dc.contributor.author | Jiang, Peishi | |
dc.contributor.author | Meinert, Nis | |
dc.contributor.author | Jordão, Helga | |
dc.contributor.author | Weisser, Constantin | |
dc.contributor.author | Holgate, Simon | |
dc.contributor.author | Lavin, Alexander | |
dc.contributor.author | Lütjens, Björn | |
dc.contributor.author | Newman, Dava | |
dc.contributor.author | Wainwright, Haruko | |
dc.contributor.author | Walker, Catherine | |
dc.contributor.author | Barnard, Patrick | |
dc.date.accessioned | 2024-01-12T00:47:35Z | |
dc.date.available | 2024-01-12T00:47:35Z | |
dc.date.issued | 2021 | |
dc.identifier.citation | Jiang, P., et al (2021) Digital Twin Earth - Coasts: Developing a fast and
physics-informed surrogate model for coastal floods
via neural operators. In: Machine Learning and the Physical Sciences
Workshop at the 35th Conference on Neural Information Processing Systems (NeurIPS)
December 13, 2021, 7pp.(arXiv:2110.07100v1 [physics.ao-ph] for this version). DOI: https://doi.org/10.48550/arXiv.2110.07100 | en_US |
dc.identifier.uri | https://repository.oceanbestpractices.org/handle/11329/2414 | |
dc.description.abstract | Developing fast and accurate surrogates for physics-based coastal and ocean models
is an urgent need due to the coastal flood risk under accelerating sea level rise,
and the computational expense of deterministic numerical models. For this purpose,
we develop the first digital twin of Earth coastlines with new physics-informed
machine learning techniques extending the state-of-art Neural Operator. As a
proof-of-concept study, we built Fourier Neural Operator (FNO) surrogates on the
simulations of an industry-standard coastal and ocean model – Nucleus for European
Modelling of the Ocean (NEMO). The resulting FNO surrogate accurately
predicts the sea surface height in most regions while achieving upwards of 45x
acceleration of NEMO. We delivered an open-source CoastalTwin platform in an
end-to-end and modular way, to enable easy extensions to other simulations and
ML-based surrogate methods. Our results and deliverable provide a promising
approach to massively accelerate coastal dynamics simulators, which can enable
scientists to efficiently execute many simulations for decision-making, uncertainty
quantification, and other research activities. | en_US |
dc.language.iso | en | en_US |
dc.publisher | Neural Information Processing Systems Foundation | en_US |
dc.subject.other | Machine learning | en_US |
dc.subject.other | Digital Twin of the Earth | en_US |
dc.subject.other | DTO | en_US |
dc.subject.other | Numerical modelling | en_US |
dc.subject.other | Coastal model | en_US |
dc.subject.other | Coastlines | en_US |
dc.subject.other | Flooding | en_US |
dc.title | Digital Twin Earth - Coasts: Developing a fast and physics-informed surrogate model for coastal floods via neural operators. | en_US |
dc.type | Book Section | en_US |
dc.description.status | Published | en_US |
dc.description.refereed | Refereed | en_US |
dc.format.pagerange | 7pp. | en_US |
dc.identifier.doi | https://doi.org/10.48550/arXiv.2110.07100 | |
dc.subject.parameterDiscipline | Other physical oceanographic measurements | en_US |
dc.subject.dmProcesses | Data analysis | en_US |
dc.subject.dmProcesses | Data visualization | en_US |
dc.subject.dmProcesses | Data processing | en_US |
dc.description.currentstatus | Current | en_US |
dc.title.parent | Machine Learning and the Physical Sciences Workshop at the 35th Conference on Neural Information Processing Systems (NeurIPS) December 13, 2021. [Online] | en_US |
dc.description.sdg | 14.a | en_US |
dc.description.maturitylevel | Mature | en_US |
dc.description.adoption | Validated (tested by third parties) | en_US |
dc.description.adoption | Multi-organisational | en_US |
dc.description.adoption | International | en_US |
dc.description.methodologyType | Reports with methodological relevance | en_US |
obps.resourceurl.publisher | https://neurips.cc/Conferences/2021 | |