English
 
Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
Add to Basket
  Local TagsRelease HistoryDetailsSummary

Released
Conference Paper

Water quality prediction for Beijing’s sub-center based on deep learning model

Authors

Luo,  Qun
IUGG 2023, General Assemblies, 1 General, International Union of Geodesy and Geophysics (IUGG), External Organizations;

Peng,  Dingzhi
IUGG 2023, General Assemblies, 1 General, International Union of Geodesy and Geophysics (IUGG), External Organizations;

Gu,  Yu
IUGG 2023, General Assemblies, 1 General, International Union of Geodesy and Geophysics (IUGG), External Organizations;

Luo,  Xiaoyu
IUGG 2023, General Assemblies, 1 General, International Union of Geodesy and Geophysics (IUGG), External Organizations;

External Ressource
No external resources are shared
Fulltext (public)
There are no public fulltexts stored in GFZpublic
Supplementary Material (public)
There is no public supplementary material available
Citation

Luo, Q., Peng, D., Gu, Y., Luo, X. (2023): Water quality prediction for Beijing’s sub-center based on deep learning model, XXVIII General Assembly of the International Union of Geodesy and Geophysics (IUGG) (Berlin 2023).
https://doi.org/10.57757/IUGG23-2988


Cite as: https://gfzpublic.gfz-potsdam.de/pubman/item/item_5018916
Abstract
In the context of rapid urbanization, a certain amount of pollution discharge would inevitably produce in the process of urbanization construction. Therefore, it is necessary to establish a fast and effective method of water quality prediction for sustainable development. The deep learning methods could express the high-dimensional and nonlinear relationship between water quality and other factors, so the LSTM and BP models were established in this paper, then the transfer learning model was proposed and optimized on the base of the upstream and downstream relationships in the Beijing’s sub-center. The results showed that the transfer learning improved NSE by 7% and 9% for LSTM and BP at Dongguan Bridge, respectively. For the Xugezhuang in the Liangshui River, it improved by 11% and 17%, respectively. At Yulinzhuang, NSE were improved by 16% and 13%, respectively. The enhancement of the model performance is more obvious based on river structure, and it would provide an idea for the effective model construction in the ungauged basins or regions.