A machine learning-based evidence map of ocean-related options for climate change mitigation and adaptation

Devi Veytia; Gaël Mariani; Vicky Martí Barclay; Laura Airoldi; Joachim Claudet; Sarah Cooley; Alexandre Magnan; Simon Neill; U. Rashid Sumaila; Olivier Thébaud; Christian R. Voolstra; Phillip Williamson; Marie Bonnin; Joseph Langridge; Adrien Comte; Frédérique Viard; Yunne-Jai Shin; Laurent Bopp; Jean-Pierre Gattuso

doi:10.1038/s44183-025-00159-w

A machine learning-based evidence map of ocean-related options for climate change mitigation and adaptation

Devi Veytia^*, Gaël Mariani, Vicky Martí Barclay, Laura Airoldi, Joachim Claudet, Sarah Cooley, Alexandre Magnan, Simon Neill, U. Rashid Sumaila, Olivier Thébaud, Christian R. Voolstra, Phillip Williamson, Marie Bonnin, Joseph Langridge, Adrien Comte, Frédérique Viard, Yunne-Jai Shin, Laurent Bopp, Jean-Pierre Gattuso

^*Corresponding author for this work

Civil And Environmental Engineering

Research output: Contribution to journal › Article › peer-review

Abstract

The ocean has a vital role to play in addressing the global challenge of climate change, which requires both mitigation and adaptation actions. The exponential increase in research relating to ocean-related options (OROs) requires a rapid and reproducible method to assess the state of knowledge. We train a state-of-the-art large language model to characterise the landscape of ORO research by classifying 44,193 (±11,615) articles across various descriptors. Research proves to be unevenly distributed, concentrating on OROs with mitigation objectives (80%), while revealing research gaps including under-researched ecosystems and an observed paucity of studies simultaneously assessing different ORO types. We also uncover social inequalities driven by mismatches between the global distribution of research effort, climate change responsibility, and risk. These findings are important to maximise the efficacy of OROs, position them within broader climate action portfolios, and inform future research priorities.

Original language	English
Article number	60
Journal	npj Ocean Sustainability
Volume	4
Issue number	1
DOIs	https://doi.org/10.1038/s44183-025-00159-w
Publication status	Published - 19 Nov 2025

Funding

The postdoctoral project of D.V. and the expert panel meetings were funded by the French Priority Research Programme (PPR) on Ocean & Climate. We acknowledge the support of Supercomputing Wales, a project partly funded by the European Regional Development Fund (ERDF) under grant reference 80898.

Keywords

climate change
ocean-related options
ocean-based solutions

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1038/s44183-025-00159-wLicence: CC BY-NC-ND 4.0

Veytia-etal-2025-A-machine-learning-based-evidence-map-of-ocean-related-optionsFinal published version, 3.77 MBLicence: CC BY-NC-ND 4.0

Cite this

Veytia, D., Mariani, G., Martí Barclay, V., Airoldi, L., Claudet, J., Cooley, S., Magnan, A., Neill, S., Sumaila, U. R., Thébaud, O., Voolstra, C. R., Williamson, P., Bonnin, M., Langridge, J., Comte, A., Viard, F., Shin, Y.-J., Bopp, L., & Gattuso, J.-P. (2025). A machine learning-based evidence map of ocean-related options for climate change mitigation and adaptation. npj Ocean Sustainability, 4(1), Article 60. https://doi.org/10.1038/s44183-025-00159-w

@article{2b7bb75769244a3baf9457e01b8b117c,

title = "A machine learning-based evidence map of ocean-related options for climate change mitigation and adaptation",

abstract = "The ocean has a vital role to play in addressing the global challenge of climate change, which requires both mitigation and adaptation actions. The exponential increase in research relating to ocean-related options (OROs) requires a rapid and reproducible method to assess the state of knowledge. We train a state-of-the-art large language model to characterise the landscape of ORO research by classifying 44,193 (±11,615) articles across various descriptors. Research proves to be unevenly distributed, concentrating on OROs with mitigation objectives (80\%), while revealing research gaps including under-researched ecosystems and an observed paucity of studies simultaneously assessing different ORO types. We also uncover social inequalities driven by mismatches between the global distribution of research effort, climate change responsibility, and risk. These findings are important to maximise the efficacy of OROs, position them within broader climate action portfolios, and inform future research priorities.",

keywords = "climate change, ocean-related options, ocean-based solutions",

author = "Devi Veytia and Ga{\"e}l Mariani and \{Mart{\'i} Barclay\}, Vicky and Laura Airoldi and Joachim Claudet and Sarah Cooley and Alexandre Magnan and Simon Neill and Sumaila, \{U. Rashid\} and Olivier Th{\'e}baud and Voolstra, \{Christian R.\} and Phillip Williamson and Marie Bonnin and Joseph Langridge and Adrien Comte and Fr{\'e}d{\'e}rique Viard and Yunne-Jai Shin and Laurent Bopp and Jean-Pierre Gattuso",

year = "2025",

month = nov,

day = "19",

doi = "10.1038/s44183-025-00159-w",

language = "English",

volume = "4",

number = "1",

}

Veytia, D, Mariani, G, Martí Barclay, V, Airoldi, L, Claudet, J, Cooley, S, Magnan, A, Neill, S, Sumaila, UR, Thébaud, O, Voolstra, CR, Williamson, P, Bonnin, M, Langridge, J, Comte, A, Viard, F, Shin, Y-J, Bopp, L & Gattuso, J-P 2025, 'A machine learning-based evidence map of ocean-related options for climate change mitigation and adaptation', npj Ocean Sustainability, vol. 4, no. 1, 60. https://doi.org/10.1038/s44183-025-00159-w

TY - JOUR

T1 - A machine learning-based evidence map of ocean-related options for climate change mitigation and adaptation

AU - Veytia, Devi

AU - Mariani, Gaël

AU - Martí Barclay, Vicky

AU - Airoldi, Laura

AU - Claudet, Joachim

AU - Cooley, Sarah

AU - Magnan, Alexandre

AU - Neill, Simon

AU - Sumaila, U. Rashid

AU - Thébaud, Olivier

AU - Voolstra, Christian R.

AU - Williamson, Phillip

AU - Bonnin, Marie

AU - Langridge, Joseph

AU - Comte, Adrien

AU - Viard, Frédérique

AU - Shin, Yunne-Jai

AU - Bopp, Laurent

AU - Gattuso, Jean-Pierre

PY - 2025/11/19

Y1 - 2025/11/19

N2 - The ocean has a vital role to play in addressing the global challenge of climate change, which requires both mitigation and adaptation actions. The exponential increase in research relating to ocean-related options (OROs) requires a rapid and reproducible method to assess the state of knowledge. We train a state-of-the-art large language model to characterise the landscape of ORO research by classifying 44,193 (±11,615) articles across various descriptors. Research proves to be unevenly distributed, concentrating on OROs with mitigation objectives (80%), while revealing research gaps including under-researched ecosystems and an observed paucity of studies simultaneously assessing different ORO types. We also uncover social inequalities driven by mismatches between the global distribution of research effort, climate change responsibility, and risk. These findings are important to maximise the efficacy of OROs, position them within broader climate action portfolios, and inform future research priorities.

AB - The ocean has a vital role to play in addressing the global challenge of climate change, which requires both mitigation and adaptation actions. The exponential increase in research relating to ocean-related options (OROs) requires a rapid and reproducible method to assess the state of knowledge. We train a state-of-the-art large language model to characterise the landscape of ORO research by classifying 44,193 (±11,615) articles across various descriptors. Research proves to be unevenly distributed, concentrating on OROs with mitigation objectives (80%), while revealing research gaps including under-researched ecosystems and an observed paucity of studies simultaneously assessing different ORO types. We also uncover social inequalities driven by mismatches between the global distribution of research effort, climate change responsibility, and risk. These findings are important to maximise the efficacy of OROs, position them within broader climate action portfolios, and inform future research priorities.

KW - climate change

KW - ocean-related options

KW - ocean-based solutions

UR - https://zenodo.org/records/13349908

UR - https://github.com/dveytia/ORO-map-relevance

U2 - 10.1038/s44183-025-00159-w

DO - 10.1038/s44183-025-00159-w

M3 - Article

VL - 4

JO - npj Ocean Sustainability

JF - npj Ocean Sustainability

IS - 1

M1 - 60

ER -

A machine learning-based evidence map of ocean-related options for climate change mitigation and adaptation

Abstract

Funding

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this