Hybrid machine learning data assimilation  for marine biogeochemistry

Higgs, Ieuan; Bannister, Ross; Skákala, Jozef; Carrassi, Alberto; Ciavatta, Stefano

doi:10.5194/bg-23-315-2026

Articles | Volume 23, issue 1

https://doi.org/10.5194/bg-23-315-2026

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

https://doi.org/10.5194/bg-23-315-2026

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

Articles | Volume 23, issue 1

Research article

|

12 Jan 2026

Research article |

| 12 Jan 2026

Hybrid machine learning data assimilation for marine biogeochemistry

Ieuan Higgs, Ross Bannister, Jozef Skákala, Alberto Carrassi, and Stefano Ciavatta

Viewed

Since the preprint corresponding to this journal article was posted outside of Copernicus Publications, the preprint-related metrics are limited to HTML views.

Total article views: 5,336 (including HTML, PDF, and XML)

HTML	PDF	XML	Total	BibTeX	EndNote
4,235	810	291	5,336	403	304

HTML: 4,235
PDF: 810
XML: 291
Total: 5,336
BibTeX: 403
EndNote: 304

Views and downloads (calculated since 25 Apr 2025)

Month	HTML	PDF	XML	Total
Apr 2025	82	0	82
May 2025	86	0	86
Jun 2025	60	2	62
Jul 2025	68	2	70
Aug 2025	242	4	246
Sep 2025	1,030	0	1,030
Oct 2025	66	0	66
Nov 2025	76	0	76
Dec 2025	98	0	98
Jan 2026	456	106	9	571
Feb 2026	415	81	7	503
Mar 2026	228	43	4	275
Apr 2026	258	120	11	389
May 2026	235	68	12	315
Jun 2026	52	21	5	78
Jul 2026	170	34	7	211
Aug 2026	53	39	20	112
Sep 2026	242	170	104	516
Oct 2026	318	128	104	550
Nov 2026	0

Cumulative views and downloads (calculated since 25 Apr 2025)

Month	HTML	PDF	XML	Total
Apr 2025	82	0	82
May 2025	86	0	86
Jun 2025	60	2	62
Jul 2025	68	2	70
Aug 2025	242	4	246
Sep 2025	1,030	0	1,030
Oct 2025	66	0	66
Nov 2025	76	0	76
Dec 2025	98	0	98
Jan 2026	456	106	9	571
Feb 2026	415	81	7	503
Mar 2026	228	43	4	275
Apr 2026	258	120	11	389
May 2026	235	68	12	315
Jun 2026	52	21	5	78
Jul 2026	170	34	7	211
Aug 2026	53	39	20	112
Sep 2026	242	170	104	516
Oct 2026	318	128	104	550
Nov 2026	0

Viewed (geographical distribution)

Since the preprint corresponding to this journal article was posted outside of Copernicus Publications, the preprint-related metrics are limited to HTML views.

Total article views: 5,336 (including HTML, PDF, and XML) Thereof 5,243 with geography defined and 93 with unknown origin.

Country	#	Views	%

1

1

Cited

Saved (final revised paper)

Latest update: 02 Nov 2026

Short summary

We explored how machine learning can improve computer models that simulate ocean ecosystems. These models help us understand how the ocean works, but they often struggle due to limited observations and complex processes. Our approach uses machine learning to better connect the parts of the system we can observe with those we cannot. This leads to more accurate and efficient predictions, offering a promising way to improve future ocean monitoring and forecasting tools.