Chlorophyll a Simulation in a Lake Ecosystem Using a Model with Wavelet Analysis and Artificial Neural Network

Abstract

Accurate and reliable forecasting is important for the sustainable management of ecosystems. Chlorophyll a (Chl a) simulation and forecasting can provide early warning information and enable managers to make appropriate decisions for protecting lake ecosystems. In this study, we proposed a method for Chl a simulation in a lake that coupled the wavelet analysis and the artificial neural networks (WA-ANN). The proposed method had the advantage of data preprocessing, which reduced noise and managed nonstationary data. Fourteen variables were included in the developed and validated model, relating to hydrologic, ecological and meteorologic time series data from January 2000 to December 2009 at the Lake Baiyangdian study area, North China. The performance of the proposed WA-ANN model for monthly Chl a simulation in the lake ecosystem was compared with a multiple stepwise linear regression (MSLR) model, an autoregressive integrated moving average (ARIMA) model and a regular ANN model. The results showed that the WA-ANN model was suitable for Chl a simulation providing a more accurate performance than the MSLR, ARIMA, and ANN models. We recommend that the proposed method be widely applied to further facilitate the development and implementation of lake ecosystem management.

NDVI dynamics under changing meteorological factors in a shallow lake in future metropolitan, semiarid area in North China

“…Partly because of a large amount of natural evapotranspiration and artificial water withdrawal, its ecological environment is fragile. In particular, the recent construction of dams and reservoirs upstream of the lake, which are intended to provide economic and social benefits to water users, has profoundly changed the natural hydrologic regime 22 , 39 . Low water use efficiency and ecological degradation will hinder the implementation of the plan of establishing XNA.…”

Prediction of Algal Chlorophyll-a and Water Clarity in Monsoon-Region Reservoir Using Machine Learning Approaches

“…The reason for using CHL-a and transparency is their wide application as indicators of the eutrophication and turbidity in aquatic ecosystems [6][7][8][9][10]. The accurate simulation and prediction of chlorophyll-a concentrations have become an important issue as it is considered to be a central metric for reservoirs eutrophication management [11]. In addition, transparency (Secchi depth) provides an estimate of the volume of the habitat of phytoplankton and the extent of the benthic habitat of primary productivity as well as turbidity [10,12,13].…”

Modeling Chlorophyll <formula formulatype="inline"> <tex Notation="TeX">$a$</tex> </formula> Concentration Affected by Artificial Upwelling in Qiandao Lake

“…Polat [13] demonstrated that the concentration of NO NO N, PO P, and SiO Si in surface water could significantly affect nutrient and Chl concentration. Wang et al [14] took 14 variables, including hydrological, meteorological, and physicochemical data, into account to simulate the Chl concentration in Lake Baiyangdian using wavelet analysis and an artificial neural network. It is noted that all these studies were based on a relatively long period of several years during which the data were gathered monthly.…”