MeteoSaver v1.0: a machine-learning based software  for the transcription of historical weather data

Muheki, Derrick; Vercruysse, Bas; Chandrasekar, Krishna Kumar Thirukokaranam; Verbruggen, Christophe; Birkholz, Julie M.; Hufkens, Koen; Verbeeck, Hans; Boeckx, Pascal; Lampe, Seppe; Hawkins, Ed; Thorne, Peter; Ntumba, Dominique Kankonde; Moulasa, Olivier Kapalay; Thiery, Wim

doi:10.5194/gmd-19-3213-2026

Articles | Volume 19, issue 8

https://doi.org/10.5194/gmd-19-3213-2026

© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/gmd-19-3213-2026

© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 19, issue 8

Model description paper

|

23 Apr 2026

Model description paper |

| 23 Apr 2026

MeteoSaver v1.0: a machine-learning based software for the transcription of historical weather data

Derrick Muheki, Bas Vercruysse, Krishna Kumar Thirukokaranam Chandrasekar, Christophe Verbruggen, Julie M. Birkholz, Koen Hufkens, Hans Verbeeck, Pascal Boeckx, Seppe Lampe, Ed Hawkins, Peter Thorne, Dominique Kankonde Ntumba, Olivier Kapalay Moulasa, and Wim Thiery

Viewed

Total article views: 10,340 (including HTML, PDF, and XML)

HTML	PDF	XML	Total	Supplement	BibTeX	EndNote
8,764	1,364	212	10,340	172	174	203

HTML: 8,764
PDF: 1,364
XML: 212
Total: 10,340
Supplement: 172
BibTeX: 174
EndNote: 203

Views and downloads (calculated since 10 Jun 2025)

Month	HTML	PDF	XML	Total
Jun 2025	362	52	14	428
Jul 2025	122	36	6	164
Aug 2025	934	34	4	972
Sep 2025	4,098	70	14	4,182
Oct 2025	1,138	98	30	1,266
Nov 2025	218	88	6	312
Dec 2025	178	160	16	354
Jan 2026	112	178	12	302
Feb 2026	170	136	12	318
Mar 2026	294	170	34	498
Apr 2026	367	140	16	523
May 2026	521	95	18	634
Jun 2026	58	27	10	95
Jul 2026	140	61	8	209
Aug 2026	52	19	12	83

Cumulative views and downloads (calculated since 10 Jun 2025)

Month	HTML	PDF	XML	Total
Jun 2025	362	52	14	428
Jul 2025	122	36	6	164
Aug 2025	934	34	4	972
Sep 2025	4,098	70	14	4,182
Oct 2025	1,138	98	30	1,266
Nov 2025	218	88	6	312
Dec 2025	178	160	16	354
Jan 2026	112	178	12	302
Feb 2026	170	136	12	318
Mar 2026	294	170	34	498
Apr 2026	367	140	16	523
May 2026	521	95	18	634
Jun 2026	58	27	10	95
Jul 2026	140	61	8	209
Aug 2026	52	19	12	83

Viewed (geographical distribution)

Total article views: 10,340 (including HTML, PDF, and XML) Thereof 10,269 with geography defined and 71 with unknown origin.

Country	#	Views	%

1

1

Cited

Saved (final revised paper)

Latest update: 16 Aug 2026

Short summary

Archives worldwide host vast records of observed weather data crucial for understanding climate variability. However, most of these records are still in paper form, limiting their use. To address this, we developed MeteoSaver, an open-source tool, to transcribe these records to machine-readable format. Applied to ten handwritten temperature sheets, it achieved a median accuracy of 74 %. This tool offers a promising solution to preserve records from archives and unlock historical weather insights.