Вход на сайт

Просмотр новости

Найдите то, что Вас интересует

From manual classification to transformer-based language models: assessing the quality and consistency of historical convective event records

Дата публикации: 07-10-2026 12:00:00






Before measuring instruments, thunderstorms and hail were recorded only in written reports. We analysed around 7000 reports from 1000 to 1817 and, using a rule-based workflow, linguistically decoded the intensity of the thunderstorm and hail events described. The annual cycle derived from this corresponds well with modern observations. With these data, language models can be trained to reliably classify such events and make large collections of text accessible for climate research.



Основное содержимое страницы с новостью.

Bayerische Akademie der Wissenschaften: Der Baierischen Akademie der Wissenschaften in München meteorologische Ephemeriden, vol. 8, Bayerische Akademie der Wissenschaften, München, https://nbn-resolving.org/urn:nbn:de:bvb:12-bsb10332543-1, 1789. a

Beck, H. E., McVicar, T. R., Vergopolan, N., Berg, A., Lutsko, N. J., Dufour, A., Zeng, Z., Jiang, X., van Dijk, A. I. J. M., and Miralles, D. G.: High-resolution (1 km) Köppen-Geiger maps for 1901–2099 based on constrained CMIP6 projections, Scientific Data, 10, 724, https://doi.org/10.1038/s41597-023-02549-6, 2023. a, b

Brázdil, R., Dobrovolný, P., Luterbacher, J., Moberg, A., Pfister, C., Wheeler, D., and Zorita, E.: European climate of the past 500 years: new challenges for historical climatology, Climatic Change, 101, 7–40, https://doi.org/10.1007/s10584-009-9783-z, 2010. a

Brázdil, R., Chromá, K., Valášek, H., Dolák, L., and Řezníčková, L.: Damaging hailstorms in South Moravia, Czech Republic, in the seventeenth to twentieth centuries as derived from taxation records, Theor. Appl. Climatol., 123, 185–198, https://doi.org/10.1007/s00704-014-1338-1, 2016a. a, b, c

Brázdil, R., Chromá, K., Valášek, H., Dolák, L., Řezníčková, L., Zahradníček, P., and Dobrovolný, P.: A long-term chronology of summer half-year hailstorms for South Moravia, Czech Republic, Clim. Res., 71, 91–109, https://doi.org/10.3354/cr01432, 2016b. a, b, c

Brönnimann, S., Martius, O., Rohr, C., Bresch, D. N., and Lin, K. E.: Historical weather data for climate risk assessment, Ann. NY Acad. Sci., 1436, 121–137, https://doi.org/10.1111/nyas.13966, 2019. a, b

Burgdorf, A.-M.: A global inventory of quantitative documentary evidence related to climate since the 15th century, Clim. Past, 18, 1407–1428, https://doi.org/10.5194/cp-18-1407-2022, 2022. a

Camuffo, D., Cocheo, C., and Enzi, S.: Seasonality of instability phenomena (hailstorms and thunderstorms) in Padova, northern Italy, from archive and instrumental sources since AD 1300, The Holocene, 10, 635–642, https://doi.org/10.1191/095968300666845195, 2000. a, b, c, d, e, f

Cutter, S. L.: The Changing Nature of Hazard and Disaster Risk in the Anthropocene, Ann. Am. Assoc. Geogr., 111, 819–827, https://doi.org/10.1080/24694452.2020.1744423, 2021. a

Deutscher Wetterdienst: Beobachterhandbuch für Wettermeldestellen des synoptisch-klimatologischen Mess- und Beobachtungsnetzes, Vorschriften und Betriebsunterlagen 3 (VuB 3 BHB), Deutscher Wetterdienst, Offenbach am Main, 2014. a

Deutscher Wetterdienst (DWD): Offizielle Webseite des Deutschen Wetterdienstes, https://www.dwd.de/ (last access: 24 September 2026), 2025. a

Devlin, J., Chang, M.-W., Lee, K., and Toutanova, K.: BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding, in: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), 4171–4186, Association for Computational Linguistics, Minneapolis, Minnesota, https://doi.org/10.18653/v1/N19-1423, 2019. a

Diodato, N., Ljungqvist, F. C., and Bellocchi, G.: A millennium-long reconstruction of damaging hydrological events across Italy, Sci. Rep., 9, 9963, https://doi.org/10.1038/s41598-019-46207-7, 2019. a

Ehrmanntraut, A.: Historical German Text Normalization Using Type- and Token-Based Language Modeling, arXiv [preprint], https://doi.org/10.48550/arXiv.2409.02841, 2025. a

Eichler, E. and Walther, H. (Eds.): Historisches Ortsnamenbuch von Sachsen, no. 21 in Quellen und Forschungen zur sächsischen Geschichte, Akademie, Berlin, ISBN 978-3-05-003728-8, 2001. a

Erfurt, M., Skiadaresis, G., Tijdeman, E., Blauhut, V., Bauhus, J., Glaser, R., Schwarz, J., Tegel, W., and Stahl, K.: A multidisciplinary drought catalogue for southwestern Germany dating back to 1801, Nat. Hazards Earth Syst. Sci., 20, 2979–2995, https://doi.org/10.5194/nhess-20-2979-2020, 2020. a

Ernst, P.: Deutsche Sprachgeschichte: eine Einführung in die diachrone Sprachwissenschaft des Deutschen, no. 2583 in utb Sprachwissenschaft, Facultas, Wien, 3rd edn., ISBN 978-3-8252-5532-9, 2021. a, b

European Severe Storms Laboratory (ESSL): European Severe Storms Laboratory: official website, https://www.essl.org/cms/ (last access: 24 September 2026), 2025. a

Giordani, A., Kunz, M., Bedka, K. M., Punge, H. J., Paccagnella, T., Pavan, V., Cerenzia, I. M. L., and Di Sabatino, S.: Characterizing hail-prone environments using convection-permitting reanalysis and overshooting top detections over south-central Europe, Nat. Hazards Earth Syst. Sci., 24, 2331–2357, https://doi.org/10.5194/nhess-24-2331-2024, 2024. a

Glaser, R.: Klimageschichte Mitteleuropas: 1200 Jahre Wetter, Klima, Katastrophen, Primus, Darmstadt, 3rd edn., ISBN 3-86312-350-6, 2013. a, b, c, d

Glaser, R.: HISKLID: Historische Klimadatenbank, https://freidok.uni-freiburg.de/proj/3720 (last access: 24 September 2026), 2014. a

Grotefend, H.: Taschenbuch der Zeitrechnung des deutschen Mittelalters und der Neuzeit, Hahn, Hannover, 14th edn., ISBN 978-3-7752-5177-8, 2007. a

Grzega, J.: Climatic Conditions and Lexis: Some Diachronic Notes on Weather‐Related Words in English and Other European Languages, T. Philol. Soc., 120, 320–331, https://doi.org/10.1111/1467-968X.12243, 2022. a

Gudd, M.: Gewitter und Gewitterschäden im südlichen hessischen Berg- und Beckenland und im Rhein-Main-Tiefland 1881 bis 1980, PhD thesis, Johannes Gutenberg-Universität Mainz, https://doi.org/10.25358/OPENSCIENCE-3426, 2004. a

Hawkins, E., Brohan, P., Burgess, S. N., Burt, S., Compo, G. P., Gray, S. L., Haigh, I. D., Hersbach, H., Kuijjer, K., Martínez-Alvarado, O., McColl, C., Schurer, A. P., Slivinski, L., and Williams, J.: Rescuing historical weather observations improves quantification of severe windstorm risks, Nat. Hazards Earth Syst. Sci., 23, 1465–1482, https://doi.org/10.5194/nhess-23-1465-2023, 2023. a

Huang, S.-Y., Wu, S.-Y., Chen, Y.-J., Tsai, R. T.-H., and Fan, I.-C.: Climate event classification based on historical meteorological records and its presentation on a Spatio-Temporal research platform, Digit. Scholarsh. Hum., 37, 1022–1032, https://doi.org/10.1093/llc/fqab099, 2022. a

Hulton, F. and Schultz, D. M.: Climatology of large hail in Europe: characteristics of the European Severe Weather Database, Nat. Hazards Earth Syst. Sci., 24, 1079–1098, https://doi.org/10.5194/nhess-24-1079-2024, 2024. a

Kahraman, A., Kendon, E. J., and Fowler, H. J.: Climatology of severe hail potential in Europe based on a convection-permitting simulation, Clim. Dynam., 62, 6625–6642, https://doi.org/10.1007/s00382-024-07227-w, 2024. a

Lamont, J. v.: Gewitterbeobachtungen von Ansbach, Burglengenfeld, Dillingen, Gunzenhausen, Hof, Hohenpeißenberg, Neustadt a.d.A., Würzburg von 1842 u. 1843, Annalen für Meteorologie, Erdmagnetismus und verwandte Gegenstände, 1844, 147–167, https://www.digitale-sammlungen.de/en/view/bsb10133287 (last access: 24 September 2026), 1844. a

Lenke, W.: Klimadaten von 1621–1650 nach Beobachtungen des Landgrafen Hermann IV. von Hessen (Uranophilus Cyriandrus), Tech. Rep. 63, Deutscher Wetterdienst, Offenbach am Main, https://www.dwd.de/DE/leistungen/pbfb_verlag_berichte/pdf_einzelbaende/63_pdf.pdf?__blob=publicationFile&v=3 (last access: 24 September 2026), 1960. a, b, c, d, e

Luterbacher, J., Allan, R., Wilkinson, C., Hawkins, E., Teleti, P., Lorrey, A., Brönnimann, S., Hechler, P., Velikou, K., and Xoplaki, E.: The Importance and Scientific Value of Long Weather and Climate Records; Examples of Historical Marine Data Efforts across the Globe, Climate, 12, 39, https://doi.org/10.3390/cli12030039, 2024. a

Martius, O., Hering, A., Kunz, M., Manzato, A., Mohr, S., Nisi, L., and Trefalt, S.: Challenges and Recent Advances in Hail Research, B. Am. Meteorol. Soc., 99, ES51–ES54, https://doi.org/10.1175/BAMS-D-17-0207.1, 2018. a

Porto Tapiquén, C. E.: Europe [shapefile], Orogénesis Soluciones Geográficas, Porlamar, Venezuela, based on shapes from Environmental Systems Research Institute (ESRI), https://github.com/efrainmaps/shapefiles-es (last access: 30 September 2026), 2015. a

Preußisches Meteorologisches Institut: Ergebnisse der Gewitter-Beobachtungen 1892/94, Behrend, Berlin, https://dwdbib.dwd.de/retrosammlung/periodical/titleinfo/586912 (last access: 30 September 2026), 1897. a

Punge, H. and Kunz, M.: Hail observations and hailstorm characteristics in Europe: A review, Atmos. Res., 176–177, 159–184, https://doi.org/10.1016/j.atmosres.2016.02.012, 2016. a

Reitzenstein, W.-A. F. v.: Lexikon fränkischer Ortsnamen. Herkunft und Bedeutung. Oberfranken, Mittelfranken, Unterfranken, C.H. Beck, München, ISBN 978-3-406-59131-0, 2009. a

Reitzenstein, W.-A. F. v.: Lexikon schwäbischer Ortsnamen. Herkunft und Bedeutung. Bayerisch-Schwaben, C.H. Beck, München, ISBN 978-3-406-65208-0, 2013. a

Sakaji, H. and Kaneda, N.: Indexing and Visualization of Climate Change Narratives Using BERT and Causal Extraction, in: 2023 IEEE International Conference on Big Data (BigData), 5674–5683, https://doi.org/10.1109/BigData59044.2023.10386320, 2023. a

Schätz, F.: Voraussetzungen und Grenzen der Auswertung klimarelevanter Informationen historischer Textquellen mit Hilfe von Automatisierungsprozessen, Dissertation, Albert-Ludwigs-Universität Freiburg, Freiburg im Breisgau, https://doi.org/10.6094/UNIFR/244079, 2023. a, b, c, d, e

Schätz, F.: HailBERT-de-v1, Hugging Face [code], https://doi.org/10.57967/hf/6989, 2025a. a

Schätz, F.: ThunderstormBERT-de-v1, Hugging Face [code], https://doi.org/10.57967/hf/6982, 2025b. a

Schätz, F. and Glaser, R.: Historical Climate Observations of Thunderstorms and Hail in Central Europe (1000–1900), FreiData [data set], https://doi.org/10.60493/834bd-mww13, 2025.  a, b

Stahl, K., Kohn, I., Blauhut, V., Urquijo, J., De Stefano, L., Acácio, V., Dias, S., Stagge, J. H., Tallaksen, L. M., Kampragou, E., Van Loon, A. F., Barker, L. J., Melsen, L. A., Bifulco, C., Musolino, D., de Carli, A., Massarutto, A., Assimacopoulos, D., and Van Lanen, H. A. J.: Impacts of European drought events: insights from an international database of text-based reports, Nat. Hazards Earth Syst. Sci., 16, 801–819, https://doi.org/10.5194/nhess-16-801-2016, 2016. a

Taszarek, M., Allen, J., Púčik, T., Groenemeijer, P., Czernecki, B., Kolendowicz, L., Lagouvardos, K., Kotroni, V., and Schulz, W.: A Climatology of Thunderstorms across Europe from a Synthesis of Multiple Data Sources, J. Climate, 32, 1813–1837, https://doi.org/10.1175/JCLI-D-18-0372.1, 2019. a

Tornado and Storm Research Organisation (TORRO): The TORRO Hail Intensity Scale (H-Scale), https://www.torro.org.uk/research/hail/hscale (last access: 24 September 2026), 2025. a, b

Webersinke, N., Kraus, M., Bingler, J. A., and Leippold, M.: ClimateBert: A Pretrained Language Model for Climate-Related Text, arXiv [preprint], https://doi.org/10.48550/arXiv.2110.12010, 2022. a

Wilks, D. S.: Statistical methods in the atmospheric sciences: an introduction, Elsevier, Amsterdam, 4th edn., ISBN 978-0-12-816527-0, 2019. a, b, c

Zhou, B., Zou, L., Mostafavi, A., Lin, B., Yang, M., Gharaibeh, N., Cai, H., Abedin, J., and Mandal, D.: VictimFinder: Harvesting rescue requests in disaster response from social media with BERT, Computers, Environment and Urban Systems, 95, 101824, https://doi.org/10.1016/j.compenvurbsys.2022.101824, 2022. a

Схожие новости

#Наименование новостиТональностьИнформативностьДата публикации
1Meteosat Third Generation Lightning Imager detection performances012.1120-10-2026
2Invited perspective: Uncertainties in natural systems may be uncomfortable, but ignoring them would be absurd09.2108-10-2026
3Propagating meteorological uncertainty in physically based mountain snow modeling09.6315-10-2026
4 Probabilistic Rainfall Downscaling: Joint Generalized Neural Models with Censored Spatial Gaussian Copula 05.9817-08-2026
5GlaUnTI: a hybrid physics–machine learning model enables transferable glacier surface mass balance estimation0821-10-2026
6Efficient ensemble estimation using an MCMC sampler: a reconstruction of the Mediterranean low-frequency variability combining observed and simulated sea level09.0119-10-2026
7Data-driven seasonal climate predictions via variational inference and transformers07.3331-12-2025
8Subseasonal Forecasting and MJO Teleconnections in Machine Learning Weather Prediction Models06.7921-08-2026
9How meteorologists use atmospheric soundings to determine storm instability010.9920-05-2026

Классификация: Наука. Схожих патентов: 0. Схожих новостей: 9. Тональность: 0. Информативность: 11.32. Источник: www.egu.eu.