Water temperature is a critical indicator and weathervane of aquatic ecosystems.However,the vast majority of rivers lack long-term continuous and complete water temperature datasets.In this study,ensemble models by co...Water temperature is a critical indicator and weathervane of aquatic ecosystems.However,the vast majority of rivers lack long-term continuous and complete water temperature datasets.In this study,ensemble models by combining NARX(nonlinear autoregressive network with exogenous inputs)and air2stream were used to reconstruct daily river water temperatures for 27 hydrological stations in the Odra River Basin,one of the largest river systems in Europe.For each hydrological station,both the NARX and air2stream models were calibrated and validated,and the better-performed model was selected to reconstruct daily river water temperatures from 1985 to 2022.The results showed that hybrid modeling by combining NARX and air2stream is promising for reconstructing daily river water temperatures.Based on the reconstructed dataset,annual and seasonal trends of water temperature and characteristics of river heatwaves were evaluated.The results indicated that annual river water temperatures showed a consistent warming trend over the past 40 years with an average warming rate of 0.315C/decade.Seasonal river water temperatures indicated that summer warms faster,followed by autumn and spring,and winter river water temperatures showed an insignificant warming trend.River heatwaves are increased in frequency,duration,and intensity in the Odra River Basin,and 6 out of 27 hydrological stations have river heatwaves categorized as‘severe’and‘extreme’,suggesting that mitigation measures are needed to reduce the impact of climate warming on aquatic systems.Moreover,results showed that air temperature is the major controller of river heatwaves,and river heatwaves tend to intensify with the warming of air temperatures.展开更多
基金the National Science Foundation of China(Grant No.42401572)Natural Science Foundation of the Jiangsu Higher Education Institutions of China(Grant No.22KJB170023)Postgraduate Research&Practice Innovation Program of Jiangsu Province(No.KYCX24_3758).
文摘Water temperature is a critical indicator and weathervane of aquatic ecosystems.However,the vast majority of rivers lack long-term continuous and complete water temperature datasets.In this study,ensemble models by combining NARX(nonlinear autoregressive network with exogenous inputs)and air2stream were used to reconstruct daily river water temperatures for 27 hydrological stations in the Odra River Basin,one of the largest river systems in Europe.For each hydrological station,both the NARX and air2stream models were calibrated and validated,and the better-performed model was selected to reconstruct daily river water temperatures from 1985 to 2022.The results showed that hybrid modeling by combining NARX and air2stream is promising for reconstructing daily river water temperatures.Based on the reconstructed dataset,annual and seasonal trends of water temperature and characteristics of river heatwaves were evaluated.The results indicated that annual river water temperatures showed a consistent warming trend over the past 40 years with an average warming rate of 0.315C/decade.Seasonal river water temperatures indicated that summer warms faster,followed by autumn and spring,and winter river water temperatures showed an insignificant warming trend.River heatwaves are increased in frequency,duration,and intensity in the Odra River Basin,and 6 out of 27 hydrological stations have river heatwaves categorized as‘severe’and‘extreme’,suggesting that mitigation measures are needed to reduce the impact of climate warming on aquatic systems.Moreover,results showed that air temperature is the major controller of river heatwaves,and river heatwaves tend to intensify with the warming of air temperatures.
