A physics-informed statistical learning framework for forecasting local suspended sediment concentrations in marine environment
Zhang, Shaotong, Wu, Ryan, Wang, You-Gan, Jeng, Dong-Sheng and Li, Guangxue. (2022). A physics-informed statistical learning framework for forecasting local suspended sediment concentrations in marine environment. Water Research. 218, pp. 1-16. https://doi.org/10.1016/j.watres.2022.118518
|Authors||Zhang, Shaotong, Wu, Ryan, Wang, You-Gan, Jeng, Dong-Sheng and Li, Guangxue|
An in-situ monitoring of water quality (suspended sediment concentration, SSC) and concurrent hydrodynamics was conducted in the subaqueous Yellow River Delta in China. Empirical mode decomposition and spectral analysis on the SSC time series reveal the different periodicities of each physical mechanism that contribute to the SSC variations. Based on this physical understanding, the decomposed SSC time series were trained separately with a newly-proposed augmented lncosh ridge regression, in which (1) a lncosh function was incorporated in traditional ridge regression for handling outliers in original data, and (2) the temporal auto-correlation in the decomposed SSC series was used for augmented regression. Finally, the trained sub-series were added up as the final prediction. The advantages of this decomposition-ensemble framework is that it depends on SSC only, superior to the normal process-based models which need the concurrent hydrodynamics for estimating bed shear stress. This will not only reduce the measurement uncertainties of the input when training the data-driven model, but also save the prediction cost as no other parameters than SSC need to be measured and input for running the model. The framework realized 6-hour-ahead high-accuracy forecasting with mean relative errors of 5.80-9.44% in the present case study. The proposed framework can be extended to forecast any signal that is superposed by components with various timescales (periodicities) which is common in nature.
|Keywords||Augmented lncosh ridge regression; Marine ranching; Outlier handling; Temporal auto-correlation; The Yellow River Delta; Water quality|
|Year||01 Jan 2022|
|Journal citation||218, pp. 1-16|
|Digital Object Identifier (DOI)||https://doi.org/10.1016/j.watres.2022.118518|
|Web address (URL)||https://www.sciencedirect.com/science/article/pii/S0043135422004638|
|Open access||Published as non-open access|
|Research or scholarly||Research|
All rights reserved
File Access Level
|Online||27 Apr 2022|
|Publication process dates|
|Accepted||21 Apr 2022|
|Deposited||11 Jan 2023|
|ARC Funded Research||This output has been funded, wholly or partially, under the Australian Research Council Act 2001|
© 2022 Elsevier Ltd. All rights reserved.
This work was supported in part by Australian Research Council (ARC) Discovery Project ( DP160104292 ).
This study was supported by the Natural Science Foundation of Shandong Province (grant number ZR2019BD009 ), the Natural Science Foundation of China (grant number 41807229 ), the China Postdoctoral Science Foundation (grant number 2018M640656 ), Shandong Provincial Postdoctoral Program for Innovative Talents (grantee Shaotong Zhang), and the Funding for Study Abroad Program by the Government of Shandong Province (grant number 201801026 ). This work was supported in part by Industrial Transformation Training Centres (IC190100020).
|Place of publication||United Kingdom|
3views this month
0downloads this month