{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T14:04:24Z","timestamp":1772719464636,"version":"3.50.1"},"reference-count":34,"publisher":"MDPI AG","issue":"24","license":[{"start":{"date-parts":[[2019,12,6]],"date-time":"2019-12-06T00:00:00Z","timestamp":1575590400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100004318","name":"Microsoft","doi-asserted-by":"publisher","award":["Modeling crop-specific impact of heat waves by deep learning"],"award-info":[{"award-number":["Modeling crop-specific impact of heat waves by deep learning"]}],"id":[{"id":"10.13039\/100004318","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>The use of analog-similar weather patterns for weather forecasting and analysis is an established method in meteorology. The most challenging aspect of using this approach in the context of operational radar applications is to be able to perform a fast and accurate search for similar spatiotemporal precipitation patterns in a large archive of historical records. In this context, sequential pairwise search is too slow and computationally expensive. Here, we propose an architecture to significantly speed up spatiotemporal analog retrieval by combining nonlinear geometric dimensionality reduction (UMAP) with the fastest known Euclidean search algorithm for time series (MASS) to find radar analogs in constant time, independently of the desired temporal length to match and the number of extracted analogs. We show that UMAP, combined with a grid search protocol over relevant hyperparameters, can find analog sequences with lower mean square error (MSE) than principal component analysis (PCA). Moreover, we show that MASS is 20 times faster than brute force search on the UMAP embedding space. We test the architecture on real dataset and show that it enables precise and fast operational analog ensemble search through more than 2 years of radar archive in less than 3 seconds on a single workstation.<\/jats:p>","DOI":"10.3390\/rs11242922","type":"journal-article","created":{"date-parts":[[2019,12,6]],"date-time":"2019-12-06T10:41:44Z","timestamp":1575628904000},"page":"2922","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["MASS-UMAP: Fast and Accurate Analog Ensemble Search in Weather Radar Archives"],"prefix":"10.3390","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1264-0529","authenticated-orcid":false,"given":"Gabriele","family":"Franch","sequence":"first","affiliation":[{"name":"Predictive Models for Biomedicine and Environment, Fondazione Bruno Kessler, 38123 Trento, Italy"},{"name":"Department of Information Engineering and Computer Science (DISI), University of Trento, 38123 Trento, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2705-5728","authenticated-orcid":false,"given":"Giuseppe","family":"Jurman","sequence":"additional","affiliation":[{"name":"Predictive Models for Biomedicine and Environment, Fondazione Bruno Kessler, 38123 Trento, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8544-6540","authenticated-orcid":false,"given":"Luca","family":"Coviello","sequence":"additional","affiliation":[{"name":"Predictive Models for Biomedicine and Environment, Fondazione Bruno Kessler, 38123 Trento, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marta","family":"Pendesini","sequence":"additional","affiliation":[{"name":"Meteotrentino, 38122 Trento, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5384-3605","authenticated-orcid":false,"given":"Cesare","family":"Furlanello","sequence":"additional","affiliation":[{"name":"Predictive Models for Biomedicine and Environment, Fondazione Bruno Kessler, 38123 Trento, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2019,12,6]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"636","DOI":"10.1175\/1520-0469(1969)26<636:APARBN>2.0.CO;2","article-title":"Atmospheric predictability as revealed by naturally occurring analogues","volume":"26","author":"Lorenz","year":"1969","journal-title":"J. Atmos. Sci."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"3554","DOI":"10.1175\/2011MWR3653.1","article-title":"Kalman filter and analog schemes to postprocess numerical weather predictions","volume":"139","author":"Nipen","year":"2011","journal-title":"Mon. Weather Rev."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"2474","DOI":"10.1175\/1520-0442(1999)012<2474:TAMAAS>2.0.CO;2","article-title":"The analog method as a simple statistical downscaling technique: Comparison with more complicated methods","volume":"12","author":"Zorita","year":"1999","journal-title":"J. Clim."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"4093","DOI":"10.1175\/MWR-D-16-0441.1","article-title":"The analog data assimilation","volume":"145","author":"Lguensat","year":"2017","journal-title":"Mon. Weather Rev."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Tandeo, P., Ailliot, P., Ruiz, J., Hannart, A., Chapron, B., Cuzol, A., Monbet, V., Easton, R., and Fablet, R. (2015). Combining analog method and ensemble data assimilation: Application to the Lorenz-63 chaotic system. Machine Learning and Data Mining Approaches to Climate Science, Springer.","DOI":"10.1007\/978-3-319-17220-0_1"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"789","DOI":"10.1016\/j.renene.2019.06.132","article-title":"Using the analog ensemble method as a proxy measurement for wind power predictability","volume":"146","author":"Shahriari","year":"2020","journal-title":"Renew. Energy"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1083","DOI":"10.1175\/1520-0493(1982)110<1083:LRTPUA>2.0.CO;2","article-title":"Long-range temperature prediction using a simple analog approach","volume":"110","author":"Bergen","year":"1982","journal-title":"Mon. Weather Rev."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"3498","DOI":"10.1175\/MWR-D-12-00281.1","article-title":"Probabilistic Weather Prediction with an Analog Ensemble","volume":"141","author":"Eckel","year":"2013","journal-title":"Mon. Weather Rev."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"768","DOI":"10.1016\/j.renene.2014.11.061","article-title":"A novel application of an analog ensemble for short-term wind power forecasting","volume":"76","author":"Alessandrini","year":"2015","journal-title":"Renew. Energy"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1016\/j.apenergy.2015.08.011","article-title":"An analog ensemble for short-term probabilistic solar power forecast","volume":"157","author":"Alessandrini","year":"2015","journal-title":"Appl. Energy"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"314","DOI":"10.3402\/tellusa.v46i3.15481","article-title":"Searching for analogues, how long must we wait?","volume":"46","year":"1994","journal-title":"Tellus A"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"2106","DOI":"10.1002\/qj.878","article-title":"NORA\u2013Nowcasting of Orographic Rainfall by means of Analogues","volume":"137","author":"Panziera","year":"2011","journal-title":"Q. J. R. Meteorol. Soc."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1016\/j.atmosres.2017.05.003","article-title":"Probabilistic precipitation nowcasting based on an extrapolation of radar reflectivity and an ensemble approach","volume":"194","author":"Sokol","year":"2017","journal-title":"Atmos. Res."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"2890","DOI":"10.1175\/MWR-D-14-00342.1","article-title":"A Comparison of Two Techniques for Generating Nowcasting Ensembles. Part II: Analogs Selection and Comparison of Techniques","volume":"143","author":"Atencia","year":"2015","journal-title":"Mon. Weather Rev."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"409","DOI":"10.1175\/BAMS-D-11-00263.1","article-title":"Use of NWP for nowcasting convective precipitation: Recent progress and challenges","volume":"95","author":"Sun","year":"2014","journal-title":"Bull. Am. Meteorol. Soc."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1002\/met.1416","article-title":"Retrieval of analogue radar images for ensemble nowcasting of orographic rainfall","volume":"22","author":"Foresti","year":"2015","journal-title":"Meteorol. Appl."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"861","DOI":"10.21105\/joss.00861","article-title":"UMAP: Uniform Manifold Approximation and Projection","volume":"3","author":"McInnes","year":"2018","journal-title":"J. Open Source Softw."},{"key":"ref_18","unstructured":"Mueen, A., Zhu, Y., Yeh, M., Kamgar, K., Viswanathan, K., Gupta, C., and Keogh, E. (2019, November 18). The Fastest Similarity Search Algorithm for Time Series Subsequences under Euclidean Distance. Available online: http:\/\/www.cs.unm.edu\/~mueen\/FastestSimilaritySearch.html."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Jolliffe, I. (2011). Principal Component Analysis, Springer.","DOI":"10.1007\/978-3-642-04898-2_455"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Becht, E., McInnes, L., Healy, J., Dutertre, C.A., Kwok, I.W.H., Ng, L.G., Ginhoux, F., and Newell, E.W. (Nature Biotechnology, 2018). Dimensionality reduction for visualizing single-cell data using UMAP, Nature Biotechnology.","DOI":"10.1038\/nbt.4314"},{"key":"ref_21","unstructured":"McInnes, L. (2019, November 18). How UMAP Works. Available online: https:\/\/umap-learn.readthedocs.io\/en\/latest\/how_umap_works.html."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Yeh, C.C.M., Zhu, Y., Ulanova, L., Begum, N., Ding, Y., Dau, A., Silva, D., Mueen, A., and Keogh, E. (2016, January 12\u201315). Matrix Profile I: All Pairs Similarity Joins for Time Series: A Unifying View That Includes Motifs, Discords and Shapelets. Proceedings of the 2016 IEEE 16th International Conference on Data Mining (ICDM), Barcelona, Spain.","DOI":"10.1109\/ICDM.2016.0179"},{"key":"ref_23","unstructured":"Yeh, C.C.M. (2018). Towards a Near Universal Time Series Data Mining Tool: Introducing the Matrix Profile. arXiv."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Dau, H.A., and Keogh, E. (2017, January 13\u201317). Matrix Profile V: A Generic Technique to Incorporate Domain Knowledge into Motif Discovery. Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD \u201917, Halifax, NS, Canada.","DOI":"10.1145\/3097983.3097993"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Gharghabi, S., Ding, Y., Yeh, C.C.M., Kamgar, K., Ulanova, L., and Keogh, E. (2017, January 18\u201321). Matrix profile VIII: Domain agnostic online semantic segmentation at superhuman performance levels. Proceedings of the 2017 IEEE International Conference on Data Mining (ICDM), New Orleans, LA, USA.","DOI":"10.1109\/ICDM.2017.21"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Yeh, C.C.M., Zimmerman, Z., Kamgar, K., and Keogh, E. (2018, January 17\u201320). Matrix profile XI: SCRIMP++: Time series motif discovery at interactive speeds. Proceedings of the 2018 IEEE International Conference on Data Mining (ICDM), Singapore.","DOI":"10.1109\/ICDM.2018.00099"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1016\/j.solener.2019.03.068","article-title":"An ultra-fast way of searching weather analogs for renewable energy forecasting","volume":"185","author":"Yang","year":"2019","journal-title":"Sol. Energy"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1332","DOI":"10.1175\/JHM-D-11-096.1","article-title":"Data Transformation and Uncertainty in Geostatistical Combination of Radar and Rain Gauges","volume":"13","author":"Erdin","year":"2012","journal-title":"J. Hydrometeorol."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"258","DOI":"10.1093\/bioinformatics\/btm550","article-title":"Algebraic stability indicators for ranked lists in molecular profiling","volume":"24","author":"Jurman","year":"2008","journal-title":"Bioinformatics"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1093\/comjnl\/9.1.60","article-title":"Computer programs for hierarchical polythetic classification (\u201csimilarity analysis\u201d)","volume":"9","author":"Lance","year":"1966","journal-title":"Comput. J."},{"key":"ref_31","unstructured":"Jurman, G., Riccadonna, S., Visintainer, R., and Furlanello, C. (2009, January 11). Canberra distance on ranked lists. Proceedings of the Advances in Ranking NIPS 2009 Workshop, Vancouver, BC, Canada."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1111\/j.1469-8137.1912.tb05611.x","article-title":"The distribution of the flora in the alpine zone. 1","volume":"11","author":"Jaccard","year":"1912","journal-title":"New Phytol."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"2385","DOI":"10.1109\/TIP.2009.2025923","article-title":"Complex wavelet structural similarity: A new image similarity index","volume":"18","author":"Sampat","year":"2009","journal-title":"IEEE Trans. Image Process."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Von Hardenberg, J., Ferraris, L., and Provenzale, A. (2003). The shape of convective rain cells. Geophys. Res. Lett., 30.","DOI":"10.1029\/2003GL018539"}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/11\/24\/2922\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T13:40:48Z","timestamp":1760190048000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/11\/24\/2922"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12,6]]},"references-count":34,"journal-issue":{"issue":"24","published-online":{"date-parts":[[2019,12]]}},"alternative-id":["rs11242922"],"URL":"https:\/\/doi.org\/10.3390\/rs11242922","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,12,6]]}}}