Binbin Huang

To improve the precision of water quality forecasting, the variational mode decomposition (VMD) method was used to denoise the total nitrogen (TN) and total phosphorus (TP) time series and obtained several high- and low-frequency components at four online surface water quality monitoring stations in Poyang Lake. For each of the aforementioned high-frequency components, a long short-term memory (LSTM) network was introduced to achieve excellent prediction results. Meanwhile, a novel metaheuristic optimization algorithm, called the chaos sparrow search algorithm (CSSA), was implemented to compute the optimal hyperparameters for the LSTM model. For each low-frequency component with periodic changes, the multiple linear regression model (MLR) was adopted for rapid and effective prediction. Finally, a novel combined water quality prediction model based on VMD-CSSA-LSTM-MLR (VCLM) was proposed and compared with nine prediction models. Results indicated that (1), for the three standalone models, LSTM performed best in terms of mean absolute error (MAE), mean absolute percentage error (MAPE), and the root mean square error (RMSE), as well as the Nash–Sutcliffe efficiency coefficient (NSE) and Kling–Gupta efficiency (KGE). (2) Compared with the standalone model, the decomposition and prediction of TN and TP into relatively stable sub-sequences can evidently improve the performance of the model. (3) Compared with CEEMDAN, VMD can extract the multiscale period and nonlinear information of the time series better. The experimental results proved that the averages of MAE, MAPE, RMSE, NSE, and KGE predicted by the VCLM model for TN are 0.1272, 8.09%, 0.1541, 0.9194, and 0.8862, respectively; those predicted by the VCLM model for TP are 0.0048, 10.83%, 0.0062, 0.9238, and 0.8914, respectively. The comprehensive performance of the model shows that the proposed hybrid VCLM model can be recommended as a promising model for online water quality prediction and comprehensive water environment management in lake systems.

Runoff is the key driving factor of the Ganjiang River ecosystem. Human activities such as reservoir construction have greatly changed the state of runoff. In order to analyze the influence of Ganjiang Reservoir on the hydrological regime, the following paper is based on the daily precipitation data of 53 rainfall stations in Ganjiang River Basin from 1959 to 2016, and the daily runoff data of three stations in Dongbei, Ji’an, and Waizhou from 1959 to 2016. The Mann–Kendall test (MK) was used to analyze the trend of precipitation and runoff in Ganjiang River Basin. The Sliding t-Test (ST) was used to determine the abrupt change time of runoff in flood season within typical cross-sections of upper, middle, and lower reaches of Ganjiang River Basin, Ji’an, and Waizhou. Indicators of hydrological change (IHA), range of variability approach (RVA), and other methods were used to analyze the changes of 32 hydrological indicators in Ganjiang River Basin. The results showed that (1) The annual and flood season precipitation in Ganjiang River Basin increased from 1992 to 2016, but it did not reach a significant level. The change of annual runoff at Dongbei and Waizhou Stations was the same as that of the annual precipitation in Ganjiang River Basin. The runoff of Dongbei Station in flood season decreased from 1986 to 2016, and the runoff of Waizhou Railway Station in flood season decreased from 2008 to 2016. It showed that precipitation had a great influence on annual runoff, and human activities made the annual runoff distribution process more uniform; (2) The abrupt changes of runoff in flood season at three hydrological stations in Ganjiang River Basin occurred in 1991, and reached a significant level of 0.01; (3) There were five hydrological indicators of Dongbei Station which had reached height change. The change degree of low (l) pulse duration was −92.24%, the change degree of high (h) pulse count was −86.8%, the change degree of flow rise rate was 87.06%, the change degree of fall rate was −92.24%, and the change degree of number of reversals was −100%. Four hydrological indicators of Ji’an Station had reached high change degree, the count and duration of high pulse changes were −73.33% and −73.65%, the change degree of fall rate was −79%, and the change degree of number of reversals was −100%. Waizhou Station did not reach the high change indicator. The hydrological regime of the upper and middle reaches of Ganjiang River has changed greatly, while the hydrological regime of the lower reaches has changed little. The hydrological regime in the upper and middle reaches of Ganjiang River Basin has been highly changed by human activities such as dam construction. The change of hydrological conditions in the upper and middle reaches of Ganjiang River Basin may reduce the area of aquatic organisms’ habitat, be harmful to the spawning, migration, and survival of aquatic organisms, reduce the interception of organic matter in floodplains, and increase the drought pressure of plants. The reservoir ecological operation of rivers with numerous reservoirs should be considered, joint reservoir dispatching schemes should be formulated for the study area so as to maximize the comprehensive benefits. This study provides a reference for water resources management and reservoir operation in Ganjiang River Basin. The next step is to use a habitat model to simulate the habitat of Ganjiang River Basin.