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.
ABSTRACT:The temporal and spatial trends of four climate extreme indices for Guangdong Province of China were calculated based on observed daily precipitation, daily maximum, and daily minimum temperatures at 24 weather stations as well as the frequency of typhoon events during the period of 1957-2013. An integrated extreme climatic index (IECI) was derived from four individual climate extreme indices (high temperature days (H td ), low temperature days (L td ), intensive precipitation days (I pd ) and number of typhoon events (TT)), considering their weights using an information theory model. A simple linear regression model was utilized to analyze the spatiotemporal trends of the climate extremes. The correlation analysis between the above extreme climatic indices and the socioeconomic losses [affected area of crops (AAC), direct losses of the economy (DLE), and affected population (AP)] was calculated. The results indicate that H td increased while L td decreased significantly at the 5% significance level. By contrast, there were no significant long-term changes in I pd and TT. The rate of change of IECI was 0.006 per decade and no long-term trend was detected in IECI. Spatially, a positive trend was observed in the Yuexi River Basin (YXRB) for I pd , while a negative trend was found in the East River Basin (ERB). L td followed an opposite spatial pattern to that of H td . Extreme temperature days occurred more frequently in the Pearl River Delta (PRD) than in other parts of Guangdong Province. Regions with positive IECI rates of change were mostly in the YXRB, the coastal area of the Yuedong River Basin (YDRB) and the northern and southern part of the ERB. The correlation coefficients between IECI and AAC, DLE, and AP are 0.375, 0.424 and 0.603, respectively. In general, IECI correlated more strongly with the loss indices caused by extreme climatic events than did the four individual extreme climatic indices.
The development of clean energy is of great importance in alleviating both the energy crisis and environmental pollution resulting from rapid global economic growth. Hydroelectric generation is considered climate benign, as it neither requires fossil carbon to produce energy nor emits large amounts of greenhouse gases (GHG), unlike conventional energy generation techniques such as coal and oil power plants. However, dams and their associated reservoirs are not entirely GHG-neutral and their classification as a clean source of energy requires further investigation. This study evaluated the environmental impact of the Xiajiang hydropower station based on life cycle assessment (LCA) according to the 2006 Intergovernmental Panel on Climate Change (IPCC) guidelines, focusing specifically on GHG emissions after the submersion of the reservoir. Results reveal that although hydropower is not as clean as we thought, it is still an absolute “low emissions” power type in China. The amount of GHG emissions produced by this station is 3.72 million tons with an emissions coefficient of 32.63 g CO2eq/kWh. This figure is lower than that of thermal power, thus implying that hydropower is still a clean energy resource in China. Our recommendations to further minimize the environmental impacts of this station are the optimization of relevant structural designs, the utilization of new and improved construction materials, and the extension of farmland lifting technology.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.