Trends of water and sand fluxes in the Yellow River analyzed based on LSTM model prediction

Peixi Yan; Haotian Luo; Kaiwen Zheng

doi:10.62051/gx429058

Authors

Peixi Yan
Haotian Luo
Kaiwen Zheng

DOI:

https://doi.org/10.62051/gx429058

Keywords:

Water-Sand Flux, LSTM Neural Network Model, Time Series Trend Charts.

Abstract

The Yellow River, the river with the highest sand content in China, the change in its water-sand flux has a significant impact on the ecological environment and resource management. In this paper, we mainly use the LSTM neural network model to predict the change rule of water and sand flux in the next two years according to the data from 2016 to 2021, and finally draw time series graphs according to the prediction results, we find that the water and sand flux has seasonality and sudden change, according to this characteristic, we formulate the optimal monitoring program for the dynamic change of water and sand flux in the next two years, to reduce the waste of monitoring resources. Mastering the change rule of water and sand flux in the Yellow River can provide a scientific basis for allocating water resources and constructing an ecological environment in the Yellow River.

Downloads

Download data is not yet available.

References

[1] Lin Z ,Chao Z ,Qing W , et al.Sediment Coarsening in Tidal Flats and Stable Coastline of the Abandoned Southern Yellow River Sub-Delta in Response to Fluvial Sediment Flux Decrease During the Past Decades#13;[J].Frontiers in Marine Science,2021,8

[2] Gao P ,Wang Y ,Li P , et al.Land degradation changes in the Yellow River Delta and its response to streamflow‐sediment fluxes since 1976[J].Land Degradation Development, 2018, 29 (9):3212-3220.

[3] Ma X ,Zhang G ,Liu S , et al.Distributions and fluxes of nitrous oxide in lower reaches of Yellow River and its estuary: Impact of water-sediment regulation[J].Estuarine, Coastal and Shelf Science,2016,16822-28.

[4] Coastal Research; Researchers at Ludong University Have Reported New Data on Coastal Research (Long-term Trend and Change Point Analysis On Runoff and Sediment Flux Into the Sea From the Yellow River During the Period of 1950-2018)[J].Energy Ecology,2020,

[5] Coastal Research; Researchers at Ludong University Have Reported New Data on Coastal Research (Long-term Trend and Change Point Analysis On Runoff and Sediment Flux Into the Sea From the Yellow River During the Period of 1950-2018)[J].Energy Ecology,2020,

[6] Dang J ,Cui Z ,Liu J , et al.Analysis of the Change Rule and Future Trend of Yellow River Water and Sand Flux Based on Linear Programming Model[J].Academic Journal of Environment Earth Science,2024,6(2):

[7] Zhang K ,Li Y ,Jiang M , et al.Data-Driven Analysis of Water and Sediment Flux at the Xiaolangdi Station of the Yellow River[J].Academic Journal of Environment Earth Science,2024,6(2):

[8] Sui Y ,Shi H ,You Z , et al.Long-term Trend and Change Point Analysis on Runoff and Sediment Flux into the Sea from the Yellow River during the Period of 1950-2018[J].Journal of Coastal Research,2020,99(sp1):203-207.

[9] Sherstinsky A. Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network[J]. Physica D: Nonlinear Phenomena, 2020, 404: 132306.

[10] Song X, Liu Y, Xue L, et al. Time-series well performance prediction based on Long Short-Term Memory (LSTM) neural network model[J]. Journal of Petroleum Science and Engineering, 2020, 186: 106682.