Physics-guided generative adversarial networks for sea subsurface temperature prediction
Physics-guided generative adversarial networks for sea subsurface temperature prediction
Sea subsurface temperature, an essential component of aquatic wildlife, underwater dynamics and heat transfer with the sea surface, is affected by global warming in climate change. Existing research is commonly based on either physics-based numerical models or data based models. Physical modeling and machine learning are traditionally considered as two unrelated fields for the sea subsurface temperature prediction task, with very different scientific paradigms (physics-driven and data-driven). However, we believe both methods are complementary to each other. Physical modeling methods can offer the potential for extrapolation beyond observational conditions, while data-driven methods are flexible in adapting to data and are capable of detecting unexpected patterns. The combination of both approaches is very attractive and offers potential performance improvement. In this paper, we propose a novel framework based on generative adversarial network (GAN) combined with numerical model to predict sea subsurface temperature. First, a GAN-based model is used to learn the simplified physics between the surface temperature and the target subsurface temperature in numerical model. Then, observation data are used to calibrate the GAN-based model parameters to obtain better prediction. We evaluate the proposed framework by predicting daily sea subsurface temperature in the South China sea. Extensive experiments demonstrate the effectiveness of the proposed framework compared to existing state-of-the-art methods.
1-14
Meng, Yuxin
2032bc96-3da7-4596-83cc-7fa5ef2e8c5c
Rigall, Eric
f85fc376-7def-43b7-8247-77d1df71a943
Chen, Xueen
34ea7fed-6e78-4270-b701-43763dbb6232
Gao, Feng
b70fc7ee-1c00-4b32-aa1a-272e603a3add
Dong, Junyu
cb626ba3-7c15-4441-b364-bc33349ad5b4
Chen, Sheng
9310a111-f79a-48b8-98c7-383ca93cbb80
Meng, Yuxin
2032bc96-3da7-4596-83cc-7fa5ef2e8c5c
Rigall, Eric
f85fc376-7def-43b7-8247-77d1df71a943
Chen, Xueen
34ea7fed-6e78-4270-b701-43763dbb6232
Gao, Feng
b70fc7ee-1c00-4b32-aa1a-272e603a3add
Dong, Junyu
cb626ba3-7c15-4441-b364-bc33349ad5b4
Chen, Sheng
9310a111-f79a-48b8-98c7-383ca93cbb80
Meng, Yuxin, Rigall, Eric, Chen, Xueen, Gao, Feng, Dong, Junyu and Chen, Sheng
(2021)
Physics-guided generative adversarial networks for sea subsurface temperature prediction.
IEEE Transactions on Neural Networks and Learning Systems, .
(In Press)
Abstract
Sea subsurface temperature, an essential component of aquatic wildlife, underwater dynamics and heat transfer with the sea surface, is affected by global warming in climate change. Existing research is commonly based on either physics-based numerical models or data based models. Physical modeling and machine learning are traditionally considered as two unrelated fields for the sea subsurface temperature prediction task, with very different scientific paradigms (physics-driven and data-driven). However, we believe both methods are complementary to each other. Physical modeling methods can offer the potential for extrapolation beyond observational conditions, while data-driven methods are flexible in adapting to data and are capable of detecting unexpected patterns. The combination of both approaches is very attractive and offers potential performance improvement. In this paper, we propose a novel framework based on generative adversarial network (GAN) combined with numerical model to predict sea subsurface temperature. First, a GAN-based model is used to learn the simplified physics between the surface temperature and the target subsurface temperature in numerical model. Then, observation data are used to calibrate the GAN-based model parameters to obtain better prediction. We evaluate the proposed framework by predicting daily sea subsurface temperature in the South China sea. Extensive experiments demonstrate the effectiveness of the proposed framework compared to existing state-of-the-art methods.
Text
pggan_finalversion
- Accepted Manuscript
Restricted to Repository staff only until 26 October 2023.
Request a copy
More information
Accepted/In Press date: 26 October 2021
Identifiers
Local EPrints ID: 452565
URI: http://eprints.soton.ac.uk/id/eprint/452565
ISSN: 2162-237X
PURE UUID: 626e9669-06f5-4a37-b48b-ae22a52cce0e
Catalogue record
Date deposited: 11 Dec 2021 11:27
Last modified: 23 Jul 2022 00:32
Export record
Contributors
Author:
Yuxin Meng
Author:
Eric Rigall
Author:
Xueen Chen
Author:
Feng Gao
Author:
Junyu Dong
Author:
Sheng Chen
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics