With the increasingly serious problem of surface water environmental safety, it is of great significance to study the changing trend of reservoir water quality, and it is necessary to establish a water quality prediction and early warning system for the management and maintenance of water resources. Aiming at the problem of water quality prediction in reservoirs, a CA-NARX algorithm is designed, which combines the improved dynamic clustering algorithm with the idea of machine learning and the forward dynamic regression neural network. The improved dynamic clustering algorithm is used to classify the eutrophication degree of waterbodies according to the total phosphorus and total nitrogen content. Considering four meteorological factors, air temperature, water temperature, water surface evaporation, and rainfall, synthetically for each water quality condition, the total phosphorus and total nitrogen in the waterbody are forecasted by an improved forward NARX dynamic regression neural network. Based on this, the CA-NARX prediction algorithm can realize short period water quality prediction. Compared with the traditional support vector regression machine model, improved GA-BP neural network, and exponential smoothing method, the CA-NARX model has the least prediction error.
● Increased DAAO offsets 3/4 of the decrease of DAAP in 2013–2020.● DAAO increases are mainly due to O3 concentration increase and population aging.● Health benefit from PM2.5 reduction after 2017 is larger than that before 2017.● Reducing PM2.5 concentration by 1% results in 0.6% reduction of DAAP.● Reducing O3 concentration by 1% results in 2% reduction of DAAO. PM2.5 concentration declined significantly nationwide, while O3 concentration increased in most regions in China in 2013–2020. Recent evidences proved that peak season O3 is related to increased death risk from non-accidental and respiratory diseases. Based on these new evidences, we estimate excess deaths associated with long-term exposure to ambient PM2.5 and O3 in China following the counterfactual analytic framework from Global Burden Disease. Excess deaths from non-accidental diseases associated with long-term exposure to ambient O3 in China reaches to 579 (95% confidential interval (CI): 93, 990) thousand in 2020, which has been significantly underestimated in previous studies. In addition, the increased excess deaths associated with long-term O3 exposure (234 (95% CI: 177, 282) thousand) in 2013–2020 offset three quarters of the avoided excess deaths (302 (95% CI: 244, 366) thousand) mainly due to PM2.5 exposure reduction. In key regions (the North China Plain, the Yangtze River Delta and the Fen-Wei Plain), the former is even larger than the latter, particularly in 2017–2020. Health benefit of PM2.5 concentration reduction offsets the adverse effects of population growth and aging on excess deaths attributed to PM2.5 exposure. Increase of excess deaths associated with O3 exposure is mainly due to the strong increase of O3 concentration, followed by population aging. Considering the faster population aging process in the future, collaborative control, and faster reduction of PM2.5 and O3 are needed to reduce the associated excess deaths. 相似文献