Frequency Analysis of the Nonstationary Annual Runoff Series Using the Mechanism-Based Reconstruction Method

Due to climate change and human activities, the statistical characteristics of annual runoff series of many rivers around the world exhibit complex nonstationary changes, which seriously impact the frequency analysis of annual runoff and are thus becoming a hotspot of research. A variety of nonstationary frequency analysis methods has been proposed by many scholars, but their reliability and accuracy in practical application are still controversial. The recently proposed Mechanism-based Reconstruction (Me-RS) method is a method to deal with nonstationary changes in hydrological series, which solves the frequency analysis problem of the nonstationary hydrological series by transforming nonstationary series into stationary Me-RS series. Based on the Me-RS method, a calculation method of design annual runoff under the nonstationary conditions is proposed in this paper and applied to the Jialu River Basin (JRB) in northern Shaanxi, China. From the aspects of rationality and uncertainty, the calculated design value of annual runoff is analyzed and evaluated. Then, compared with the design values calculated by traditional frequency analysis method regardless of whether the sample series is stationary, the correctness of the Me-RS theory and its application reliability is demonstrated. The results show that calculation of design annual runoff based on the Me-RS method is not only scientific in theory, but also the obtained design values are relatively consistent with the characteristics of the river basin, and the uncertainty is obviously smaller. Therefore, the Me-RS provides an effective tool for annual runoff frequency analysis under nonstationary conditions.

Hydrological time series prediction by extreme machine learning and sparrow search algorithm

In general, accurate hydrological time series prediction information is of great significance for the rational planning and management of water resource system. Extreme learning machine (ELM) is an effective tool proposed for the single-layer feedforward neural network in the regression and classification problems. However, the standard ELM model falls into local minimum with a high probability in hydrological prediction problems since the randomly assigned parameters (like input-hidden weights and hidden biases) often remain unchanged at the learning process. For effectively improving the prediction accuracy, this paper develops a hybrid hydrological forecasting model where the emerging sparrow search algorithm (SSA) is firstly used to determine the satisfying parameter combinations of the ELM model, and then the Moore-Penrose generalized inverse method is chosen to analytically obtain the weight matrix between the hidden layer and output layer. The proposed method is used to forecast the long-term daily runoff series collected from three real-world hydrological stations in China. Based on several performance evaluation indexes, the results show that the proposed method outperforms several ELM variants optimized by other evolutionary algorithms in both training and testing phases. Hence, an effective evolutionary machine learning tool is developed for accurate hydrological time series forecasting. HIGHLIGHT Hydrologic forecasting, sparrow search algorithm, extreme machine learning.

A Novel Runoff Forecasting Model Based on the Decomposition-Integration-Prediction Framework

Runoff forecasting is of great importance for flood mitigation and power generation plan preparation. To explore the better application of time-frequency decomposition technology in runoff forecasting and improve the prediction accuracy, this research has developed a framework of runoff forecasting named Decomposition-Integration-Prediction (DIP) using parallel-input neural network, and proposed a novel runoff forecasting model with Variational Mode Decomposition (VMD), Gated Recurrent Unit (GRU), and Stochastic Fractal Search (SFS) algorithm under this framework. In this model, the observed runoff series is first decomposed into several sub-series via the VMD method to extract different frequency information. Secondly, the parallel layers in the parallel-input neural network based on GRU are trained to receive the input samples of each subcomponent and integrate their output adaptively through the concatenation layers. Finally, the output of concatenation layers is treated as the final runoff forecasting result. In this process, the SFS algorithm was adopted to optimize the structure of the neural network. The prediction performance of the proposed model was evaluated using the historical monthly runoff data at Pingshan and Yichang hydrological stations in the Upper Yangtze River Basin of China, and seven various single and decomposition-based hybrid models were developed for comparison. The results show that the proposed model has obvious advantages in overall prediction performance, model training time, and multi-step-ahead prediction compared to several comparative methods, which is a reasonable and more efficient monthly runoff forecasting method based on time series decomposition and neural networks.

Wavelet Analysis of Rainfall and Runoff Multidecadal Time Series on Large River Basins in Western North Africa

This work is dedicated to the study of the spatio-temporal variability of climate in Morocco by the analysis of rainfall (gridded and gauged data) and runoff. The wavelet analysis method has been used in this study to compare the rainfall and runoff series and to show the major discontinuities identified in 1970, 1980, and 2000. Several modes of variability have been detected; this approach has been applied to show annual (1 year) and inter-annual modes (2–4 years, 4–8 years, 8–12/8–16 years, and 16–30 years), and some modes are specific to some stations. This analysis will be complemented by the gridded data covering the period from 1940 to 1999, which will allow for a better understanding of the spatial variability of the highlighted signals set, which identified frequencies at 1 year and 8–16 years, distinguished different time periods at each basin and identified three main discontinuities in 1970, 1980, and 2000. The contribution of climatic indices is important as it is between 55% and 80%.

A 500-year runoff reconstruction for European catchments

Since the beginning of this century, Europe has been experiencing severe drought events (2003, 2007, 2010, 2018, and 2019) which have had adverse impacts on various sectors, such as agriculture, forestry, water management, health, and ecosystems. During the last few decades, projections of the impact of climate change on hydroclimatic extremes were often capable of reproducing changes in the characteristics of these extremes. Recently, the research interest has been extended to include reconstructions of hydro-climatic conditions to provide historical context for present and future extremes. While there are available reconstructions of temperature, precipitation, drought indicators, or the 20th century runoff for Europe, long-term runoff reconstructions are still lacking (e.g, monthly or daily runoff series for short periods are commonly available). Therefore, we considered reconstructed precipitation and temperature fields for the period between 1500 and 2000 together with reconstructed scPDSI, natural proxy data, and observed runoff over 14~European catchments to calibrate and validate the semi-empirical hydrological model GR1A and two data-driven models (Bayesian recurrent and long short-term memory neural network). The validation of input precipitation fields revealed an underestimation of the variance across most of Europe. On the other hand, the data-driven models have been proven to correct this bias in many cases, unlike the semi-empirical hydrological model GR1A. The comparison to observed historical runoff data has shown a good match between the reconstructed and observed runoff and between the runoff characteristics, particularly deficit volumes. The reconstructed runoff is available via figshare, an open source scientific data repository under the DOI https://doi.org/10.6084/m9.figshare.15178107, (Sadaf et al., 2021).

Runoff Prediction Model Based on Improved Convolutional Neural Network

Due to the influence of human regulation and storage factors, the runoff series monitored at the hydropower stations often show the characteristics of non-periodicity, which makes runoff prediction simulation difficult. This paper attempts to construct an improved one-dimensional convolutional neural network (CNN) model for runoff prediction simulation. The improved CNN model consists of two convolution layers and a full connection layer and uses LeakyRelu as the activation function. Based on the historical rainfall and runoff data of the ZheXi reservoir in Hunan Province, this paper uses the improved CNN model to simulate runoff prediction and compares the results with the traditional ANN model and the traditional CNN model. The results show that the improved CNN model is superior to the traditional ANN model and the traditional CNN model. It proves that the improved CNN model is suitable for the non-periodic runoff prediction simulation, and it can avoid the data problems such as gradient disappearance that may occur in the traditional neural network model.

Analysis on the Variation of Hydro-Meteorological Variables in the Yongding River Mountain Area Driven by Multiple Factors

In recent decades, strong human activities have not only brought about climate change including both global warming and shifts in the weather patterns but have also caused anomalous variations of hydrological elements in different basins all around the world. Studying the mechanisms and causes of these hydrological variations scientifically is the basis for the management of water resources and the implementation of ecological protection. Therefore, taking the Yongding River mountain area as a representative watershed in China, the changes of different observed and simulated hydro-meteorological variables and their possible causes are analyzed on an inter-annual scale based on ground based observations and remotely sensed data of hydrology, meteorology and underlying surface characteristics from 1956 to 2016. The results show that the annual natural runoff of Guanting hydrological station in the main stream of the Yongding River, Cetian hydrological station and Xiangshuibao hydrological station in the tributary of the Yongding River all have a significant decreasing trend and abrupt changes, and all the abrupt change points of the annual natural runoff series of the three hydrological stations appear in the early 1980s. On the inter-annual scale, the water balance model with double parameters is unable to effectively simulate the natural surface runoff after the abrupt change points. The annual average precipitation after the abrupt change points decreases by no more than 10%, compared with that before the abrupt change points. However, the precipitation from July to August, which is the main runoff-production period, decreases by more than 25%, besides the intra-annual temporal distribution of precipitation becoming uniform and a significant decrease in effective rainfall, which is the source of the runoff. Meanwhile, the NDVI in the basin show an increasing trend, while the groundwater level and land water storage decrease significantly. These factors do not lead only to the continuous reduction of the annual natural runoff in the Yongding River mountain area from 1956 to 2016, but also result in significant changes of the hydro-meteorological relationship in the basin.