume":"393","author":"M Hanel","year":"2010","unstructured":"Hanel M, Buishand TA (2010) On the value of hourly precipitation extremes in regional climate model simulations. J Hydrol 393(3):265\u2013273. https:\/\/doi.org\/10.1016\/j.jhydrol.2010.08.024","journal-title":"J Hydrol"},{"key":"1438_CR13","doi-asserted-by":"publisher","first-page":"125249","DOI":"10.1016\/j.jhydrol.2020.125249","volume":"590","author":"P Hosseinzadehtalaei","year":"2020","unstructured":"Hosseinzadehtalaei P, Tabari H, Willems P (2020) Climate change impact on short-duration extreme precipitation and intensity-duration-frequency curves over Europe. J Hydrol 590:125249. https:\/\/doi.org\/10.1016\/j.jhydrol.2020.125249","journal-title":"J Hydrol"},{"key":"1438_CR14","volume-title":"Forecast verification: a practitioner\u2019s guide in atmospheric science","author":"IT Jolliffe","year":"2012","unstructured":"Jolliffe IT, Stephenson DB (2012) Forecast verification: a practitioner\u2019s guide in atmospheric science. John Wiley & Sons"},{"key":"1438_CR15","doi-asserted-by":"publisher","unstructured":"Kesa O, Styles O, Sanchez V (2022) Multiple object tracking and forecasting: jointly predicting current and future object locations. In: 2022 IEEE\/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW), pp 560\u201356 https:\/\/doi.org\/10.1109\/WACVW54805.2022.00062","DOI":"10.1109\/WACVW54805.2022.00062"},{"issue":"10","key":"1438_CR16","doi-asserted-by":"publisher","first-page":"1486","DOI":"10.1109\/TIP.2005.854442","volume":"14","author":"J Kim","year":"2005","unstructured":"Kim J, Fisher JW, Yezzi A et al (2005) A nonparametric statistical method for image segmentation using information theory and curve evolution. IEEE Trans Image Process 14(10):1486\u20131502. https:\/\/doi.org\/10.1109\/TIP.2005.854442","journal-title":"IEEE Trans Image Process"},{"key":"1438_CR17","unstructured":"Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv:1412.6980"},{"key":"1438_CR18","doi-asserted-by":"publisher","unstructured":"Ko J, Lee K, Hwang H et al (2022) Effective training strategies for deep-learning-based precipitation nowcasting and estimation. Computers & Geosciences 161:10507. https:\/\/doi.org\/10.1016\/j.cageo.2022.105072, https:\/\/www.sciencedirect.com\/science\/article\/pii\/S009830042200036X","DOI":"10.1016\/j.cageo.2022.105072"},{"key":"1438_CR19","doi-asserted-by":"crossref","unstructured":"Komj\u00e1ti K, Varga \u00c1J, M\u00e9ri L et\u00a0al (2022) Investigation of a supercell merger leading to the ef4 tornado in the Czech Republic on june 24, 2021 using radar data and numerical model outputs. Id\u00f6j\u00e1r\u00e1s 126(4)","DOI":"10.28974\/idojaras.2022.4.2"},{"key":"1438_CR20","unstructured":"Korosec M (2021) The most powerful tornado on record hit the Czech Republic, leaving several fatalities and 200+ injured across the hodonin district. Weather Report https:\/\/www.severe-weather.eu\/weather-report\/europe-severe-weather-tornado-hodonin-czech-republic-mk\/, published: 25\/06\/2021"},{"key":"1438_CR21","doi-asserted-by":"publisher","unstructured":"Kumar B, Haral H, Kalapureddy M et al (2024) Utilizing deep learning for near real-time rainfall forecasting based on radar data. Physics and Chemistry of the Earth, Parts A\/B\/C 135:103600. https:\/\/doi.org\/10.1016\/j.pce.2024.103600, https:\/\/www.sciencedirect.com\/science\/article\/pii\/S1474706524000585","DOI":"10.1016\/j.pce.2024.103600"},{"key":"1438_CR22","doi-asserted-by":"crossref","unstructured":"Li B, Wu W, Wang Q, et\u00a0al (2018) Siamrpn++: evolution of siamese visual tracking with very deep networks. 1812.11703","DOI":"10.1109\/CVPR.2019.00441"},{"key":"1438_CR23","unstructured":"McMahan B, Moore E, Ramage D et\u00a0al (2017) Communication-Efficient Learning of Deep Networks from Decentralized Data. In: Singh A, Zhu J (eds) Proceedings of the 20th international conference on artificial intelligence and statistics, Proceedings of Machine Learning Research, vol\u00a054. PMLR, pp 1273\u20131282. https:\/\/proceedings.mlr.press\/v54\/mcmahan17a.html"},{"issue":"6","key":"1438_CR24","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1109\/MCOM.001.1900461","volume":"58","author":"S Niknam","year":"2020","unstructured":"Niknam S, Dhillon HS, Reed JH (2020) Federated learning for wireless communications: motivation, opportunities, and challenges. IEEE Commun Mag 58(6):46\u201351. https:\/\/doi.org\/10.1109\/MCOM.001.1900461","journal-title":"IEEE Commun Mag"},{"key":"1438_CR25","doi-asserted-by":"publisher","unstructured":"Novak P (2007) The czech hydrometeorological institute\u2019s severe storm nowcasting system. Atmos Res 83(2):450\u2013457. https:\/\/doi.org\/10.1016\/j.atmosres.2005.09.014, European Conference on Severe Storms 2004","DOI":"10.1016\/j.atmosres.2005.09.014"},{"key":"1438_CR26","unstructured":"Pavl\u00edk P, Rozinajov\u00e1 V, Ezzeddine AB (2022) Radar-based volumetric precipitation nowcasting: a 3d convolutional neural network with u-net architecture. In: 2nd Workshop on Complex Data Challenges in Earth Observation (CDCEO 2022), https:\/\/ceur-ws.org\/Vol-3207\/paper10.pdf"},{"key":"1438_CR27","doi-asserted-by":"publisher","unstructured":"Pfitzner B, Steckhan N, Arnrich B (2021) Federated learning in a medical context: a systematic literature review. ACM Trans Internet Technol 21(2). https:\/\/doi.org\/10.1145\/3412357. https:\/\/doi.org\/10.1145\/3412357","DOI":"10.1145\/3412357"},{"key":"1438_CR28","doi-asserted-by":"publisher","unstructured":"Rajczak J, Sch\u00e4r C (2017) Projections of future precipitation extremes over europe: a multimodel assessment of climate simulations. Journal of Geophysical Research: Atmospheres 122(20):10,773\u201310,800. https:\/\/doi.org\/10.1002\/2017JD027176","DOI":"10.1002\/2017JD027176"},{"key":"1438_CR29","doi-asserted-by":"publisher","first-page":"672","DOI":"10.1038\/s41586-021-03854-z","volume":"597","author":"S Ravuri","year":"2021","unstructured":"Ravuri S, Lenc K, Willson M et al (2021) Skilful precipitation nowcasting using deep generative models of radar. Nature 597:672\u2013677. https:\/\/doi.org\/10.1038\/s41586-021-03854-z","journal-title":"Nature"},{"issue":"1","key":"1438_CR30","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1038\/s41746-020-00323-1","volume":"3","author":"N Rieke","year":"2020","unstructured":"Rieke N, Hancox J, Li W et al (2020) The future of digital health with federated learning. NPJ digital medicine 3(1):119","journal-title":"NPJ digital medicine"},{"issue":"5660","key":"1438_CR31","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1038\/273287a0","volume":"273","author":"R Rinehart","year":"1978","unstructured":"Rinehart R, Garvey E (1978) Three-dimensional storm motion detection by conventional weather radar. Nature 273(5660):287\u2013289","journal-title":"Nature"},{"key":"1438_CR32","doi-asserted-by":"publisher","unstructured":"Sabah F, Chen Y, Yang Z et al (2024) Model optimization techniques in personalized federated learning: a survey. Expert Syst Appl 243:122874. https:\/\/doi.org\/10.1016\/j.eswa.2023.122874. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0957417423033766","DOI":"10.1016\/j.eswa.2023.122874"},{"key":"1438_CR33","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1016\/j.neucom.2022.11.011","volume":"518","author":"J S\u00e1inz-Pardo D\u00edaz","year":"2023","unstructured":"S\u00e1inz-Pardo D\u00edaz J, L\u00f3pez Garc\u00eda \u00c1 (2023) Study of the performance and scalability of federated learning for medical imaging with intermittent clients. Neurocomputing 518:142\u2013154","journal-title":"Neurocomputing"},{"key":"1438_CR34","unstructured":"Shi X, Chen Z, Wang H et\u00a0al (2015) Convolutional lstm network: a machine learning approach for precipitation nowcasting. Advances in neural information processing systems 28"},{"key":"1438_CR35","unstructured":"Shi X, Gao Z, Lausen L, et\u00a0al (2017) Deep learning for precipitation nowcasting: A benchmark and a new model. In: Guyon I, Luxburg UV, Bengio S et\u00a0al (eds) Advances in neural information processing systems, vol\u00a030. Curran Associates, Inc., https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/file\/a6db4ed04f1621a119799fd3d7545d3d-Paper.pdf"},{"key":"1438_CR36","doi-asserted-by":"publisher","unstructured":"S\u00e1inz-Pardo D\u00edaz J, Castrillo M, Garc\u00eda \u00c1lvaro L\u00f3pez (2023) Deep learning based soft-sensor for continuous chlorophyll estimation on decentralized data. Water Res 246:120726. https:\/\/doi.org\/10.1016\/j.watres.2023.120726, https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0043135423011661","DOI":"10.1016\/j.watres.2023.120726"},{"issue":"6","key":"1438_CR37","first-page":"356","volume":"46","author":"A Svoboda","year":"1998","unstructured":"Svoboda A, Pek\u00e1rov\u00e1 P (1998) The catastrophic flood of July 1998 in the mal\u00e1 svinka catchment - simulation of its course [in slovak]. Vodohospod\u00e1rsky \u010dasopis 46(6):356\u2013365","journal-title":"Vodohospod\u00e1rsky \u010dasopis"},{"key":"1438_CR38","doi-asserted-by":"publisher","unstructured":"Svoboda V, Hanel M, M\u00e1ca P et al (2016) Projected changes of rainfall event characteristics for the Czech Republic. Journal of Hydrology and Hydromechanics 64(4):415\u2013425. https:\/\/doi.org\/10.1515\/johh-2016-0036","DOI":"10.1515\/johh-2016-0036"},{"key":"1438_CR39","doi-asserted-by":"crossref","unstructured":"Tan AZ, Yu H, Cui L, et\u00a0al (2022) Towards personalized federated learning. IEEE Transactions on Neural Networks and Learning Systems","DOI":"10.1109\/TNNLS.2022.3160699"},{"issue":"37","key":"1438_CR40","doi-asserted-by":"publisher","first-page":"R81","DOI":"10.1088\/0305-4470\/35\/37\/201","volume":"35","author":"K Tanaka","year":"2002","unstructured":"Tanaka K (2002) Statistical-mechanical approach to image processing. J Phys A: Math Gen 35(37):R81. https:\/\/doi.org\/10.1088\/0305-4470\/35\/37\/201","journal-title":"J Phys A: Math Gen"},{"key":"1438_CR41","doi-asserted-by":"publisher","unstructured":"Tang J, Matyas C (2018) A nowcasting model for tropical cyclone precipitation regions based on the trec motion vector retrieval with a semi-lagrangian scheme for doppler weather radar. Atmosphere 9(5https:\/\/doi.org\/10.3390\/atmos9050200","DOI":"10.3390\/atmos9050200"},{"key":"1438_CR42","doi-asserted-by":"crossref","unstructured":"Wang Q, Zhang L, Bertinetto L, et\u00a0al (2019) Fast online object tracking and segmentation: a unifying approach. 1812.05050","DOI":"10.1109\/CVPR.2019.00142"},{"key":"1438_CR43","doi-asserted-by":"publisher","unstructured":"Woo Wc, Wong Wk (2017) Operational application of optical flow techniques to radar-based rainfall nowcasting. Atmosphere 8(3https:\/\/doi.org\/10.3390\/atmos8030048","DOI":"10.3390\/atmos8030048"},{"key":"1438_CR44","doi-asserted-by":"crossref","unstructured":"Yang W, Zhang Y, Ye K, et\u00a0al (2019) Ffd: a federated learning based method for credit card fraud detection. In: Big Data\u2013BigData 2019: 8th international congress, held as part of the services conference federation, SCF 2019, San Diego, CA, USA, June 25\u201330, 2019, Proceedings 8, Springer, pp 18\u201332","DOI":"10.1007\/978-3-030-23551-2_2"},{"key":"1438_CR45","unstructured":"Zhang W, Tanida J, Itoh K et\u00a0al (1988) Shift-invariant pattern recognition neural network and its optical architecture. In: Proceedings of annual conference of the Japan Society of Applied Physics, Montreal, CA"},{"key":"1438_CR46","doi-asserted-by":"publisher","first-page":"24462","DOI":"10.1109\/ACCESS.2021.3056919","volume":"9","author":"W Zhang","year":"2021","unstructured":"Zhang W, Wang X, Zhou P et al (2021) Client selection for federated learning with non-iid data in mobile edge computing. IEEE Access 9:24462\u201324474. https:\/\/doi.org\/10.1109\/ACCESS.2021.3056919","journal-title":"IEEE Access"},{"key":"1438_CR47","doi-asserted-by":"crossref","unstructured":"Zhang Z, Peng H (2019) Deeper and wider siamese networks for real-time visual tracking. 1901.01660","DOI":"10.1109\/CVPR.2019.00472"},{"key":"1438_CR48","doi-asserted-by":"crossref","unstructured":"Zhu Z, Wang Q, Li B et\u00a0al (2018) Distractor-aware siamese networks for visual object tracking. 1808.06048","DOI":"10.1007\/978-3-030-01240-3_7"}],"container-title":["Earth Science Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12145-024-01438-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s12145-024-01438-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12145-024-01438-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T09:09:38Z","timestamp":1732093778000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s12145-024-01438-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,2]]},"references-count":48,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2024,12]]}},"alternative-id":["1438"],"URL":"https:\/\/doi.org\/10.1007\/s12145-024-01438-9","relation":{},"ISSN":["1865-0473","1865-0481"],"issn-type":[{"type":"print","value":"1865-0473"},{"type":"electronic","value":"1865-0481"}],"subject":[],"published":{"date-parts":[[2024,9,2]]},"assertion":[{"value":"24 April 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 July 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 September 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing Interests"}}]}}