Model Error Correction in Data Assimilation by Integrating Neural Networks
In this paper, we suggest a new methodology which combines Neural Networks (NN) into Data Assimilation (DA). Focusing on the structural model uncertainty, we propose a framework for integration NN with the physical models by DA algorithms, to improve both the assimilation process and the forecasting...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Tsinghua University Press
2019-06-01
|
| Series: | Big Data Mining and Analytics |
| Subjects: | |
| Online Access: | https://www.sciopen.com/article/10.26599/BDMA.2018.9020033 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832572946255708160 |
|---|---|
| author | Jiangcheng Zhu Shuang Hu Rossella Arcucci Chao Xu Jihong Zhu Yi-ke Guo |
| author_facet | Jiangcheng Zhu Shuang Hu Rossella Arcucci Chao Xu Jihong Zhu Yi-ke Guo |
| author_sort | Jiangcheng Zhu |
| collection | DOAJ |
| description | In this paper, we suggest a new methodology which combines Neural Networks (NN) into Data Assimilation (DA). Focusing on the structural model uncertainty, we propose a framework for integration NN with the physical models by DA algorithms, to improve both the assimilation process and the forecasting results. The NNs are iteratively trained as observational data is updated. The main DA models used here are the Kalman filter and the variational approaches. The effectiveness of the proposed algorithm is validated by examples and by a sensitivity study. |
| format | Article |
| id | doaj-art-5b3da76349d74dfbb5a5501b2b53b0a4 |
| institution | Kabale University |
| issn | 2096-0654 |
| language | English |
| publishDate | 2019-06-01 |
| publisher | Tsinghua University Press |
| record_format | Article |
| series | Big Data Mining and Analytics |
| spelling | doaj-art-5b3da76349d74dfbb5a5501b2b53b0a42025-02-02T05:59:19ZengTsinghua University PressBig Data Mining and Analytics2096-06542019-06-0122839110.26599/BDMA.2018.9020033Model Error Correction in Data Assimilation by Integrating Neural NetworksJiangcheng Zhu0Shuang Hu1Rossella Arcucci2Chao Xu3Jihong Zhu4Yi-ke Guo5<institution content-type="dept">State Key Laboratory of Industrial Control Technology</institution>, <institution>Zhejiang University</institution>, <city>Hangzhou</city> <postal-code>310027</postal-code>, <country>China</country>.<institution content-type="dept">Department of Computer Science and Technology</institution>, <institution>Tsinghua University</institution>, <city>Beijing</city> <postal-code>100084</postal-code>, <country>China</country>.<institution content-type="dept">Data Science Institute</institution>, <institution>Imperial College London</institution>, <city>London</city> <postal-code>SW7 2AZ</postal-code>, <country>UK</country>.<institution content-type="dept">State Key Laboratory of Industrial Control Technology</institution>, <institution>Zhejiang University</institution>, <city>Hangzhou</city> <postal-code>310027</postal-code>, <country>China</country>.<institution content-type="dept">Department of Computer Science and Technology</institution>, <institution>Tsinghua University</institution>, <city>Beijing</city> <postal-code>100084</postal-code>, <country>China</country>.<institution content-type="dept">Data Science Institute</institution>, <institution>Imperial College London</institution>, <city>London</city> <postal-code>SW7 2AZ</postal-code>, <country>UK</country>.In this paper, we suggest a new methodology which combines Neural Networks (NN) into Data Assimilation (DA). Focusing on the structural model uncertainty, we propose a framework for integration NN with the physical models by DA algorithms, to improve both the assimilation process and the forecasting results. The NNs are iteratively trained as observational data is updated. The main DA models used here are the Kalman filter and the variational approaches. The effectiveness of the proposed algorithm is validated by examples and by a sensitivity study.https://www.sciopen.com/article/10.26599/BDMA.2018.9020033data assimilationdeep learningneural networkskalman filtervariational approach |
| spellingShingle | Jiangcheng Zhu Shuang Hu Rossella Arcucci Chao Xu Jihong Zhu Yi-ke Guo Model Error Correction in Data Assimilation by Integrating Neural Networks Big Data Mining and Analytics data assimilation deep learning neural networks kalman filter variational approach |
| title | Model Error Correction in Data Assimilation by Integrating Neural Networks |
| title_full | Model Error Correction in Data Assimilation by Integrating Neural Networks |
| title_fullStr | Model Error Correction in Data Assimilation by Integrating Neural Networks |
| title_full_unstemmed | Model Error Correction in Data Assimilation by Integrating Neural Networks |
| title_short | Model Error Correction in Data Assimilation by Integrating Neural Networks |
| title_sort | model error correction in data assimilation by integrating neural networks |
| topic | data assimilation deep learning neural networks kalman filter variational approach |
| url | https://www.sciopen.com/article/10.26599/BDMA.2018.9020033 |
| work_keys_str_mv | AT jiangchengzhu modelerrorcorrectionindataassimilationbyintegratingneuralnetworks AT shuanghu modelerrorcorrectionindataassimilationbyintegratingneuralnetworks AT rossellaarcucci modelerrorcorrectionindataassimilationbyintegratingneuralnetworks AT chaoxu modelerrorcorrectionindataassimilationbyintegratingneuralnetworks AT jihongzhu modelerrorcorrectionindataassimilationbyintegratingneuralnetworks AT yikeguo modelerrorcorrectionindataassimilationbyintegratingneuralnetworks |