Spatial-temporal process simulation and prediction of chlorophyll-a concentration in Dianchi Lake based on wavelet analysis and long-short term memory network

• Published in: Journal of hydrology (Amsterdam) Vol. 582; p. 124488
• Main Authors: Yu, Zhenyu, Yang, Kun, Luo, Yi, Shang, Chunxue
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.03.2020
• Subjects: chlorophyll; climate change; Continuous wavelet transform; Cyanobacterial bloom; data collection; Geospatial analysis; hydrology; lakes; Long-short term memory network; neural networks; nonpoint source pollution; prediction; urbanization; water management; water pollution; water quality; wavelet; Wavelet threshold denoising; Cyanobacterial bloom; Wavelet threshold denoising; Geospatial analysis; Long-short term memory network; Continuous wavelet transform

•Chlorophyll-a (Chla) higher than 100 μg/L from 2005 to 2020 have a tendency to spread.•Wavelet mean fusion (WMF) is proposed based on wavelet domain threshold denoising (WDTD)•WDTD, WMF and long-short term memory (LSTM) are combined to a long-term prediction model.•The model is used to predict Chla...