Simulation of karst spring discharge using a combination of time–frequency analysis methods and long short-term memory neural networks

Lixing An, Yonghong Hao, Tian Chyi Jim Yeh, Yan Liu, Wenqiang Liu, Baoju Zhang

Research output: Contribution to journalArticle

Abstract

Spring discharges from karst aquifers are results of spatially and temporally complex hydrologic processes, such as precipitation, surface runoff, infiltration, groundwater flow as well as anthropogenic factors. These processes are spatially and temporally varying at a multiplicity of scales with nonlinear and nonstationary characteristics. For improving the prediction accuracy of karst springs discharge, this study first applied the time–frequency analysis methods, including singular spectrum analysis (SSA) and ensemble empirical mode decomposition (EEMD) to extract frequency and trend feature of Niangziguan Springs discharge. Then the long short-term memory (LSTM) was used to simulate each frequency and trend subsequence. Subsequently, the prediction of spring discharge was completed by a combination of the simulated results from LSTM. Finally, the performances of LSTM, SSA-LSTM, and EEMD-LSTM under different inputs were compared. The results show that the performance of SSA-LSTM and EEMD-LSTM are better than LSTM, and the EEMD-LSTM model achieved the best prediction performance.

Original languageEnglish (US)
Article number125320
JournalJournal of Hydrology
Volume589
DOIs
StatePublished - Oct 2020

Keywords

  • Deep learning
  • Ensemble empirical mode decomposition (EEMD)
  • Karst spring discharge
  • Long short-term memory (LSTM)
  • Nonlinear and nonstationary time series
  • Singular spectrum analysis (SSA)

ASJC Scopus subject areas

  • Water Science and Technology

Fingerprint Dive into the research topics of 'Simulation of karst spring discharge using a combination of time–frequency analysis methods and long short-term memory neural networks'. Together they form a unique fingerprint.

  • Cite this