Comparison of an artificial neural network and a conceptual rainfall–runoff model in the simulation of ephemeral streamflow

ABSTRACT

The rainfall–runoff process is governed by parameters that can seldom be measured directly for use with distributed models, but are rather inferred by expert judgment and calibrated against historical records. Here, a comparison is made between a conceptual model (CM) and an artificial neural network (ANN) for their ability to efficiently model complex hydrological processes. The Sacramento soil moisture accounting model (SAC-SMA) is calibrated using a scheme based on genetic algorithms and an input delay neural network (IDNN) is trained for variable delays and hidden layer neurons which are thoroughly discussed. The models are tested for 15 ephemeral catchments in Crete, Greece, using monthly rainfall, streamflow and potential evapotranspiration input. SAC-SMA performs well for most basins and acceptably for the entire sample with R² of 0.59–0.92, while scoring better for high than low flows. For the entire dataset, the IDNN improves simulation fit to R² of 0.70–0.96 and performs better for high flows while being outmatched in low flows. Results show that the ANN models can be superior to the conventional CMs, as parameter sensitivity is unclear, but CMs may be more robust in extrapolating beyond historical record limits and scenario building.

EDITOR M.C. Acreman; ASSOCIATE EDITOR not assigned     

Copula entropy coupled with artificial neural network for rainfall–runoff simulation

The rainfall–runoff relationship is not only nonlinear and complex but also difficult to model. Artificial neural network (ANN), as a data-driven technique, has gained significant attention in recent years and has been shown to be an efficient alternative to traditional methods for hydrological modeling. However, for different input combinations, ANN models can yield different results. Therefore, input variables and ANN types need to be carefully considered, when using an ANN model for stream flow forecasting. This study proposes the copula-entropy (CE) theory to identify the inputs of an ANN model. The CE theory permits to calculate mutual information (MI) and partial MI directly which avoids calculating the marginal and joint probability distributions. Three different ANN models, namely multi-layer feed (MLF) forward networks, radial basis function networks and general regression neural network, were applied to predict stream flow of Jinsha River, China. Results showed that the inputs selected by the CE method were better than those by the traditional linear correlation analysis, and the MLF ANN model with the inputs selected by CE method obtained the best predicted results for the Jinsha River at Pingshan gauging station.     

Prediction and modelling of rainfall–runoff during typhoon events using a physically-based and artificial neural network hybrid model

Abstract

The accurate prediction of hourly runoff discharge in a watershed during heavy rainfall events is of critical importance for flood control and management. This study predicts n-h-ahead runoff discharge in the Sandimen basin in southern Taiwan using a novel hybrid approach which combines a physically-based model (HEC-HMS) with an artificial neural network (ANN) model. Hourly runoff discharge data (1200 datasets) from seven heavy rainfall events were collected for the model calibration (training) and validation. Six statistical indicators (i.e. mean absolute error, root mean square error, coefficient of correlation, error of time to peak discharge, error of peak discharge and coefficient of efficiency) were employed to evaluate the performance. In comparison with the HEC-HMS model, the single ANN model, and the time series forecasting (ARMAX) model, the developed hybrid HEC-HMS–ANN model demonstrates improved accuracy in recursive n-h-ahead runoff discharge prediction, especially for peak flow discharge and time.     

Simulation and control of the linked systems of water quantity–water quality–socio-economics in the Huaihe River basin

Abstract

This work makes explicit an algebraic expression giving the matrix of transient influence coefficients associated with a one-dimensional semi-confined aquifer model. The domain studied is divided into a series of connected and completely mixed compartments over which the governing equation is discretized. The discrete equations obtained are solved for the compartmental hydraulic head and used to derive the algebraic expression in question. The basic properties of the so-called algebraic influence coefficients are investigated. In particular, their consistency with the exact Green function is highlighted. Finally, the newly derived influence coefficients are applied to a simplified aquifer system in order to formulate and solve the problem of identifying illegal groundwater pumping.     

Climate and hydrological changes in the Ob River Basin during 1936–2017

Changes in the hydrological regimes of Arctic rivers could affect the thermohaline circulation of the Arctic Ocean. In this study, we analysed spatiotemporal variations in temperature and precipitation in the Ob River Basin regions during 1936–2017 based on data from the Global Precipitation Climatology Center. Changes in discharge and response to climate change were examined based on monthly observed data during the same period. It is indicated the Ob River Basin experienced significant overall rapid warming and wetting (increased precipitation) in the study period, with average rates of 0.20°C (10 year⁻¹) and 5.3 mm (10 year⁻¹), respectively. The annual spatial variations of temperature and precipitation showed different scales in different regions. The discharge in spring and winter significantly increased at a rate of 384.1 and 173.1 m³/s (10 year⁻¹), respectively. Hydrograph separation indicated infiltration and supported that deep flow paths increased the contribution of groundwater to base flow. Meanwhile, the variation of the ratio of Q_max/Q_min suggested that the basin storage and the mechanism of discharge generation have significantly changed. The hydrological processes were influenced by changes of permafrost in a certain in the Ob River Basin. An increase in the recession coefficient (RC) implies that the permafrost degradation in the basin due to climate warming affected hydrological processes in winter. Permafrost degradation affected the Q_max/Q_min more significantly in the warm season than RC due to the enhanced infiltration that converted more surface water into groundwater in the cold season. The impact of precipitation on discharge, including surface flow and base flow, was more significant than temperature at the annual and seasonal scales in the Ob River Basin. The base flow was more obviously influenced by temperature than surface flow. The results of this study are significant for analyses of the basin water budget and freshwater input to the Arctic Ocean.     

Trend and change-point analyses of streamflow and sediment discharge in the Yellow River during 1950–2005

Abstract

The objectives of this work are: (a) to statistically test and quantify the decreasing trends of streamflow and sediment discharge of the Yellow River in China during 1950–2005, (b) to identify change points or transition years of the decreasing trends, and (c) to diagnose whether the decreasing trends were caused by precipitation changes or human intervention, or both. The results show that significant decreasing trends in annual streamflow and sediment discharge have existed since the late 1950s at three stations located in the upper, middle, and lower reaches of the Yellow River (P?=?0.01). Change-point analyses further revealed that transition years existed and that rapid decline in streamflow and sediment discharge began in 1985 in most parts of the basin (P?=?0.05). Adoption of conservation measures in the 1980s and 1990s corroborates the identified transition years. Double-mass curves of precipitation vs streamflow (sediment) for the periods before and after the transition years show remarkable decreases in proportionality of streamflow (sediment) generation. All percentiles of streamflow and sediment discharge after the transition years showed rapid reduction. In the absence of significantly decreasing precipitation trends, it is concluded that the decreasing trends were very likely caused by human intervention. Relative to the period before the transition, human intervention during 1985–2005 reduced cumulative streamflow by 13.5, 14.3 and 24.6% and cumulative sediment discharge by 29.0, 24.8 and 26.5%, at Toudaoguai, Huayuankou and Lijin, respectively, showing the quantitative conservation effect in the basin.

Citation Gao, P., Zhang, X.-C., Mu, X.-M., Wang, F., Li, R. & Zhang, X. (2010) Trend and change-point analyses of streamflow and sediment discharge in the Yellow River during 1950–2005. Hydrol. Sci. J. 55(2), 275–285.     

Rainfall–runoff–inundation analysis of the 2010 Pakistan flood in the Kabul River basin

Abstract

Pakistan has suffered a devastating flood disaster in 2010. In the Kabul River basin (92 605 km²), large-scale riverine and flash floods caused destructive damage with more than 1100 casualties. This study analysed rainfall–runoff and inundation in the Kabul River basin with a newly developed model that simulates the processes of rainfall–runoff and inundation simultaneously based on two-dimensional diffusion wave equations. The simulation results showed a good agreement with an inundation map produced based on MODIS for large-scale riverine flooding. In addition, the simulation identified flash flood-affected areas, which were confirmed to be severely damaged based on a housing damage distribution map. Since the model is designed to be used even immediately after a disaster, it can be a useful tool for analysing large-scale flooding and to provide supplemental information to agencies for relief operations.

Editor Z.W. Kundzewicz

Citation Sayama, T., Ozawa, G., Kawakami, T., Nabesaka, S. and Fukami, K., 2012. Rainfall–runoff–inundation analysis of the 2010 Pakistan flood in the Kabul River basin. Hydrological Sciences Journal, 57 (2), 298–312.     

Clustering spatial–temporal precipitation data using wavelet transform and self-organizing map neural network

A data analysis method is proposed to cluster and explore spatio-temporal characteristics of the 22 years of precipitation data (1982–2003) for Taiwan. The wavelet transform self-organizing map (WTSOM) framework combines the wavelet transform (WT) and a self-organizing map (SOM) neural network. WT is used to extract dynamic and multiscale features of the non-stationary precipitation time-series, and SOM is applied to objectively identify spatially homogeneous clusters on the high-dimensional wavelet-transformed feature space. Haar and Morlet wavelets are applied in the data preprocessing stage to preserve the desired characteristics of the precipitation data. A two-level SOM neural network is applied to identify clusters in the wavelet space in the clustering stage. The performance of clustering is evaluated using silhouette coefficients. The results indicate that singularities or sharp transitions are more significant than changes in the periodicity or data structure in the spatial–temporal precipitation data. The WTSOM results show that six clusters are optimal for both Haar and Morlet wavelet functions, but their corresponding geographic locations are different. The geographic locations of clusters based on the Haar wavelet, which captures the occurrence of extreme hydrological events, appear in blocks while those classified by the Morlet wavelet, which indicates periodicity changes and describes fine structures, appear in strips that cross the island of Taiwan. Principal component analysis is applied to the precipitation data of each cluster. The first principal components explain 62–90% of the total variation of data. Characteristics of precipitation data for each cluster are explored using scalogram analysis. The results show that both extreme hydrological events and periodicity changes appear in the spatial and temporal precipitation data but with different characteristics for each cluster. Recognizing homogeneous hydrologic regions and identifying the associated precipitation characteristics improves the efficiency of water resources management in adapting to climate change, preventing the degradation of the water environment, and reducing the impact of climate-induced disasters. Measures for countering the stress of precipitation variation for water resources management are provided.     

Solar–terrestrial,ionospheric and natural phenomena studies using the South America VLF network (SAVNET)

The South America VLF Network (SAVNET) has been installed in April 2009, and is composed of eight tracking receivers spread over South America, in Brazil, Peru and Argentina, and the Antarctica Peninsula. SAVNET is monitoring the properties of subionospheric propagating waves that reveal changes of the electrical properties of the ionospheric diurnal D-region or nocturnal E-region. In this paper, we will show the ability of the diagnostic obtained by SAVNET to discuss the monitoring of the solar activity on short timescales related to ionization due to solar flares. The sensitivity of flare detection as a function of the solar activity level will be discussed. On longer timescales related to the solar cycle, SAVNET is also able to provide information on the solar Lyman-α radiation. Finally we show that the VLF technique is well suited to search for of seismic-electromagnetic effects, and to provide a genuine diagnostic of high-energy astrophysical phenomena.     

Comparison of Pb(Ⅱ) and Cd(Ⅱ) micro-interfacial adsorption on fine sediment in the Pearl River Basin,China

The complex micro-interfacial interaction theories of heavy metal ions such as Pb(Ⅱ)and Cd(Ⅱ)adsorption on fine sediment in aqueous solution were not systematically investigated.The aim of this work was to reflect the micro-interfacial adsorption characteristics.Sediment samples were collected from an estuary.The Isothermal and kinetics adsorption experiment were done to acquire the data.Isothermal,kinetics,film diffusion and intraparticle diffusion models were adopted to fit the adsorption experimental data.The results indicated that the Langmuir,Freundlich and Temkin models were suitable for analyzing the isothermal experimental data.The maximum adsorption capacities of Pb(Ⅱ)and Cd(Ⅱ)on the sediment were 1.1377 and 0.9821 mg·g-1,respectively.The qm and KL of the Langmuir model,Kf and nF of the Freundlich model,and b and A of the Temkin model all exhibited a power function relationship with the initial adsorbate concentration.The pseudo-second-order model provided a better fit for the experimental kinetics data compared with the fit of the pseudo-first-order and Elovich models.The pseudo-second-order parameters k2 and qe of Pb(Ⅱ)and qe of Cd(Ⅱ)both had a power function relationship with adsorption time,additionally,the k2 of Cd(Ⅱ)had an exponential function relationship with adsorption time.The liquid-film diffusion parameters kfd of Pb(Ⅱ)and Cd(Ⅱ)were 0.0569 and 0.1806 min
1,respectively.The intraparticle diffusion parameter kid values of Pb(Ⅱ)and Cd(Ⅱ)were 0.0055 mg$g
1$min1/2 and 0.0049 mg$g
1$min1/2,respectively.The physical significance of the model parameters showed that Pb(Ⅱ)adsorption on sediment was stronger than Cd(Ⅱ).The results of this study provided a theoretical reference for the micro-interfacial mechanism of heavy metal ion adsorption on sediment.     

“Playing the game”, identity and perception-of-the-other in water cooperation in the Jordan River Basin

ABSTRACT

The concept of Integrated Water Resources Management (IWRM) has enjoyed immense popularity and thus has been the preferred approach for river basin management. IWRM generally has a strong focus on rational choice, based on a technocratic conceptual interpretation of the conventional hydrological cycle. However, uncritical acceptance of IWRM runs the risk of blinding policy makers and academics for the defining impact of context, socio-cultural, political, historical and cognitive dimensions in water cooperation. Human behaviour in water cooperation was tested and observed during eight experiments with the Jordan River Basin Boardgame Exercise (JRBBE) played with respondent groups from inside and outside the Jordan River Basin. The experiments consisted of one control group outside the basin and seven respondent groups both outside and inside the basin. This article argues that the role of identities, beliefs and perception-of-the-other, should be taken more into account in order to develop successful and socio-political sustainable river basin management.

EDITOR D. Koutsoyiannis; ASSOCIATE EDITOR not assigned     

Physical–biological coupling in the Pearl River Estuary

The Pearl River Estuary is a subtropical estuary and the second largest in China based on discharge volume from the Pearl River. Processes in the estuary vary spatially and temporally (wet vs dry season). In the dry season at the head of the estuary, hypoxic and nearly anoxic conditions occur and NH₄ reaches >600 μM, NO₃ is ∼300 μM and nitrite is ∼60 μM indicating that nitrification and denitrification may be important dry season processes in the region extending 40 km upstream of the Humen outlet. There are very few biological studies conducted in this upper section of the estuary in either the dry or wet seasons and hence there is a need for further research in this region of the river. In the wet season, the salinity wedge extends to the Hongqimen outlet and oxygen is low (35–80% saturation). Nitrate is ∼100 μM, silicate ∼140 μM; and phosphate is relatively low at ∼0.5 μM, yielding an N:P ratio up to ∼200:1 in summer. Nutrients decrease in the lower estuary and primary productivity may become potentially P-limited. Eutrophication is not as severe as one would expect from the nutrient inputs from the Pearl River and from Hong Kong's sewage discharge. This estuary shows a remarkable capacity to cope with excessive nutrients. Physical processes such as river discharge, tidal flushing, turbulent dispersion, wind-induced mixing, and estuarine circulation play an important role in controlling the production and accumulation of algal blooms and the potential occurrence of hypoxia. Superimposed on the physical processes of the estuary are the chemical and biological processes involved in the production of the bloom. For example, the 100N:1P ratio indicates that P potentially limits the amount of algal biomass (and potential biological oxygen demand) in summer. While extended periods of hypoxia are rare in Hong Kong waters, episodic events have been reported to occur during late summer due to factors such as low wind, high rainfall and river discharge which result in strong density stratification that significantly dampens vertical mixing processes. Nutrient loads are likely to change over the next several decades and monitoring programs are essential to detect the response of the ecosystem due to the future changes in nutrient loading and the ratio of nutrients.     

Evolution mechanisms of the intraseasonal oscillation associated with the Yangtze River Basin flood in 1998

Early in the1970s,Madden and Julian[1,2]first re-vealed the existence of eastward propagation of the intraseasonal(or30-60-day)oscillation(ISO)in the zonal wind fields over the tropics.Later on,the northward propagation of the ISO activities over the Indian Ocean was discovered by Yasunari[3,4],which accounts for the seasonal variations of the Indian summer monsoon.Similar studies were carried out on the low-frequency oscillation activities related to the ENSO and the East Asian summer …     

Ecological–Geochemical Conditions of Surface Water and Groundwater and Estimation of the Anthropogenic Effect in the Basin of the Ganjiang River

Water Resources - Data of studies of 2013–2019 were used to assess the current environmental-geochemical conditions of surface water and groundwater in the basin of the Ganjiang River, the...     

The FAM(Fuzzy Asociative Memory)neural network model and its application in earthquake prediction

ＴｈｅＦＡＭ（ＦｕｚｚｙＡｓｏｃｉａｔｉｖｅＭｅｍｏｒｙ）ｎｅｕｒａｌｎｅｔｗｏｒｋｍｏｄｅｌａｎｄｉｔｓａｐｐｌｉｃａｔｉｏｎｉｎｅａｒｔｈｑｕａｋｅｐｒｅｄｉｃｔｉｏｎＷＥＩＷＡＮＧ１）（王炜）ＧＥＮＧＦＥＮＧＷＵ２）（吴耿锋）ＢＩＮＳＨＵＨ...     

Comparison of Pb(Ⅱ) and Cd(Ⅱ) micro-interfacial adsorption on ?ne sediment in the Pearl River Basin,China

The complex micro-interfacial interaction theories of heavy metal ions such as Pb(II) and Cd(II)adsorption on fine sediment in aqueous solution were not systematically investigated. The aim of this work was to reflect the micro-interfacial adsorption characteristics. Sediment samples were collected from an estuary. The Isothermal and kinetics adsorption experiment were done to acquire the data.Isothermal, kinetics, film diffusion and intraparticle diffusion models were adopted to fit the adsorption experimental data. The results indicated that the Langmuir, Freundlich and Temkin models were suitable for analyzing the isothermal experimental data. The maximum adsorption capacities of Pb(II) and Cd(II)on the sediment were 1.1377 and 0.9821 mg·g_(-1), respectively. The q_m and K_L of the Langmuir model, K_f and n_F of the Freundlich model, and b and A of the Temkin model all exhibited a power function relationship with the initial adsorbate concentration. The pseudo-second-order model provided a better fit for the experimental kinetics data compared with the fit of the pseudo-first-order and Elovich models.The pseudo-second-order parameters k_2 and q_e of Pb(II) and q_e of Cd(II) both had a power function relationship with adsorption time, additionally, the k_2 of Cd(II) had an exponential function relationship with adsorption time. The liquid-film diffusion parameters k_(fd) of Pb(II) and Cd(II) were 0.0569 and 0.1806 min_(-1), respectively. The intraparticle diffusion parameter k_(id) values of Pb(II) and Cd(II) were0.0055 mg·g_(-1)·min_(1/2) and 0.0049 mg·g_(-1)min_(1/2), respectively. The physical significance of the model parameters showed that Pb(II) adsorption on sediment was stronger than Cd(II). The results of this study provided a theoretical reference for the micro-interfacial mechanism of heavy metal ion adsorption on sediment.     

Crustal velocity and strain rate fields in the Balearic Islands based on continuous GPS time series from the XGAIB network (2010–2013)

In this paper, we present a first estimation, using the GIPSY-OASIS software, of the crustal velocity and strain rate fields in the Balearic Islands (Spain), based on continuous GPS observations from the XGAIB network spanning the period 2010–2013. The XGAIB network consists of nine permanent, widely distributed stations that have operated continuously since 2010. In this paper, we describe the XGAIB network and the CGPS data processing and present our principle results in terms of the position time series and velocities of all of the sites, which were observed for more than three and a half years. In addition, strain tensors were estimated from the velocity field to obtain the first realistic crustal deformation model of the archipelago. The strains exhibit gradual variation across the Balearic Islands, from WNW–ESE extension in the southwest (Ibiza and Formentera) to NW–SE compression in the northeast (Menorca). These results constitute an advance in our knowledge of the tectonics of the western Mediterranean region.     

New fuzzy neural network–Markov model and application in mid- to long-term runoff forecast

ABSTRACT

In this paper, a mid- to long-term runoff forecast model is developed using an ideal point fuzzy neural network–Markov (NFNN-MKV) hybrid algorithm to improve the forecasting precision. Combining the advantages of the new fuzzy neural network and the Markov prediction model, this model can solve the problem of stationary or volatile strong random processes. Defined error statistics algorithms are used to evaluate the performance of models. A runoff prediction for the Si Quan Reservoir is made by utilizing the modelling method and the historical runoff data, with a comprehensive consideration of various runoff-impacting factors such as rainfall. Compared with the traditional fuzzy neural networks and Markov prediction models, the results show that the NFNN-MKV hybrid algorithm has good performance in faster convergence, better forecasting accuracy and significant improvement of neural network generalization. The absolute percentage error of the NFNN-MKV hybrid algorithm is less than 7.0%, MSE is less than 3.9, and qualification rate reaches 100%. For further comparison of the proposed model, the NFNN-MKV model is employed to estimate (training and testing for 120-month-ahead prediction) and predict river discharge for 156 months at Weijiabao on the Weihe River in China. Comparisons among the results of the NFNN-MKV model, the WNN model and the SVR model indicate that the NFNN-MKV model is able to significantly increase prediction accuracy.

Editor D. Koutsoyiannis; Associate editor Y. Gyasi-Agyei     

Spatial distribution and temporal variation of reference evapotranspiration during 1961–2006 in the Yellow River Basin,China

Abstract

To explore the spatial and temporal variations of the reference evapotranspiration (ET_ref) is helpful to understand the response of hydrological processes to climate changes. In this study, ET_ref was calculated by the Penman-Monteith method (P-M method) using air temperature, wind speed, relative humidity and sunshine hours at 89 meteorological stations during 1961–2006 in the Yellow River Basin (YRB), China. The spatial distribution and temporal variations of ET_ref were explored by means of the kriging method, the Mann-Kendall (M-K) method and the linear regression model, and the causes for the variations discussed. The contribution of main meteorological variables to the variations of ET_ref was explored. From the results we found that: (1) the spatial distributions of ET_ref display seasonal variation, with similar spatial patterns in spring, summer and autumn; (2) temporal trends for ET_ref showed large variation in the upper, middle and lower regions of the basin, most of the significant trends (P?=?0.05) were detected in the middle and lower regions, and, in particular, the upward and downward trends were mainly detected in the middle region and lower region of the basin, respectively; and (3) sensitivity analysis identified the most sensitive variable for ET_ref as relative humidity, followed by air temperature, sunshine hours and wind speed at the basin scale.

Citation Yang, Zhifeng, Liu, Qiang & Cui, Baoshan (2011) Spatial distribution and temporal variation of reference evapotranspiration during 1961–2006 in the Yellow River Basin, China. Hydrol. Sci. J. 56(6), 1015–1026.     

Hydrochemical Regime in Riverine Aqual Complexes: Case Study of the Small Il’d River (Rybinsk Reservoir Basin)

Water Resources - The results of studying the space and time dynamics of the hydrochemical regime in discrete aquatic areas of a riverine aquatic–territorial complex of a small river over...