Cluster regression model and level fluctuation features of Van Lake, Turkey

Lake water levels change under the influences of natural and/or anthropogenic environmental conditions. Among these influences are the climate change, greenhouse effects and ozone layer depletions which are reflected in the hydrological cycle features over the lake drainage basins. Lake levels are among the most significant hydrological variables that are influenced by different atmospheric and environmental conditions. Consequently, lake level time series in many parts of the world include nonstationarity components such as shifts in the mean value, apparent or hidden periodicities. On the other hand, many lake level modeling techniques have a stationarity assumption. The main purpose of this work is to develop a cluster regression model for dealing with nonstationarity especially in the form of shifting means. The basis of this model is the combination of transition probability and classical regression technique. Both parts of the model are applied to monthly level fluctuations of Lake Van in eastern Turkey. It is observed that the cluster regression procedure does preserve the statistical properties and the transitional probabilities that are indistinguishable from the original data.     

Implications for the water level change triggered moderate (M ≥ 4.0) earthquakes in Lake Van basin, Eastern Turkey

The water level in Lake Van has shown alternating rises and decreases in history, causing economical, environmental and social problems over the littoral area. The water level changes were obtained to be in the order of 100 m between 18000 and 1000 B.C., in the order of 10 m between 1000 B.C. and 500 A.D. and relatively stable and fluctuating in the order of a few metres during the past 1500 years. The most recent change of the water level took place between 1987 and 1996, during which the water level increased episodically about 2 m and its altitude changed from approximately 1648.3 m to about 1650.2 m. All these changes were mainly related to climate changes. In this study, the water level changes in the lake after 1860 are compared with the seismic activity of faults lying close to the basin. Temporal correlations of seismicity with the water level changes are very persuasive and dramatic, indicating hydrogeological triggering of the earthquakes. This study shows that 14 M ≥ 5.0 earthquakes and increasing number of 4.0 ≤ M < 5.0 earthquakes accompanied or followed the dramatic (about 1 m or larger) changes of the annual mean of the water level in the lake and that there was a tendency of M ≥ 4 earthquakes to occur between November and February, during which the lake level is low within a year.     

Short-term water quality variable prediction using a hybrid CNN–LSTM deep learning model

Stochastic Environmental Research and Risk Assessment - Water quality monitoring is an important component of water resources management. In order to predict two water quality variables, namely...     

Multiple model combination methods for annual maximum water level prediction during river ice breakup

The Athabasca River is the largest unregulated river in Alberta, Canada, with ice jams frequently occurring in the vicinity of Fort McMurray. Modelling tools are desired to forecast ice‐related flood events. Multiple model combination methods can often obtain better predictive performances than any member models due to possible variance reduction of forecast errors or correction of biases. However, few applications of this method to river ice forecasting are reported. Thus, a framework of multiple model combination methods for maximum breakup water level (MBWL) Prediction during river ice breakup is proposed. Within the framework, the member models describe the relations between the MBWL (predicted variable) and their corresponding indicators (predictor variables); the combining models link the relations between the predicted MBWL by each member model and the observed MBWL. Especially, adaptive neuro‐fuzzy inference systems, artificial neural networks, and multiple linear regression are not only employed as member models but also as combining models. Simple average methods (SAM) are selected as the basic combining model due to simple calculations. In the SAM, an equal weight (1/n) is assigned to n member models. The historical breakup data of the Athabasca River at Fort McMurray for the past 36 years (1980 to 2015) are collected to facilitate the comparison of models. These models are examined using the leave‐one‐out cross validation and the holdout validation methods. A SAM, which is the average output from three optimal member models, is selected as the best model as it has the optimal validation performance (lowest average squared errors). In terms of lowest average squared errors, the SAM improves upon the optimal artificial neural networks, adaptive neuro‐fuzzy inference systems, and multiple linear regression member models by 21.95%, 30.97%, and 24.03%, respectively. This result sheds light on the effectiveness of combining different forecasting models when a scarce river ice data set is investigated. The indicators included in the SAM may indicate that the MBWL is affected by water flow conditions just after freeze‐up, overall freezing conditions during winter, and snowpack conditions before breakup.     

Developing a novel hybrid model for seismic loss prediction of regional-scale buildings

Bulletin of Earthquake Engineering - Seismic loss prediction of regional-scale buildings provides key information for disaster management. However, previous seismic loss prediction models ignored...     

Adaptive neuro-fuzzy inference system for prediction of water level in reservoir

Accurate prediction of the water level in a reservoir is crucial to optimizing the management of water resources. A neuro-fuzzy hybrid approach was used to construct a water level forecasting system during flood periods. In particular, we used the adaptive network-based fuzzy inference system (ANFIS) to build a prediction model for reservoir management. To illustrate the applicability and capability of the ANFIS, the Shihmen reservoir, Taiwan, was used as a case study. A large number (132) of typhoon and heavy rainfall events with 8640 hourly data sets collected in past 31 years were used. To investigate whether this neuro-fuzzy model can be cleverer (accurate) if human knowledge, i.e. current reservoir operation outflow, is provided, we developed two ANFIS models: one with human decision as input, another without. The results demonstrate that the ANFIS can be applied successfully and provide high accuracy and reliability for reservoir water level forecasting in the next three hours. Furthermore, the model with human decision as input variable has consistently superior performance with regard to all used indexes than the model without this input.     

Application of wavelet-artificial intelligence hybrid models for water quality prediction: a case study in Aji-Chay River,Iran

The accuracy of Artificial Neural Network (ANN), Adaptive Neuro-Fuzzy Inference System (ANFIS), wavelet-ANN and wavelet-ANFIS in predicting monthly water salinity levels of northwest Iran’s Aji-Chay River was assessed. The models were calibrated, validated and tested using different subsets of monthly records (October 1983 to September 2011) of individual solute (Ca²⁺, Mg²⁺, Na⁺, SO₄ ^2? and Cl^?) concentrations (input parameters, meq L^?1), and electrical conductivity-based salinity levels (output parameter, µS cm^?1), collected by the East Azarbaijan regional water authority. Based on the statistical criteria of coefficient of determination (R²), normalized root mean square error (NRMSE), Nash–Sutcliffe efficiency coefficient (NSC) and threshold statistics (TS) the ANFIS model was found to outperform the ANN model. To develop coupled wavelet-AI models, the original observed data series was decomposed into sub-time series using Daubechies, Symlet or Haar mother wavelets of different lengths (order), each implemented at three levels. To predict salinity input parameter series were used as input variables in different wavelet order/level-AI model combinations. Hybrid wavelet-ANFIS (R² = 0.9967, NRMSE = 2.9 × 10^?5 and NSC = 0.9951) and wavelet-ANN (R² = 0.996, NRMSE = 3.77 × 10^?5 and NSC = 0.9946) models implementing the db4 mother wavelet decomposition outperformed the ANFIS (R² = 0.9954, NRMSE = 3.77 × 10^?5 and NSC = 0.9914) and ANN (R² = 0.9936, NRMSE = 3.99 × 10^?5 and NSC = 0.9903) models.     

Application of a spreadsheet hydrological model for computing the long-term water balance of Lake Awassa,Ethiopia

Abstract

The water balance of the closed freshwater Lake Awassa was estimated using a spreadsheet hydrological model based on long-term monthly hydrometeorological data. The model uses monthly evaporation, river discharge and precipitation data as input. The net groundwater flux is obtained from model simulation as a residual of other water balance components. The result revealed that evaporation, precipitation, and runoff constitute 131, 106 and 83 × 10⁶ m³ of the annual water balance of the lake, respectively. The annual net groundwater outflow from the lake to adjacent basins is 58 × 10⁶ m³. The simulated and recorded lake levels fit well for much of the simulation period (1981–1999). However, for recent years, the simulated and recorded levels do not fit well. This may be explained in terms of the combined effects of land-use change and neotectonism, which have affected the long-term average water balance. With detailed long-term hydrogeological and meteorological data, investigation of the subsurface hydrodynamics, and including the effect of land-use change and tectonism on surface water and groundwater fluxes, the water balance model can be used efficiently for water management practice. The result of this study is expected to play a positive role in future sustainable use of water resources in the catchment.     

Implementation of online model updating in hybrid simulation

Hybrid simulation combines numerical and experimental methods for cost‐effective, large‐scale testing of structures under simulated earthquake loading. Structural system level response can be obtained by expressing the equation of motion for the combined experimental and numerical substructures, and solved using time‐stepping integration similar to pure numerical simulations. It is often assumed that a reliable model exists for the numerical substructures while the experimental substructures correspond to parts of the structure that are difficult to model. A wealth of data becomes available during the simulation from the measured experiment response that can be used to improve upon the numerical models, particularly if a component with similar structural configuration and material properties is being tested and subjected to a comparable load pattern. To take advantage of experimental measurements, a new hybrid test framework is proposed with an updating scheme to update the initial modeling parameters of the numerical model based on the instantaneously‐measured response of the experimental substructures as the test progresses. Numerical simulations are first conducted to evaluate key algorithms for the selection and calibration of modeling parameters that can be updated. The framework is then expanded to conduct actual hybrid simulations of a structural frame model including a physical substructure in the laboratory and a numerical substructure that is updated during the tests. The effectiveness of the proposed framework is demonstrated for a simple frame structure but is extendable to more complex structural behavior and models. Copyright © 2013 John Wiley & Sons, Ltd.     

人类活动对青海湖水位下降的影响

青海湖是我国最大的内陆湖泊,位于青藏高原的东北隅。近三十年来由于自然要素和人为活动的影响,湖周生态环境急剧退化,湖水位下降达3.35m,湖面收缩约300多km~2。根据调查研究以及其他方面的资料。青海湖多年平均亏水量4.36×10~8m~3,而人为活动耗水量占亏水量的8.7％。仅占湖面蒸发量的1％。所以,人为耗水与湖水位波动无明显相关,湖水位下降虽然是综合效应,但主导因素是气候变化,并导致湖周生态环境的恶化。     

Screening level ecological risk assessment for synthetic musks in surface water of Lake Taihu, China

A total of thirty-three surface water samples were collected from Meiliang Bay, Gonghu Bay and Xukou Bay of Lake Taihu, and analyzed for synthetic musks, including 1,3,4,6,7,8-hexahydro-4,6,6,7,8,8-hexamethylcyclopenta-[γ]-2-benzopyrane (HHCB), 7-acetyl-1,1,3,4,4,6-hexamethyl-1,2,3,4-tetrahydronaphthalene (AHTN), 1-tert-butyl-3,5-dimethyl-2,5-dinitro-4-acetylbenzene (MK) and 1-tert-butyl-3,5-dimethyl-2,4,6-trinitrobenzene (MX). Ecological risks of these compounds were characterized by hazard quotient (HQ) method due to a lack of sufficient available toxicity data of synthetic musks. HHCB was the main synthetic musk detected in Lake Taihu, followed by AHTN, MK, and MX. The risk assessment results indicate that low ecological risks were posed by HHCB and total synthetic musks, and even lower risks posed by other synthetic musks in the worst case; much lower ecological risks were caused by both individual and total synthetic musks in the general case. The combined ecological risk from total synthetic musks calculation suggests that the combined ecological risk from all four synthetic musks was expected to be slightly higher than for the individual musks due to their joint action. The HQ spatial distribution maps show that several hot-spot areas were mainly around the river inlets to Lake Taihu, indicating that synthetic musks may be transported to Lake Taihu with municipal sewage and industrial wastewater from surrounding areas. However, the ecological risks in hot-spot areas posed by individual and total synthetic musks were still acceptable.     

Neural network and wavelet conjunction model for modelling monthly level fluctuations in Turkey

This paper proposes the application of a conjunction model (neuro‐wavelet) for forecasting monthly lake levels. The neuro‐wavelet (NW) conjunction model is improved combining two methods, discrete wavelet transform and artificial neural networks. The application of the methodology is presented for the Lake Van, which is the biggest lake in Turkey, and Lake Egirdir. The accuracy of the NW model is investigated for 1‐ and 6‐month‐ahead lake level forecasting. The root mean square errors, mean absolute relative errors and determination coefficient statistics are used for evaluating the accuracy of NW models. The results of the proposed models are compared with those of the neural networks. In the 1‐month‐ahead lake level forecasting, the NW conjunction model reduced the root mean square errors and mean absolute relative errors by 87–34% and 86–31% for the Van and Egirdir lakes, respectively. In the 6‐month‐ahead lake level forecasting, the NW conjunction model reduced the root mean square errors and mean absolute relative errors by 34–48% and 30‐46% for the Van and Egirdir lakes, respectively. The comparison results indicate that the suggested model could significantly increase the short‐ and long‐term forecast accuracy. Copyright © 2009 John Wiley & Sons, Ltd.     

A hybrid artificial neural network-numerical model for ground water problems

Numerical models constitute the most advanced physical-based methods for modeling complex ground water systems. Spatial and/or temporal variability of aquifer parameters, boundary conditions, and initial conditions (for transient simulations) can be assigned across the numerical model domain. While this constitutes a powerful modeling advantage, it also presents the formidable challenge of overcoming parameter uncertainty, which, to date, has not been satisfactorily resolved, inevitably producing model prediction errors. In previous research, artificial neural networks (ANNs), developed with more accessible field data, have achieved excellent predictive accuracy over discrete stress periods at site-specific field locations in complex ground water systems. In an effort to combine the relative advantages of numerical models and ANNs, a new modeling paradigm is presented. The ANN models generate accurate predictions for a limited number of field locations. Appending them to a numerical model produces an overdetermined system of equations, which can be solved using a variety of mathematical techniques, potentially yielding more accurate numerical predictions. Mathematical theory and a simple two-dimensional example are presented to overview relevant mathematical and modeling issues. Two of the three methods for solving the overdetermined system achieved an overall improvement in numerical model accuracy for various levels of synthetic ANN errors using relatively few constrained head values (i.e., cells), which, while demonstrating promise, requires further research. This hybrid approach is not limited to ANN technology; it can be used with other approaches for improving numerical model predictions, such as regression or support vector machines (SVMs).     

FEUWAnet: a multi-box water level and lateral exchange model for riparian wetlands

Riparian wetlands as typical aquatic-terrestrial interfaces control, in a very specific way, nonpoint water and related chemical fluxes exchanging between catchment areas to their respective water systems (streams, lakes). The existing groundwater and soilwater flow models reveal gaps in dealing with the complex behaviour of processes and the considerable spatial and temporal heterogeneity of riparian wetlands. Based on long-term experience gained through field observations and the interpretation of model produced data, a multi-box aggregation of processes which determines lateral as well as vertical flows and, as a whole, water balance, is used to discretise a generic riparian wetland transect situated between an upland aquifer and a receiving water body.

The resulting mathematical model, FEUWAnet, endowed also with an original methodology to adapt parameters, has been applied to a riparian alder wetland adjacent to Lake Belau (northern Germany). Results of simulations illustrate a good fit between calculated water levels and observed values and an accordance of calculated water balance to previous independent evaluations. This confirms that the sound simplifications of real situations performed by the FEUWAnet mathematical model are a promising way to deal with hydrological complexity of riparian zones. Moreover, FEUWAnet permits, to a certain extent, one to unravel the spatial heterogeneity and temporal variation of lateral (from catchment area to water systems) and vertical (from canopy to groundwater zone) water fluxes typical of riparian ecosystems: this is the necessary step to undertake when developing integrated models capable of assessing the effectiveness of riparian systems in controlling the fluxes of nonpoint pollution discharging in the open water bodies.     

多目标驱动的太湖调度水位研究

太湖是流域洪水集散地、水资源调配中心,也是长三角水生态环境的晴雨表,其水位高低影响防洪、供水、水生态、水环境等系统功能,使得太湖面临统筹调度问题日益凸显。本文以太湖为主要研究对象,基于多年实测数据,采用数理统计、河网水动力模型计算,分析流域降雨、进出湖水量和水生态环境演变规律及其与太湖水位的互馈关系,综合考虑不同调度期流域防洪、供水、水生态、水环境目标及其承受风险的时空差异性,优化太湖调度水位,并在此基础上提出太湖调度功能区划图。结果表明,在设计洪水和供水条件下,通过调度水位调整,统筹调控流域水工程,前期预降太湖水位,后期适抬太湖水位,实现太湖多目标调度,可有效保障流域防洪、供水和航运安全,改善河湖生态环境,共绘美丽太湖。     

鄱阳湖水位变化规律的研究

根据都昌水位站１９５３￣１９９２年水位资料,对鄱阳湖水位的基本特征、退水过程及演变趋势进行了统计分析,在此基础上指出鄱阳湖开发利用中面临的主要问题和水位变化对鄱阳湖生态环境可能造成的影响。     

抚仙湖历史水位反演与未来30年水位变化预测

在极端气候事件频发和人类活动加剧的背景下,抚仙湖水位波动显著,尤其是2009—2012年极端干旱事件的发生,使抚仙湖平均水位（1721.31 m）低于法定最低水位（1721.65 m）,给生态环境安全带来严重威胁.因此,找到合适有效的湖泊水位模拟方法,对气候变化影响下的未来水位进行预测,并做好相应的应对准备,对湖泊生态系统的保护至关重要.本文运用DYRESM水动力模型对抚仙湖1959—2050年水位进行了模拟.因抚仙湖流域尚无长时间序列的历史水文观测数据,故利用模型和水量补偿法对抚仙湖入湖水量进行反推,构建了降水量-入湖水量的回归方程,并通过有效的实测入湖水量和水位数据,对回归方程的精度进行了检验.利用全球气候模式BCC-CSM2-MR中SSP245和SSP585两种情景提供的未来气候预估数据,运用DYRESM预测了抚仙湖2021—2050年水位变化趋势.结果表明：（1）构建的DYRESM水动力模型和降水-入湖水量回归方程精度较高,模型结果能很好地反映抚仙湖水位的年际和年内变化趋势,且能有效捕捉到抚仙湖的水位峰值.（2）在SSP245和SSP585两种情景下,抚仙湖2021—2050年多年平均水位分别为1722.98和1723.93 m,较1959—2017年平均水位1721.77 m分别升高1.21和2.16 m.两种情景下抚仙湖未来水位均有部分时段超过法定最高蓄水位（1723.35 m）,但均高于法定最低水位.因此,未来气候变化对抚仙湖水量的影响有限,并不会导致水位过低,当水位超过法定最高蓄水位时,可通过控制出流闸门将水位调节在合理范围内.     

A neural network model for predicting aquifer water level elevations

Artificial neural networks (ANNs) were developed for accurately predicting potentiometric surface elevations (monitoring well water level elevations) in a semiconfined glacial sand and gravel aquifer under variable state, pumping extraction, and climate conditions. ANNs "learn" the system behavior of interest by processing representative data patterns through a mathematical structure analogous to the human brain. In this study, the ANNs used the initial water level measurements, production well extractions, and climate conditions to predict the final water level elevations 30 d into the future at two monitoring wells. A sensitivity analysis was conducted with the ANNs that quantified the importance of the various input predictor variables on final water level elevations. Unlike traditional physical-based models, ANNs do not require explicit characterization of the physical system and related physical data. Accordingly, ANN predictions were made on the basis of more easily quantifiable, measured variables, rather than physical model input parameters and conditions. This study demonstrates that ANNs can provide both excellent prediction capability and valuable sensitivity analyses, which can result in more appropriate ground water management strategies.     

Evaporation estimation models for Lake Eğirdir,Turkey

Lake E?irdir is located in the Lakes District in southwestern Turkey and it is the second largest freshwater resource lake. Evaporation is an important parameter in hydrological and meteorological practical studies. This study has three objectives: (1) to develop models for the estimation of daily evaporation using measured data from the automated GroWeather meteorological station located near Lake E?irdir; (2) to compare the evaporation models with the classical Penman approach; (3) to evaluate the potential of each model. The comparisons are based on daily and monthly available data from 2001 and 2002. The evaporation estimation models (EEMs) developed in this paper have lower mean absolute errors and higher coefficient of determination R² values than the Penman method. In order to evaluate the potential of the EEMs, daily evaporation values are calculated by the Priestley–Taylor, Brutsaert–Stricker, de Bruin, Makkink and Hamon methods. The EEMs are statistically indistinguishable from the classical methods on the basis of the parameters of mean, standard deviation, etc. In the evaluation of daily and monthly values, the relative error percentage for daily evaporation has lower values than for monthly evaporation. It can be seen that the EEMs help in calculating daily evaporation rather than monthly. Final evaluation and comparison indicate that there is a good agreement between the results of EEMs and the Penman approach than with the classical methods. Copyright © 2006 John Wiley & Sons, Ltd.     

洞庭湖生态水位及其保障研究

湖泊生态水位是维持湖泊生态系统健康的重要因素.基于洞庭湖城陵矶、杨柳潭、南咀3个水文站1959-2016年日平均水位序列进行分析,采用Mann-Kendall法、累积距平法和滑动T检验法综合确定洞庭湖水位变异时间节点,结合生态水位年内展布法以及IHA-RVA法,计算分析湖泊最小和适宜生态水位,并且采用Tennant法进行合理验证,在此基础上对水文变异前、后湖泊生态水位保障度进行研究.研究结果表明:(1)洞庭湖城陵矶和杨柳潭水文站年均水位呈上升趋势,而且城陵矶站水位上升趋势显著,南咀站年均水位呈显著下降趋势.(2)洞庭湖3个典型水文站水位年际变化突变年份为2003年,突变年份基本上与三峡工程蓄水时间相符.(3)城陵矶、南咀和杨柳潭年均最小生态水位分别为21.41、28.95和27.84 m,分别占多年平均水位的86.3%、95.9%和95.7%,城陵矶、南咀和杨柳潭年均适宜生态水位分别为23.29、29.51和28.36 m,分别占多年平均水位的93.9%、97.8%和97.5%,生态水位计算结果考虑了天然湖泊水位年内丰枯变化,满足了湖泊生态目标需求.(4)洞庭湖最低生态水位保障程度较高,基本能达到80%以上,但适宜生态水位保障程度相对较低,其中2003年以后洞庭湖10月和11月生态水位保障程度显著下降,与上游水利工程蓄水有关,建议在此期间采取调度措施适当增加洞庭湖水量,以保障湖泊生态系统的健康与生物多样性.