Articles | Volume 18, issue 3
https://doi.org/10.5194/essd-18-1783-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/essd-18-1783-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Data description article
| 
10 Mar 2026
Data description article |
| 10 Mar 2026
| 10 Mar 2026
Reconstructing nineteenth-century Danube river water levels with transformer-based computer vision
Malte Rehbein
CORRESPONDING AUTHOR
Chair of Computational Humanities, University of Passau, Passau, Germany
Max Planck Institute of Geoanthropology, Jena, Germany
Cited articles
Aghajani, M., Ahmadi, H., Mirzaei, N., and Batllo, J.: Digitizing Analog Seismograms of Iranian Seismic Stations – Preserving Records for Strong Earthquakes in Iran 1960–1990, J. Seismol., 27, 693–706, https://doi.org/10.1007/s10950-023-10158-4, 2023. a
Antico, A., Aguiar, R. O., and Amsler, M. L.: Hydrometric Data Rescue in the Paraná River Basin, Water Resour. Res., 54, 1368–1381, https://doi.org/10.1002/2017WR020897, 2018. a
Antico, A., Mendizabal, S., Ferreira, L. J., Aguiar, R. O., and Amsler, M. L.: Addendum to “Hydrometric Data Rescue in the Paraná River Basin” by Andrés Antico, Ricardo O. Aguiar, and Mario L. Amsler, Water Resour. Res., 56, e2019WR026654, https://doi.org/10.1029/2019WR026654, 2020. a
Becker, A. and Grünewald, U.: Flood Risk in Central Europe, Science, 300, 1099–1099, https://doi.org/10.1126/science.1083624, 2003. a, b
Berking, J., Oleson, J. P., Sürmelihindi, G., Nenci, E., Maganzani, L., Ronin, M., Schrakamp, I., Gerrard, C., Gutiérrez, A., Trümper, M., Bouffier, S., Dumas, V., Lenhardt, P., Paillet, J.-L., and Schomberg, A.: Water Management in Ancient Civilizations, Humboldt-Universität zu Berlin, https://doi.org/10.18452/19758, 2019. a
Biswas, A. K.: History of Hydrology, North-Holland Publ., Amsterdam, ISBN 978-0-444-10025-2, 1970. a
Bogiatzis, P. and Ishii, M.: DigitSeis: A New Digitization Software for Analog Seismograms, Seismol. Res. Lett., 87, 726–736, https://doi.org/10.1785/0220150246, 2016. a
Bradshaw, E., Rickards, L., and Aarup, T.: Sea Level Data Archaeology and the Global Sea Level Observing System (GLOSS), GeoResJ, 6, 9–16, https://doi.org/10.1016/j.grj.2015.02.005, 2015. a
Bradshaw, E., Woodworth, P., Hibbert, A., Bradley, L., Pugh, D., Fane, C., and Bingley, R.: A Century of Sea Level Measurements at Newlyn, Southwest England, Mar. Geod., 39, 115–140, https://doi.org/10.1080/01490419.2015.1121175, 2016. a
Brázdil, R., Kundzewicz, Z. W., and Benito, G.: Historical Hydrology for Studying Flood Risk in Europe, Hydrolog. Sci. J., 51, 739–764, https://doi.org/10.1623/hysj.51.5.739, 2006. a
Brohan, P., Allan, R., Freeman, J. E., Waple, A. M., Wheeler, D., Wilkinson, C., and Woodruff, S.: Marine Observations of Old Weather, B. Am. Meteorol. Soc., 90, 219–230, https://doi.org/10.1175/2008BAMS2522.1, 2009. a
Brönnimann, S., Brugnara, Y., Allan, R. J., Brunet, M., Compo, G. P., Crouthamel, R. I., Jones, P. D., Jourdain, S., Luterbacher, J., Siegmund, P., Valente, M. A., and Wilkinson, C. W.: A Roadmap to Climate Data Rescue Services, Geosci. Data J., 5, 28–39, https://doi.org/10.1002/gdj3.56, 2018. a
Burnhill, T. and Adamson, P.: Floods and the Mekong River System (Part 3), Catch and Culture, Fisheries Research and Development in the Mekong Region, 14, 25–30, 2008. a
Burr, G., Podolsky, L., and Lapointe, Y. A.: Redrawing historical weather data and participatory archives for the future, Comma, 297–315, https://doi.org/10.3828/coma.2021.28, 2021. a
Caldwell, P. C., Merrifield, M. A., and Thompson, P. R.: Sea Level Measured by Tide Gauges from Global Oceans as Part of the Joint Archive for Sea Level (JASL) since 1846, NOAA [data set], https://doi.org/10.7289/V5V40S7W, 2001. a
Capozzi, V., Cotroneo, Y., Castagno, P., De Vivo, C., and Budillon, G.: Rescue and quality control of sub-daily meteorological data collected at Montevergine Observatory (Southern Apennines), 1884–1963, Earth Syst. Sci. Data, 12, 1467–1487, https://doi.org/10.5194/essd-12-1467-2020, 2020. a
Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., and Zagoruyko, S.: End-to-End Object Detection with Transformers, in: Computer Vision – ECCV 2020, edited by: Vedaldi, A., Bischof, H., Brox, T., and Frahm, J.-M., vol. 12346, Springer International Publishing, Cham, 213–229, ISBN 978-3-030-58451-1, https://doi.org/10.1007/978-3-030-58452-8_13, 2020. a, b
Castelvecchi, D.: “Revolutionary” AI Tools Rescue Old Weather Data to Improve Climate Models, Nature, https://doi.org/10.1038/d41586-025-02798-y, 2025. a
Chen, K., Wang, J., Pang, J., Cao, Y., Xiong, Y., Li, X., Sun, S., Feng, W., Liu, Z., Xu, J., Zhang, Z., Cheng, D., Zhu, C., Cheng, T., Zhao, Q., Li, B., Lu, X., Zhu, R., Wu, Y., Dai, J., Wang, J., Shi, J., Ouyang, W., Loy, C. C., and Lin, D.: MMDetection: Open MMLab Detection Toolbox and Benchmark, arXiv [preprint], https://doi.org/10.48550/arXiv.1906.07155, 2019. a
Cheng, Z.-Q., Dai, Q., Li, S., Sun, J., Mitamura, T., and Hauptmann, A. G.: ChartReader: A Unified Framework for Chart Derendering and Comprehension without Heuristic Rules, arXiv [preprint], https://doi.org/10.48550/arXiv.2304.02173, 2023. a
Corona-Fernandez, R. D. and Santoyo, M. A.: TIITBA – a Graphical Interface for Historical Seismograms, Vectorization, Analysis and, Correction, Zenodo [code], https://doi.org/10.5281/zenodo.6272822, 2023. a
Dangendorf, S., Wahl, T., Mudersbach, C., and Jensen, J.: The Seasonal Mean Sea Level Cycle in the Southeastern North Sea, J. Coastal Res., 165, 1915–1920, https://doi.org/10.2112/SI65-324.1, 2013. a
Dangendorf, S., Calafat, F. M., Arns, A., Wahl, T., Haigh, I. D., and Jensen, J.: Mean Sea Level Variability in the North Sea: Processes and Implications, J. Geophys. Res.-Oceans, 119, 2014JC009901, https://doi.org/10.1002/2014JC009901, 2014. a
Das, S., Ma, K., Shu, Z., Samaras, D., and Shilkrot, R.: DewarpNet: Single-Image Document Unwarping With Stacked 3D and 2D Regression Networks, in: 2019 IEEE/CVF International Conference on Computer Vision (ICCV), IEEE, Seoul, Korea (South), 131–140, ISBN 978-1-7281-4803-8, https://doi.org/10.1109/ICCV.2019.00022, 2019. a
Davila, K., Kota, B. U., Setlur, S., Govindaraju, V., Tensmeyer, C., Shekhar, S., and Chaudhry, R.: ICDAR 2019 Competition on Harvesting Raw Tables from Infographics (CHART-Infographics), in: 2019 International Conference on Document Analysis and Recognition (ICDAR), IEEE, Sydney, Australia, 1594–1599, ISBN 978-1-7281-3014-9, https://doi.org/10.1109/ICDAR.2019.00203, 2019. a
De Smeth, K., Comer, J., and Murphy, C.: Hydrometric Data Rescue and Extension of River Flow Records: Method Development and Application to Catchments Modified by Arterial Drainage, Geosci. Data J., 11, 176–196, https://doi.org/10.1002/gdj3.206, 2024. a
Donig, S. and Rehbein, M.: Für Eine “Gemeinsame Digitale Zukunft”. Eine Kritische Verortung Der Digital History, Geschichte in Wissenschaft und Unterricht, 72, 527–545, 2022. a
Drevon, D., Fursa, S. R., and Malcolm, A. L.: Intercoder Reliability and Validity of WebPlotDigitizer in Extracting Graphed Data, Behav. Modif., 41, 323–339, https://doi.org/10.1177/0145445516673998, 2017. a
Faber, E.: Studien Über Die Verbesserung Der Schiffbarkeit Der Donau von Kelheim Bis Nach Ulm, A. Troschel, Berlin-Grunewald, 1903. a
Featherstone, W. E., Penna, N. T., Filmer, M. S., and Williams, S. D. P.: Nonlinear Subsidence at Fremantle, a Long-recording Tide Gauge in the Southern Hemisphere, J. Geophys. Res.-Oceans, 120, 7004–7014, https://doi.org/10.1002/2015JC011295, 2015. a
Federal Agencies Digital Guidelines Initiative: Technical Guidelines for Digitizing Cultural Heritage Materials, 3rd edn., https://www.digitizationguidelines.gov/guidelines/FADGITechnicalGuidelinesforDigitizingCulturalHeritageMaterials_ThirdEdition_05092023.pdf (last access: 5 March 2025), 2023. a
Fields, C. and Kennington, C.: Vision Language Transformers: A Survey, arXiv [preprint], https://doi.org/10.48550/arXiv.2307.03254, 2023. a
Gallant, A. J. E. and Gergis, J.: An Experimental Streamflow Reconstruction for the River Murray, Australia, 1783–1988, Water Resour. Res., 47, 2010WR009832, https://doi.org/10.1029/2010WR009832, 2011. a
Hannah, J. and Bell, R. G.: Regional Sea Level Trends in New Zealand, J. Geophys. Res.-Oceans, 117, 2011JC007591, https://doi.org/10.1029/2011JC007591, 2012. a
Hawkins, E.: Data Rescue with AI: Google Gemini Has Changed the Game, Substack, https://climatelabbook.substack.com/p/data-rescue-with-ai (last access: 5 March 2025), 2025. a
Hawkins, E., Burt, S., Brohan, P., Lockwood, M., Richardson, H., Roy, M., and Thomas, S.: Hourly Weather Observations from the Scottish Highlands (1883–1904) Rescued by Volunteer Citizen Scientists, Geosci. Data J., 6, 160–173, https://doi.org/10.1002/gdj3.79, 2019. 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, 2023a. a
Hawkins, E., Burt, S., McCarthy, M., Murphy, C., Ross, C., Baldock, M., Brazier, J., Hersee, G., Huntley, J., Meats, R., O'Grady, J., Scrimgeour, I., and Silk, T.: Millions of Historical Monthly Rainfall Observations Taken in the UK and Ireland Rescued by Citizen Scientists, Geosci. Data J., 10, 246–261, https://doi.org/10.1002/gdj3.157, 2023b. a
Helaire, L. T., Talke, S. A., Jay, D. A., and Mahedy, D.: Historical Changes in Lower Columbia River and Estuary Floods: A Numerical Study, J. Geophys. Res.-Oceans, 124, 7926–7946, https://doi.org/10.1029/2019JC015055, 2019. a
Hohensinner, S., Lager, B., Sonnlechner, C., Haidvogl, G., Gierlinger, S., Schmid, M., Krausmann, F., and Winiwarter, V.: Changes in Water and Land: The Reconstructed Viennese Riverscape from 1500 to the Present, Water History, 5, 145–172, https://doi.org/10.1007/s12685-013-0074-2, 2013a. a
Hohensinner, S., Sonnlechner, C., Schmid, M., and Winiwarter, V.: Two Steps Back, One Step Forward: Reconstructing the Dynamic Danube Riverscape under Human Influence in Vienna, Water History, 5, 121–143, https://doi.org/10.1007/s12685-013-0076-0, 2013b. a
Holgate, S., Matthews, A., Woodworth, P., Richards, L., Tamisiea, M., Bradshaw, E., Foden, P., Gordon, K., Jevrejeva, S., and Pugh, J.: New Data Systems and Products at the Permanent Service for Mean Sea Level, J. Coastal Res., 29, 493, https://doi.org/10.2112/JCOASTRES-D-12-00175.1, 2012. a
Huffman, G. J., Adler, R. F., Behrangi, A., Bolvin, D. T., Nelkin, E. J., Gu, G., and Ehsani, M. R.: The New Version 3.2 Global Precipitation Climatology Project (GPCP) Monthly and Daily Precipitation Products, J. Climate, 36, 7635–7655, https://doi.org/10.1175/JCLI-D-23-0123.1, 2023. a
Hunter, J., Coleman, R., and Pugh, D.: The Sea Level at Port Arthur, Tasmania, from 1841 to the Present, Geophys. Res. Lett., 30, 2002GL016813, https://doi.org/10.1029/2002GL016813, 2003. a
Inayatillah, A., Haigh, I. D., Brand, J. H., Francis, K., Mortley, A., Durrant, M., Fantuzzi, L., Palmer, E., Miller, C., and Hogarth, P.: Digitising Historical Sea Level Records in the Thames Estuary, UK, Scientific Data, 9, 167, https://doi.org/10.1038/s41597-022-01223-7, 2022. a, b, c
Jaklič, A., Šajn, L., Derganc, G., and Peer, P.: Automatic Digitization of Pluviograph Strip Charts, Meteorol. Appl., 23, 57–64, https://doi.org/10.1002/met.1522, 2016. a
Jung, D., Kim, W., Song, H., Hwang, J.-I., Lee, B., Kim, B., and Seo, J.: ChartSense: Interactive Data Extraction from Chart Images, in: Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems, ACM, Denver Colorado USA, 6706–6717, ISBN 978-1-4503-4655-9, https://doi.org/10.1145/3025453.3025957, 2017. a
Kass, M., Witkin, A., and Terzopoulos, D.: Snakes: Active Contour Models, Int. J. Comput. Vision, 1, 321–331, https://doi.org/10.1007/BF00133570, 1988. a
Kelln, J., Dangendorf, S., Jensen, J., Patzke, J., and Fröhle, P.: Monthly Sea Level from Tide Gauge Stations at the German Baltic Coastline (AMSeL_Baltic Sea), PANGAEA [data set], https://doi.org/10.1594/PANGAEA.904737, 2019. a, b
Kendon, M., Doherty, A., Hollis, D., Carlisle, E., Packman, S., McCarthy, M., Jevrejeva, S., Matthews, A., Williams, J., Garforth, J., and Sparks, T.: State of the UK Climate 2023, Int. J. Climatol., 44, 1–117, https://doi.org/10.1002/joc.8553, 2024. a
Khan, M. J. U., Van Den Beld, I., Wöppelmann, G., Testut, L., Latapy, A., and Pouvreau, N.: Extension of a high temporal resolution sea level time series at Socoa (Saint-Jean-de-Luz, France) back to 1875, Earth Syst. Sci. Data, 15, 5739–5753, https://doi.org/10.5194/essd-15-5739-2023, 2023. a, b
Kim, G., Hong, T., Yim, M., Nam, J., Park, J., Yim, J., Hwang, W., Yun, S., Han, D., and Park, S.: OCR-Free Document Understanding Transformer, in: Computer Vision – ECCV 2022, edited by: Avidan, S., Brostow, G., Cissé, M., Farinella, G. M., and Hassner, T., vol. 13688, Springer Nature Switzerland, Cham, 498–517, ISBN 978-3-031-19814-4 978-3-031-19815-1, https://doi.org/10.1007/978-3-031-19815-1_29, 2022. a
Kiss, A. and Laszlovszky, J.: 14th-16th-Century Danube Floods and Long-Term Water-Level Changes in Archaeological and Sedimentary Evidence in The Western and Central Carpathian Basin: An Overview with Documentary Comparison, Journal of Environmental Geography, 6, 1–11, https://doi.org/10.2478/jengeo-2013-0001, 2013. a
Koutsoyiannis, D., Zarkadoulas, N., Angelakis, A. N., and Tchobanoglous, G.: Urban Water Management in Ancient Greece: Legacies and Lessons, J. Water Res. Pl., 134, 45–54, https://doi.org/10.1061/(ASCE)0733-9496(2008)134:1(45), 2008. a
Lakkis, S. G., Canziani, P. O., Rodriquez, J. O., and Yuchechen, A. E.: Early meteorological records from Corrientes and Bahía Blanca, Argentina: Initial ACRE-Argentina data rescue and related activities, Geosci. Data J., 10, 328–346, https://doi.org/10.1002/gdj3.176, 2023. a
Lal, J., Mitkari, A., Bhosale, M., and Doermann, D.: LineFormer: Line Chart Data Extraction Using Instance Segmentation, in: Document Analysis and Recognition – ICDAR 2023, edited by: Fink, G. A., Jain, R., Kise, K., and Zanibbi, R., vol. 14191, Springer Nature Switzerland, Cham, 387–400, ISBN 978-3-031-41733-7, https://doi.org/10.1007/978-3-031-41734-4_24, 2023 (code available at: https://github.com/TheJaeLal/LineFormer, last access: 18 August 2025). a, b, c
Latapy, A., Ferret, Y., Testut, L., Talke, S., Aarup, T., Pons, F., Jan, G., Bradshaw, E., and Pouvreau, N.: Data Rescue Process in the Context of Sea Level Reconstructions: An Overview of the Methodology, Lessons Learned, Up-to-date Best Practices and Recommendations, Geosci. Data J., 10, 396–425, https://doi.org/10.1002/gdj3.179, 2023. a, b, c, d, e
Lee, K., Joshi, M., Turc, I. R., Hu, H., Liu, F., Eisenschlos, J., Khandelwal, U., Shaw, P., Chang, M.-W., and Toutanova, K.: Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding, Proceedings of Machine Learning Research, 202, 18893–18912, 2023. a
Liu, F., Eisenschlos, J., Piccinno, F., Krichene, S., Pang, C., Lee, K., Joshi, M., Chen, W., Collier, N., and Altun, Y.: DePlot: One-shot Visual Language Reasoning by Plot-to-Table Translation, in: Findings of the Association for Computational Linguistics: ACL 2023, Association for Computational Linguistics, Toronto, Canada, 10381–10399, https://doi.org/10.18653/v1/2023.findings-acl.660, 2023. a, b
Lorrey, A. M., Pearce, P. R., Allan, R., Wilkinson, C., Woolley, J.-M., Judd, E., Mackay, S., Rawhat, S., Slivinski, L., Wilkinson, S., Hawkins, E., Quesnel, P., and Compo, G. P.: Meteorological Data Rescue: Citizen Science Lessons Learned from Southern Weather Discovery, Patterns, 3, 100495, https://doi.org/10.1016/j.patter.2022.100495, 2022. a
Lucas, M., Lang, M., Renard, B., and Le Coz, J.: A comprehensive uncertainty framework for historical flood frequency analysis: a 500-year-long case study, Hydrol. Earth Syst. Sci., 28, 5031–5047, https://doi.org/10.5194/hess-28-5031-2024, 2024. a
Luo, J., Li, Z., Wang, J., and Lin, C.-Y.: ChartOCR: Data Extraction from Charts Images via a Deep Hybrid Framework, in: 2021 IEEE Winter Conference on Applications of Computer Vision (WACV), IEEE, Waikoloa, HI, USA, 1916–1924, ISBN 978-1-6654-0477-8, https://doi.org/10.1109/WACV48630.2021.00196, 2021. a
Macdonald, N. and Black, A. R.: Reassessment of Flood Frequency Using Historical Information for the River Ouse at York, UK (1200–2000), Hydrolog. Sci. J., 55, 1152–1162, https://doi.org/10.1080/02626667.2010.508873, 2010. a
Masry, A., Long, D., Tan, J. Q., Joty, S., and Hoque, E.: ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning, in: Findings of the Association for Computational Linguistics: ACL 2022, Association for Computational Linguistics, Dublin, Ireland, 2263–2279, https://doi.org/10.18653/v1/2022.findings-acl.177, 2022. a
Masry, A., Kavehzadeh, P., Do, X. L., Hoque, E., and Joty, S.: UniChart: A Universal Vision-language Pretrained Model for Chart Comprehension and Reasoning, arXiv [preprint], https://doi.org/10.48550/arXiv.2305.14761, 2023. a
Matsumoto, H., Tanioka, Y., Nishimura, Y., Tsuji, Y., Namegaya, Y., Nakasu, T., and Iwasaki, S.-I.: Review of Tide Gauge Records in the Indian Ocean, J. Earthq. Tsunami, 3, 1–15, https://doi.org/10.1142/S1793431109000378, 2009. a
McInnes, K. L., O'Grady, J. G., Hague, B. S., Gregory, R., Hoeke, R., Trenham, C., and Stephenson, A.: Digitizing the Williamstown, Australia Tide-Gauge Record Back to 1872: Insights Into Changing Extremes, J. Geophys. Res.-Oceans, 129, e2024JC020908, https://doi.org/10.1029/2024JC020908, 2024. a, b
McLoughlin, P. J., McCarthy, G. D., Nolan, G., Lawlor, R., and Hickey, K.: The Accurate Digitization of Historical Sea Level Records, Geosci. Data J., gdj3.256, https://doi.org/10.1002/gdj3.256, 2024. a, b
Mcrae, M.: Turning the Tides on Historical Sea Level Records Is Giving up Valuable Secrets, Australia's National Science Agency, https://www.csiro.au/en/news/All/Articles/2018/May/turning-the-tides-on-historical-sea-level-records-is-giving-up-valuable-secrets (last access: 5 March 2025), 2018. a
Methani, N., Ganguly, P., Khapra, M. M., and Kumar, P.: PlotQA: Reasoning over Scientific Plots, in: 2020 IEEE Winter Conference on Applications of Computer Vision (WACV), IEEE, Snowmass Village, CO, USA, 1516–1525, ISBN 978-1-7281-6553-0, https://doi.org/10.1109/WACV45572.2020.9093523, 2020. a
Mitchell, M., Muftakhidinov, B., Winchen, T., Schaik, B. V., Wilms, A., Kylesower, Kensington, Jędrzejewski-Szmek, Z., Badger, T. G., and Badshah400: Markummitchell/Engauge-Digitizer: Version 12.1 Directory Dialogs Start in Saved Paths, Zenodo [code], https://doi.org/10.5281/zenodo.3558440, 2019. a
Murdy, J., Orford, J., and Bell, J.: Maintaining Legacy Data: Saving Belfast Harbour (UK) Tide-Gauge Data (1901–2010), GeoResJ, 6, 65–73, https://doi.org/10.1016/j.grj.2015.02.002, 2015. a
Navarro, L. M., Armstrong, C. G., Changeux, T., Frisch, D., Gil-Romera, G., Kaim, D., McClenachan, L., Munteanu, C., Szabó, P., Baranov, V., Blanco-Garrido, F., Camarero, J. J., García, M. B., Grace, M., Izdebski, A., Morueta-Holme, N., Pando, F., Schouten, R., Spitzig, A., Svenning, J.-C., Tribot, A.-S., Viana, D. S., and Clavero, M.: Integrating Historical Sources for Long-Term Ecological Knowledge and Biodiversity Conservation, Nature Reviews Biodiversity, https://doi.org/10.1038/s44358-025-00084-3, 2025. a, b
Needham, J., Ling, W., and Lu, G.: Civil Engineering and Nautics, vol. 4, Science and Civilisation in China, Physics and Physical Technology, Cambridge Univ. Press, Cambridge, ISBN 978-0-521-07060-7, 1971. a
Neppel, L., Renard, B., Lang, M., Ayral, P.-A., Coeur, D., Gaume, E., Jacob, N., Payrastre, O., Pobanz, K., and Vinet, F.: Flood Frequency Analysis Using Historical Data: Accounting for Random and Systematic Errors, Hydrolog. Sci. J., 55, 192–208, https://doi.org/10.1080/02626660903546092, 2010. a
Paulescu, D., Rogozea, M., Popa, M., and Radulian, M.: Digitized Database of Old Seismograms Recorder in Romania, Acta Geophys., 64, 963–977, https://doi.org/10.1515/acgeo-2016-0039, 2016. a
Poco, J. and Heer, J.: Reverse-Engineering Visualizations: Recovering Visual Encodings from Chart Images, Comput. Graph. Forum, 36, 353–363, https://doi.org/10.1111/cgf.13193, 2017. a
Rao, M. P., Cook, E. R., Cook, B. I., D'Arrigo, R. D., Palmer, J. G., Lall, U., Woodhouse, C. A., Buckley, B. M., Uriarte, M., Bishop, D. A., Jian, J., and Webster, P. J.: Seven Centuries of Reconstructed Brahmaputra River Discharge Demonstrate Underestimated High Discharge and Flood Hazard Frequency, Nat. Commun., 11, 6017, https://doi.org/10.1038/s41467-020-19795-6, 2020. a
Rehbein, M.: Künstliche Intelligenz Und Datenmobilisierung Zwischen Geschichtswissenschaft Und Archiv. Über Forschung in Der Digitalen Transformation Und Die Notwendigkeit Des Umdenkens, Archivalische Zeitschrift, 101, 11–27, https://doi.org/10.17613/5m74-sk48, 2024. a
Rehbein, M.: Bavarian Danube Water Level Reconstruction (1826–1894), Zenodo [data set], https://doi.org/10.5281/zenodo.17296750, 2025. a, b, c, d
Rehbein, M.: Kulturgut Und Digitalisierung, in: Clio Guide – Ein Handbuch Zu Digitalen Ressourcen Für Die Geschichtswissenschaften, 3rd edn., edited by: Daniel, S., Enderle, W., Hohls, R., Meyer, T., Prellwitz, J., Prinz, C., Schuhmann, A., and Schwandt, S., Clio Online, Berlin, https://doi.org/10.60693/wxbk-e572, 2026. a
Rehbein, M. and Ernst, M.: Erschließung Handschriftlicher Dokumente Zwischen Fachwissen, Citizen Science Und KI, Bibliothek Forschung und Praxis, 47, 503–513, https://doi.org/10.1515/bfp-2023-0043, 2023. a
Savva, M., Kong, N., Chhajta, A., Fei-Fei, L., Agrawala, M., and Heer, J.: ReVision: Automated Classification, Analysis and Redesign of Chart Images, in: Proceedings of the 24th Annual ACM Symposium on User Interface Software and Technology, ACM, Santa Barbara California USA, 393–402, ISBN 978-1-4503-0716-1, https://doi.org/10.1145/2047196.2047247, 2011. a
Scheurmann, K.: Die Flussgeschichtliche Entwicklung Bayerischer Flüsse Im 19. Und 20. Jahrhundert, Laufener Spezialbeiträge und Laufener Seminarbeiträge, 5, 29–35, 1981. a
Schrader, L.: Grundzüge Der Ritter'schen Methode, Wasserstandsbeobachtungen Aufzutragen Und Abzubilden Und Benützung Derselben Zur Darstellung Des Sommerhochwassers Der Elbe Im Jahre 1882, Zeitschrift des Oesterreichischen Ingenieur- und Architekten-Vereins, 36, 55–59, 1884. a
Short, M. A., Norman, R. S., Pillans, B., De Deckker, P., Usback, R., Opdyke, B. N., Ransley, T. R., Gray, S., and McPhail, D. C.: Two Centuries of Water-Level Records at Lake George, NSW, Aust. J. Earth Sci., 68, 453–472, https://doi.org/10.1080/08120099.2020.1821247, 2021. a
Spanoudi, S., Golfinopoulos, A., and Kalavrouziotis, I.: Water Management in Ancient Alexandria, Egypt. Comparison with Constantinople Hydraulic System, Water Supp., 21, 3427–3436, https://doi.org/10.2166/ws.2021.128, 2021. a
Sušin, N. and Peer, P.: Open-source Tool for Interactive Digitisation of Pluviograph Strip Charts, Weather, 73, 222–226, https://doi.org/10.1002/wea.3001, 2018. a
Talke, S. A. and Jay, D. A.: Nineteenth Century North American and Pacific Tidal Data: Lost or Just Forgotten?, J. Coastal Res., 29, 118, https://doi.org/10.2112/JCOASTRES-D-12-00181.1, 2013. a
Talke, S. A., Mahedy, A., Jay, D. A., Lau, P., Hilley, C., and Hudson, A.: Sea Level, Tidal, and River Flow Trends in the Lower Columbia River Estuary, 1853–Present, J. Geophys. Res.-Oceans, 125, e2019JC015656, https://doi.org/10.1029/2019JC015656, 2020. a
Teleti, P., Hawkins, E., and Wood, K. R.: Digitizing weather observations from World War II US naval ship logbooks, Geosci. Data J., 11, 314–329, https://doi.org/10.1002/gdj3.222, 2024. a
Ullmann, A., Pons, F., and Moron, V.: Tool Kit Helps Digitize Tide Gauge Records, Eos, Transactions American Geophysical Union, 86, 342–342, https://doi.org/10.1029/2005EO380004, 2005. a
Unnikrishnan, A. and Shankar, D.: Are Sea-Level-Rise Trends along the Coasts of the North Indian Ocean Consistent with Global Estimates?, Global Planet. Change, 57, 301–307, https://doi.org/10.1016/j.gloplacha.2006.11.029, 2007. a
Wang, K., Ellsworth, W. L., Beroza, G. C., Williams, G., Zhang, M., Schroeder, D., and Rubinstein, J.: Seismology with Dark Data: Image-Based Processing of Analog Records Using Machine Learning for the Rangely Earthquake Control Experiment, Seismol. Res. Lett., 90, 553–562, https://doi.org/10.1785/0220180298, 2019. a
Wang, M., Yang, F., Liao, X., Wang, B., Gao, K., Zhang, L., Guo, W., Jiang, J., Yan, B., Xu, Y., and Wan, Q.: A Novel Approach to Automatically Digitize Analog Seismograms, Seismol. Res. Lett., 96, 192–206, https://doi.org/10.1785/0220240220, 2025. a
Wasson, R., Sundriyal, Y., Chaudhary, S., Jaiswal, M. K., Morthekai, P., Sati, S., and Juyal, N.: A 1000-Year History of Large Floods in the Upper Ganga Catchment, Central Himalaya, India, Quaternary Sci. Rev., 77, 156–166, https://doi.org/10.1016/j.quascirev.2013.07.022, 2013. a
WBGU: EU-Wasserpolitik Im Aufbruch: Die EU-Wasseresilienzstrategie Als Chance Nutzen, Tech. Rep. 14, WBGU, Berlin, https://www.wbgu.de/fileadmin/user_upload/wbgu/publikationen/politikpapiere/pp14_2025/pdf/wbgu_pp14.pdf (last access: 5 March 2025), 2025a. a
WBGU: Empfehlungen für die internationale Wassergovernance: Policy Brief, Policy Brief, Wissenschaftlicher Beirat d. Bundesregierung Globale Umweltveränderungen, Berlin, ISBN 978-3-946830-48-1, 2025b. a
Weigmann: Aus Dem Wasserbaulichen Arbeitsgebiet Der Bayerischen Staatsbauverwaltung, Die Bautechnik, 13, 483–487, 1935. a
Westcott, N., Cooper, J., Andsager, K., Stoecker, L., and Shein, K.: Status and Climate Applications of the 19th Century Forts and Volunteer Observer Database, Journal of Applied and Service Climatology, 2021, 1–14, https://doi.org/10.46275/JOASC.2021.09.001, 2021. a
Wetter, O.: The potential of historical hydrology in Switzerland, Hydrol. Earth Syst. Sci., 21, 5781–5803, https://doi.org/10.5194/hess-21-5781-2017, 2017. a
Wilkinson, C., Brönnimann, S., Brugnara, Y., Brohan, P., Valente, M. A., Gilabert, A., Jourdain, S., Roucaute, E., Crouthamel, R., Manola, B.-I., and COMPO, GILBERT: Best Practice Guidelines for Climate Data Rescue, Copernicus Climate Change Service, https://doi.org/10.24381/X9RN-MP92, 2019. a, b
Willems, H. and Dahms, J.-M. (Eds.): The Nile: Natural and Cultural Landscape in Egypt: Proceedings of the International Symposium Held at the Johannes Gutenberg-Universität Mainz, 22 & 23 February 2013, transcript, ISBN 978-3-8394-3615-8, https://doi.org/10.14361/9783839436158, 2017. a
Winiwarter, V., Schmid, M., and Dressel, G.: Looking at Half a Millennium of Co-Existence: The Danube in Vienna as a Socio-Natural Site, Water History, 5, 101–119, https://doi.org/10.1007/s12685-013-0079-x, 2013. a
WMO, W. M. O.: Guidelines on Best Practices for Climate Data Rescue, no. 1182 in WMO, World Meteorological Organization, Geneva, Switzerland, ISBN 978-92-63-11182-1, 2024. a
Woodworth, P. L. and Blackman, D. L.: Changes in Extreme High Waters at Liverpool since 1768, Int. J. Climatol., 22, 697–714, https://doi.org/10.1002/joc.761, 2002. a
Woodworth, P. L., Hunter, J. R., Marcos, M., Caldwell, P., Menéndez, M., and Haigh, I.: Towards a Global Higher-frequency Sea Level Dataset, Geosci. Data J., 3, 50–59, https://doi.org/10.1002/gdj3.42, 2016. a
World Meteorological Organization: State of Global Water Resources 2024, Tech. rep., World Meteorological Organization, https://doi.org/10.59327/WMO/WATER/2024, 2025. a
Xue, N., Wu, T., Bai, S., Wang, F.-D., Xia, G.-S., Zhang, L., and Torr, P. H. S.: Holistically-Attracted Wireframe Parsing: From Supervised to Self-Supervised Learning, IEEE T. Pattern Anal., 45, 14727–14744, https://doi.org/10.1109/TPAMI.2023.3312749, 2023. a
Yepes, A. J., Zhong, X., and Burdick, D.: ICDAR 2021 Competition on Scientific Literature Parsing, arXiv [preprint], https://doi.org/10.48550/arXiv.2106.14616, 2021. a
Zhao, H., Jia, J., and Koltun, V.: Exploring Self-Attention for Image Recognition, in: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, Seattle, WA, USA, 10073–10082, ISBN 978-1-7281-7168-5, https://doi.org/10.1109/CVPR42600.2020.01009, 2020. a
Short summary
We transformed nineteenth-century hand-drawn Bavarian Danube gauge charts into daily water-level records using a largely automated, human-checked image analysis workflow. Tests at several gauges show the method reproduces levels with high accuracy while significantly cutting manual effort. The resulting open scientific datasets and traceable sources enable researchers and planners to study past floods and droughts, improve long records, and inform river management and climate impact assessments.
We transformed nineteenth-century hand-drawn Bavarian Danube gauge charts into daily water-level...
Altmetrics
Final-revised paper
Preprint