Figure 1 - uploaded by Baofu Li
Content may be subject to copyright.
Location of the Hotan River Basin in the arid region of northwest China, showing sounding stations, as well as Wuluwati and Tongguziluoke hydrological stations.
Source publication
- [...]
We use data on the freezing level height (FLH) and summer runoff in the Hotan River, China, from 1960 to 2013, to analyse the nonlinear relationships of atmospheric and hydrological factors at different time scales, by employing three nonlinear decomposition methods. Six hybrid prediction models are established by combining linear regression and ba...
Contexts in source publication
Context 1
... Hotan River has a drainage area of 48 870 km 2 and is located south of the Tarim River Basin. It originates from the north slope of Kunlun Mountains and the Karakoram Mountains, and lies between the latitudes 34°52′ and 40°29′ N and longitudes 77°25′ and 81°43′E (Fig. 1). The Hotan River has two tributaries: the east one is the Yurungkash River, which has a length of 513 km, an average annual runoff of 2195 hm 3 , and hosts the Tongguziluoke hydrological station in the mountain pass; the west tributary is the Karakash River, which has a length of 808 km, an average annual runoff of 2151 hm 3 , and ...
Context 2
... for the ESMD-MLR hybrid model, followed by the EEMD-MLR hybrid model; the MLR and the WA-MLR models had the lowest correlations (Table 3). Moreover, the AIC value of the ESMD-MLR hybrid model was the lowest, followed by the EEMD-MLR hybrid model; the AIC values were highest for the MLR and WA-MLR models. The predictive QQ plot for these models (Fig. 10(a)) indicates that all four models were somewhat over-confident, particularly at the upper end of the distribution, during the calibration period. During the calibration and validation periods, the ESMD-MLR model had the highest Cronbach's α and NSE, and the lowest RMSE, indicating higher reliability. Clearly, the hybrid model improved ...
Context 3
... the simulation of extreme points by these three models requires further improvement. Figure 11 shows the results of hybrid prediction based on combination of three nonlinear decomposition methods with BPANN. Analysis of the correlation coefficients for the validation results (Table 4) indicates the correlation between the original and simulated series was greatest for the ESMD-BPANN hybrid model, followed by the EEMD-BPANN hybrid model. ...
Context 4
... was lowest for the ESMD-BPANN hybrid model, followed by the EEMD-BPANN hybrid model; the AIC of the BPANN alone and the WA-BPANN hybrid model were the highest. Figure 12 shows the predictive QQ plots for these models. These results show again that all four models were somewhat over-confident during the calibration and validation periods. ...
Context 5
... ESMD-BPANN hybrid model exhibited the greatest accuracy among all eight models that we examined to predict runoff variations in the Hotan River from 2014-2030 (Fig. 13). Our forecasts indicate that the future runoff will have significant fluctuations, and a trend for a slight increase from 2014-2030, at a rate of 12.4 hm 3 /year. This model forecasted low runoff values for 2014, 2017, 2024 and 2028, and high ones for 2018, 2023, 2029 and 2030. This indicates that the inter-annual variations of runoff ...
Context 6
... wavelet is predicated on a priori selection of basis functions that are either of infinite length or have fixed finite length, and may cause spurious oscillations (Ayenu-Prah and Attohokine 2009). However, EEMD has self-adaptability, and the decomposition results depend on the length of the data, not the number of (b) (a) Figure 10. Predictive QQ plots obtained based on the prediction distributions generated using the single MLR and the hybrid models of MLR combined with nonlinear decomposition methods for (a) the calibration period and (b) the validation period (2002-2013). ...
Similar publications
open access: https://link.springer.com/article/10.1007/s00410-020-1659-2
==============================================================
Supersaturation of H 2 O during magma ascent leads to degassing of melt by formation and growth of vesicles that may power explosive volcanic eruptions. Here, we present experiments to study the effect of initially...
A Ca(H2PO4)2/RM composite powder suppressant with core–shell structure was prepared with modified red mud (RM) as the carrier and Ca(H2PO4)2 as the loaded particles, using a solvent–antisolvent process, in an attempt to suppress aluminum dust explosion more effectively. The suppression effects of the Ca(H2PO4)2/RM composite powder suppressant for a...
A thermoplastic ABS and an aluminium alloy 6061-T6 were joined using friction lap welding (FLW). The joint characteristics were evaluated to investigate the effects of 6061-T6 surface and the welding parameters on the joint properties. ABS and 6061-T6 were joined via an interfacial MgO layer. The voids generated by thermal decomposition would affec...
Citations
... The SPEI merges the thermostability of the PDSI with the multi-time scale properties of the SPI and has a promising application potential SPEI combines the thermal stability of PDSI with the multi-time scale characteristics of SPI, which has great application potential in characterizing drought patterns (Taylor et al., 2012;Ayantobo et al., 2017;Tian et al., 2018;Zhao et al., 2017). Previous studies on the drought patterns in China have mostly focused on the spatio-temporal characteristics of droughts such as period, trends, frequency, mutation detection, and stage delineation (Yu et al., 2014;Wang et al., 2018;Han et al., 2021;Yue et al., 2021;Duan et al., 2019;Qin et al., 2019;Zhou et al., 2019). Due to its vast area, complex terrain, and distinct monsoon climate, China's drought patterns exhibit significant spatiotemporal heterogeneity . ...
... It decomposes the high-frequency IMF into significant variational patterns, effectively solving the problems of noise and non-stationary feature recognition in high-frequency IMF. Meanwhile, compared with a single ESMD (Qin et al. 2019b), EEMD (Wang et al. 2015), EMD (Huang et al. 2014), CEEMDAN, VMD decomposition, the quadratic decomposition model in this paper has higher prediction accuracy, which also indicates that quadratic decomposition can overcome the problem of low prediction accuracy caused by high-frequency components in a single decomposition. Secondly, LSSVM model optimized by HHO method is used to model the complex input-output relationship in each sub-component at different frequencies. ...
Accurate and reliable monthly runoff predictions are crucial for dispatching, allocation, and planning management of water resources. This research provides a hybrid forecasting model to increase the precision of monthly runoff predictions. Firstly, a series of intrinsic mode functions (IMF) and residual values are obtained from raw monthly runoff time series by applying complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN). Secondly, variational mode decomposition (VMD) is used to perform a secondary decomposition of high-frequency IMFs. Thirdly, to determine the input–output relationships for all IMFs, Harris Hawks Optimization (HHO) algorithm is used to optimize least squares support vector machine (LSSVM) model. Finally, each IMF output is superimposed and reconstructed to obtain the final result. Five evaluation indicators are utilized to evaluate the effectiveness of the proposed hybrid model on monthly runoff data from Manwan and Hongjiadu Hydropowers in China. MAE, RMSE, MAPE, NSEC, and R of CEEMDAN-VMD-HHO-LSSVM model are 103.25, 137.29, 10.84, 0.98, and 0.99 in Manwan Hydropower and 18.28, 23.58, 28.49, 0.97 and 0.98 in Hongjiadu Hydropower, respectively. The five performance evaluation indicators of the proposed model exhibit excellent results when compared to those of other benchmarking models, demonstrating that the secondary decomposition can successfully extract the complex runoff sequence information so as to significantly increase the hybrid model's prediction accuracy.
... Therefore, the performance of runoff prediction still has some room for improvement. At present, scholars have proposed a hybrid prediction model, which has better forecasting performance than a single prediction model and has become a new trend in hydrological prediction (Adnan et al., 2021;Qin et al., 2019). A hybrid prediction model is usually composed of two ways. ...
Reliable runoff prediction plays a significant role in reservoir scheduling, water resources management, and efficient utilization of water resources. To effectively enhance the prediction accuracy of monthly runoff series, a hybrid prediction model (TVF-EMD-SSA-ELM) combining time varying filtering (TVF) based empirical mode decomposition (EMD), salp swarm algorithm (SSA) and extreme learning machine (ELM) is proposed. Firstly, the monthly runoff series is decomposed into several sub-series using TVF-EMD. Secondly, SSA is used to optimize the input weights and hidden layer biases of the selected ELM model. Finally, the prediction results are generated by summing and reconstructing each sub-series based on the SSA optimized ELM model. This hybrid model is applied to the monthly runoff prediction of Manwan hydropower, Hongjiadu hydropower, and Yingluoxia hydrological station, and compared with back propagation (BP), ELM, SSA-ELM, PSO-ELM, GSA-ELM, TVF-EMD-ELM, EMD-SSA-ELM, extreme-point symmetric mode decomposition (ESMD)-SSA-ELM, wavelet decomposition (WD)-SSA-ELM and complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN)-SSA-ELM models. The prediction performance of various models is reflected by four evaluation indicators (R, NSEC, NRMSE, MAPE). Results reveal that the prediction effect of the ELM model is better than that of BP, the optimization accuracy of SSA is better than those of particle swarm optimization (PSO) and gravitational search algorithm (GSA), and the prediction accuracy of the hybrid TVF-EMD and SSA is better than that of only TVF-EMD or SSA. TVF-EMD-SSA-ELM model has the highest prediction accuracy. When compared with the single ELM model, it's NRMSE and MAPE at Manwan hydropower decrease by 84.4% and 72.38%, those of Hongjiadu hydropower decrease by 85.21% and 78.38%, and those of Yingluoxi hydrological station decrease by 68.42% and 39.51%, respectively. R and NSEC of the three sites are close to 1. Therefore, the proposed model provides a new method for the prediction of monthly runoff, and the results can provide a reference for the prediction of monthly runoff in the study area.
... responded significantly to the change of 08C isotherm height (Qin et al. 2019). The above analysis during summer explains why low correlations are found between meteorological drought and hydrological drought in the headstreams of TRB. ...
In the propagation from meteorological to hydrological drought, there are time-lag and step-abrupt effects, quantified in terms of propagation time and threshold, which play an important role in hydrological drought early warning. However, seasonal drought propagation time and threshold and their dynamics as well as the corresponding driving mechanism remain unknown in a changing environment. To this end, the standardized precipitation index (SPI) and standardized runoff index (SRI) were used respectively to characterize meteorological and hydrological droughts and to determine the optimal propagation time. Then, a seasonal drought propagation framework based on Bayesian network was proposed for calculating the drought propagation threshold with SPI. Finally, the seasonal dynamics and preliminary attribution of propagation characteristics were investigated based on the random forest model and correlation analysis. The results show that 1) relatively short propagation time (less than 9 months) and large propagation threshold (from −3.18 to −1.19) can be observed in the Toxkan River basins (subbasin II), especially for spring, showing low drought resistance; 2) drought propagation time shows an extended trend in most seasons, while the drought propagation threshold displays an increasing trend in autumn and winter in the Aksu River basin (subbasins I–II), and the opposite characteristics in the Hotan and Yarkant River basins (subbasins III–V); and 3) the impacts of precipitation, temperature, potential evapotranspiration, and soil moisture on drought propagation dynamics are inconsistent across subbasins and seasons, noting that reservoirs serve as a buffer to regulate the propagation from meteorological to hydrological droughts. The findings of this study can provide scientific guidelines for watershed hydrological drought early warning and risk management.
Significance Statement
The aim of this study is to better understand how the delayed and step-abrupt effects of propagation from meteorological drought to hydrological drought can be characterized through propagation time and threshold. These response indicators determine the resistance of a catchment to hydrological droughts and meteorological droughts. They can help water resources management agencies to mitigate hydrological droughts by taking measures such as water storage, increasing revenue, and reducing expenditure. The findings of this study can provide scientific guidelines for watershed hydrological drought early warning and risk management.
... In the last two decades, Artificial Intelligence has exhibited remarkable progress in modelling nonlinear hydrological processes (Yaseen et al. 2015). In recent years, there has been an increased interest in applying back propagation artificial neural networks (BPANN) in hydrological research (Liu et al. 2020;Qin et al. 2019;Yaseen et al. 2018), and specifically, in linking runoff to climate variability and human activities (Liu et al. 2010;Tang et al. 2014). Unlike hydrological simulation models, BPANN do not require detailed knowledge of the physical characteristics of a catchment. ...
... In simulation-based models, nonlinearity refers to the dynamical property such as nonlinear response of rainfall-runoff in a catchment (Botter et al. 2009;Minshall 1960;Sivapalan et al. 2002;Wang et al. 1981), while in data-driven models, nonlinearity refers to the dependence of statistical properties, such as nonlinear relationships between input and output data (Hsu et al. 1995;Shoaib et al. 2018;Solomatine and Dulal 2003;Yuan et al. 2018). There is also compelling evidence that the performance of BPANN can be improved by combining them with nonlinear decomposition techniques, such as wavelet analysis (Adamowski and Sun 2010;Kasiviswanathan et al. 2016;Yu et al. 2013) and ensemble empirical mode decomposition (Qin et al. 2019;Tan et al. 2018). ...
Understanding the contributions of potential drivers on runoff is essential for the sustainable management of water resources; however, the impacts of climate variability and human activities on runoff at inter-annual and inter-decadal scales have rarely been assessed quantitatively. To achieve this goal, this study develops a nonlinear hybrid model, which integrates extreme-point symmetric mode decomposition (ESMD), back propagation artificial neural networks (BPANN) and weights connection method. ESMD allows to separate the times series of drivers and runoff into different time scales. BPANN is then used to simulate the relation between the drivers and runoff at each time scale separately. Weights connection method is employed to quantify the impacts of climate variability and human activities on runoff. The performance of this proposed model is compared with multiple linear regression (MLR). The mountainous area of the Hotan River Basin is selected as case study area. Results reveal that runoff exhibits significant fluctuations at inter-annual (2 and 9 years) and inter-decadal (14 years) scales. Climate variables are responsible for 81% of the runoff variations, while human activities account for 8%. The nonlinear hybrid model substantially outperforms MLR in all performance measures. We attribute this improvement to the ability of the proposed model to represent nonlinear relations and to simulate the association between drivers and runoff at different time scales. For instance, water vapor affects runoff positively at the inter-annual time scale but negatively at the inter-decadal time scale. Such opposing relations cannot be represented by MLR or many other, more traditional methods.
... Wavelet transforms and neural networks were combined to predict monthly precipitation [15] and daily precipitation [16]. Extreme-point symmetric mode decomposition (ESMD) is a method to deal with non-stationary signals; Qin, et al. [17] used it to predict runoff. ...
It has become increasingly difficult in recent years to predict precipitation scientifically and accurately due to the dual effects of human activities and climatic conditions. This paper focuses on four aspects to improve precipitation prediction accuracy. Five decomposition methods (time-varying filter-based empirical mode decomposition (TVF-EMD), robust empirical mode decomposition (REMD), complementary ensemble empirical mode decomposition (CEEMD), wavelet transform (WT), and extreme-point symmetric mode decomposition (ESMD) combined with the Elman neural network (ENN)) are used to construct five prediction models, i.e., TVF-EMD-ENN, REMD-ENN, CEEMD-ENN, WT-ENN, and ESMD-ENN. The variance contribution rate (VCR) and Pearson correlation coefficient (PCC) are utilized to compare the performances of the five decomposition methods. The wavelet transform coherence (WTC) is used to determine the reason for the poor prediction performance of machine learning algorithms in individual years and the relationship with climate indicators. A secondary decomposition of the TVF-EMD is used to improve the prediction accuracy of the models. The proposed methods are used to predict the annual precipitation in Guangzhou. The subcomponents obtained from the TVF-EMD are the most stable among the four decomposition methods, and the North Atlantic Oscillation (NAO) index, the Nino 3.4 index, and sunspots have a smaller influence on the first subcomponent (Sc-1) than the other subcomponents. The TVF-EMD-ENN model has the best prediction performance and outperforms traditional machine learning models. The secondary decomposition of the Sc-1 of the TVF-EMD model significantly improves the prediction accuracy.
Reliable annual runoff prediction is crucial for efficient water resource planning. Therefore, this study proposes a hybrid model based on the combination of sand cat swarm optimization (SCSO), echo state network (ESN), gated recurrent unit (GRU), least squares method (LSM), and Markov chain (MC) models to improve the accuracy of annual runoff prediction. First, correlation analysis is conducted on multifactor data related to runoff to determine the input of the model. Second, the SCSO algorithm is used to optimize the parameters of the ESN and GRU models, and the SCSO-ESN and SCSO-GRU models are established. Next, the LSM is used to couple the prediction results of the SCSO-ESN and SCSO-GRU models to obtain the initial prediction results of the SCSO-ESN-GRU model. Finally, the initial prediction results are corrected for errors using MC to get the final prediction results. Two stations are selected as experimental stations, and five evaluation indicators are chosen to reflect the model's predictive performance at the experimental stations. The results show that the combined prediction model corrected by the MC achieved the optimal prediction performance at both experimental stations. This study emphasizes that using a combination prediction model based on MC correction can significantly improve the accuracy of prediction.
The destruction of the Aral Sea area constitutes one of the world's most infamous ecological disaster. However, the retreat of the Aral Sea has slowed down in recent years and the underlying reasons are not reported. In this work, based on the extreme-point symmetric mode decomposition (ESMD) method and the multiple linear regression model, we analyzed the changing of the Aral Sea from 1960 to 2018, and detected the time for slowdown of retreat, then explored the driving forces. The results show that the Aral Sea retreated rapidly from 1960 to 2004, and the shrinking rates of water surface area, water volume and water level were 1087.00 km²/year, 25.07 km³/year, and 0.56 m/year, respectively; the retreat has slowed since 2005, with the shrinking rates being 760.00 km²/year, 2.86 km³/year, and 0.38 m/year, respectively. At the same time, the area of water bodies surrounding the Aral Sea increased due to the agricultural drainage water. The oscillation periods of water level in the Aral Sea are 2.1a, 7.6a and 29.5a, of which 29.5a is the main period of oscillation. The trend residual RES indicates that water level shows a non-linear downward trend, and the degree of fluctuation has decreased significantly after 2005. The impact of human activities on the Aral Sea is more significant than that of climate change. Overall, the increased upstream runoff, reduced water withdrawal, and rise in water delivery to the Aral Sea has led to a slowing down of the sea's notorious shrinkage. The findings provide a scientific reference for the management and protection of the Aral Sea.
