首页 | 本学科首页   官方微博 | 高级检索  
相似文献
 共查询到20条相似文献，搜索用时 31 毫秒
1.
Özgür Kişi 《水文研究》2009,23(14):2081-2092
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.  相似文献   

2.
This paper reports on an evaluation of the use of artificial neural network (ANN) models to forecast daily flows at multiple gauging stations in Eucha Watershed, an agricultural watershed located in north‐west Arkansas and north‐east Oklahoma. Two different neural network models, the multilayer perceptron (MLP) and the radial basis neural network (RBFNN), were developed and their abilities to predict stream flow at four gauging stations were compared. Different scenarios using various combinations of data sets such as rainfall and stream flow at various lags were developed and compared for their ability to make flow predictions at four gauging stations. The input vector selection for both models involved quantification of the statistical properties such as cross‐, auto‐ and partial autocorrelation of the data series that best represented the hydrologic response of the watershed. Measured data with 739 patterns of input–output vector were divided into two sets: 492 patterns for training, and the remaining 247 patterns for testing. The best performance based on the RMSE, R2 and CE was achieved by the MLP model with current and antecedent precipitation and antecedent flow as model inputs. The MLP model testing resulted in R2 values of 0·86, 0·86, 0·81, and 0·79 at the four gauging stations. Similarly, the testing R2 values for the RBFNN model were 0·60, 0·57, 0·58, and 0·56 for the four gauging stations. Both models performed satisfactorily for flow predictions at multiple gauging stations, however, the MLP model outperformed the RBFNN model. The training time was in the range 1–2 min for MLP, and 5–10 s for RBFNN on a Pentium IV processor running at 2·8 GHz with 1 MB of RAM. The difference in model training time occurred because of the clustering methods used in the RBFNN model. The RBFNN uses a fuzzy min‐max network to perform the clustering to construct the neural network which takes considerably less time than the MLP model. Results show that ANN models are useful tools for forecasting the hydrologic response at multiple points of interest in agricultural watersheds. Copyright © 2008 John Wiley & Sons, Ltd.  相似文献   

3.
Özgür Kişi 《水文研究》2008,22(20):4142-4152
This paper proposes the application of a neuro‐wavelet technique for modelling monthly stream flows. The neuro‐wavelet model is improved by combining two methods, discrete wavelet transform and multi‐layer perceptron, for one‐month‐ahead stream flow forecasting and results are compared with those of the single multi‐layer perceptron (MLP), multi‐linear regression (MLR) and auto‐regressive (AR) models. Monthly flow data from two stations, Gerdelli Station on Canakdere River and Isakoy Station on Goksudere River, in the Eastern Black Sea region of Turkey are used in the study. The comparison results revealed that the suggested model could increase the forecast accuracy and perform better than the MLP, MLR and AR models. Copyright © 2008 John Wiley & Sons, Ltd.  相似文献   

4.
Historical changes in the level of Lake Bosumtwi, Ghana, have been simulated using a catchment‐scale hydrological model in order to assess the importance of changes in climate and land use on lake water balance on a monthly basis for the period 1939–2004. Several commonly used models for computing evaporation in data‐sparse regions are compared, including the Penman, the energy budget, and the Priestley–Taylor methods. Based on a comparison with recorded lake level variations, the model with the energy‐budget evaporation model subcomponent is most effective at reproducing observed lake level variations using regional climate records. A sensitivity analysis using this model indicates that Lake Bosumtwi is highly sensitive to changes in precipitation, cloudiness and temperature. However, the model is also sensitive to changes in runoff related to vegetation, and this factor needs to be considered in simulating lake level variations. Both interannual and longer‐term changes in lake level over the last 65 years appear to have been caused primarily by changes in precipitation, though the model also suggests that the drop in lake level over the last few decades has been moderated by changes in cloudiness and temperature over that time. Based on its effectiveness at simulating the magnitude and rate of lake level response to changing climate over the historical record, this model offers a potential future opportunity to examine the palaeoclimatic factors causing past lake level fluctuations preserved in the geological record at Lake Bosumtwi. Copyright © 2006 John Wiley & Sons, Ltd.  相似文献   

5.
Abstract

There is a continuing effort to advance the skill of long-range hydrological forecasts to support water resources decision making. The present study investigates the potential of an extended Kalman filter approach to perform supervised training of a recurrent multilayer perceptron (RMLP) to forecast up to 12-month-ahead lake water levels and streamflows in Canada. The performance of the RMLP was compared with the conventional multilayer perceptron (MLP) using suites of diagnostic measures. The results of the forecasting experiment showed that the RMLP model was able to provide a robust modelling framework capable of describing complex dynamics of the hydrological processes, thereby yielding more accurate and realistic forecasts than the MLP model. The performance of the method in the present study is very promising; however, further investigation is required to ascertain the versatility of the approach in characterizing different water resources and environmental problems.

Citation Muluye, G. Y. (2011) Improving long-range hydrological forecasts with extended Kalman filters. Hydrol. Sci. J. 56(7), 1118–1128.  相似文献   

6.
ABSTRACT

Accurate runoff forecasting plays a key role in catchment water management and water resources system planning. To improve the prediction accuracy, one needs to strive to develop a reliable and accurate forecasting model for streamflow. In this study, the novel combination of the adaptive neuro-fuzzy inference system (ANFIS) model with the shuffled frog-leaping algorithm (SFLA) is proposed. Historical streamflow data of two different rivers were collected to examine the performance of the proposed model. To evaluate the performance of the proposed ANFIS-SFLA model, six different scenarios for the model input–output architecture were investigated. The results show that the proposed ANFIS-SFLA model (R2 = 0.88; NS = 0.88; RMSE = 142.30 (m3/s); MAE = 88.94 (m3/s); MAPE = 35.19%) significantly improved the forecasting accuracy and outperformed the classic ANFIS model (R2 = 0.83; NS = 0.83; RMSE = 167.81; MAE = 115.83 (m3/s); MAPE = 45.97%). The proposed model could be generalized and applied in different rivers worldwide.  相似文献   

7.
ABSTRACT

Nowadays, mathematical models are widely used to predict climate processes, but little has been done to compare the models. In this study, multiple linear regression (MLR), multi-layer perceptron (MLP) network and adaptive neuro-fuzzy inference system (ANFIS) models were compared for precipitation forecasting. The large-scale climate signals were considered as inputs to the applied models. After selecting the most effective climate indices, the effects of large-scale climate signals on the seasonal standardized precipitation index (SPI) of the Maharlu-Bakhtaran catchment, Iran, simultaneously and with a delay, was analysed using a cross-correlation function. Hence, the SPI time series was forecasted up to four time intervals using MLR, MLP and ANFIS. The results showed that most of the indices were significant with SPI of different lag times. Comparison of the SPI forecast results by MLR, MLP and ANFIS models showed better performance for the MLP network than the other two models (RMSE = 0.86, MAE = 0.74 for the first step ahead of SPI forecasting).
Editor D. Koutsoyiannis; Associate editor F. Pappenberger  相似文献   

8.
Integrated dynamic water and chloride balance models with a catchment‐scale hydrological model (PRMS) are used to investigate the response of a terminal tropical lake, Lake Abiyata, to climate variability and water use practices in its catchment. The hydrological model is used to investigate the response of the catchment to different climate and land‐use change scenarios that are incorporated into the lake model. Lake depth–area–volume relationships were established from lake bathymetries. Missing data in the time series were filled using statistical regression techniques. Based on mean monthly data, the lake water balance model produced a good agreement between the simulated and observed levels of Lake Abiyata for the period 1968–83. From 1984 onwards the simulated lake level is overestimated with respect to the observed one, while the chloride concentration is largely underestimated. This discrepancy is attributed to human use of water from the influent rivers or directly from the lake. The simulated lake level and chloride concentration are in better agreement with observed values (r2 = 0·96) when human water use for irrigation and salt exploitation are included in the model. A comparison of the simulation with and without human consumption indicates that climate variability controls the interannual fluctuations and that the human water use affects the equilibrium of the system by strongly reducing the lake level. Sensitivity analysis based on a mean climatic year showed that, after prolonged mean climatic conditions, Lake Abiyata reacts more rapidly to an abrupt shift to wetter conditions than to dry conditions. This study shows the significant sensitivity of the level and salinity of the terminal Lake Abiyata to small changes in climate or land use, making it a very good ‘recorder’ of environmental changes that may occur in the catchment at different time scales. Copyright © 2004 John Wiley & Sons, Ltd.  相似文献   

9.
The effects of climate change have a substantial influence on the extremely vulnerable hydrologic environment of the Tibetan Plateau. The estimation of alpine inland lake water storage variations is essential to modeling the alpine hydrologic process and evaluating water resources. Due to a lack of historical hydrologic observations in this remote and inaccessible region, such estimations also fill a gap in studies on the continuous inter‐annual and seasonal changes in the inland lake water budget. Using Lake Siling Co as a case study, we derived a time‐series of lake surface extents from MODIS imagery, and scarce lake water level data from the satellite altimetry of two sensors (ICESat/GLAS and ENVISAT RA‐2) between 2001 and 2011. Then, based on the fact that the rise in lake water levels is tightly dependent on the expansion of the lake extent, we established an empirical model to simulate a continuous lake water level dataset corresponding to the lake area data during the lake's unfreezing period. Consequently, from three dimensions, the lake surface area, water level and water storage variations consistently revealed that Lake Siling Co exhibited a dramatic trend to expand, particularly from 2001 to 2006. Based on the statistical model and lake area measurements from Landsat images since 1972, the extrapolated lake water level and water storage indicate that the lake has maintained a continual expansion process and that the cumulative water storage variations during 1999–2011 account for 66.84% of the total lake water budget (26.87 km3) from 1972 to 2011. Copyright © 2013 John Wiley & Sons, Ltd.  相似文献   

10.
Mediterranean lake–wetland systems are threatened by climate change and intensive human impacts. Individual lake responses to these threats are poorly known but urgently required to steer preservation strategies. The dramatic water-level fall (~8 m since 1987) of Lake Megali Prespa endangers this global biodiversity hotspot and the wider catchment’s water resources. Annual lake fluctuations are found to be strongly related to wet-season (Oct.–Apr.) precipitation variability, which is linked to the North Atlantic Oscillation. The lake primarily adjusts to sustained inflow changes through amending surface evaporation. Cumulative water abstraction since 1951 (~19 × 106 m3/year: ~0.006% of lake volume) explains ~70% of the long-term decrease in surface evaporation; climate variability explains the remainder. Persistent low lake levels after 1995 are caused by water abstraction. Compared to 1952/53–1977/78, the period 1978/79–2003/04 experienced significant decreases in wet-season precipitation, snowfall and discharge; the number of very dry years increased.
EDITOR A. Castellarin; ASSOCIATE EDITOR D. Gerten  相似文献   

11.
The El Niño-Southern Oscillation (ENSO) is characterized based on the date the events are mature. Their time lag defined relative to the central value of successive intervals of 4 years length, e.g. 01/1868–01/1872, 01/1872–01/1876 …, 01/1996–01/2000 … affects their evolution and, for a given amplitude, their variability. It specifies the dynamics of the quadrennial Quasi-Stationary Wave (QSW) in the tropical Pacific since ENSO always occurs at the end of the eastward phase propagation of that QSW. A third of events are unlagged with very low variability, SST anomalies being nearly concomitant between the extreme eastern and the central-eastern Pacific. A third of events are weakly lagged, in phase with the annual QSW, whose variability is much greater. Several months may elapse between the maximum SST anomalies east of the basin and along its equatorial central part. The last third of the events exhibits considerable variability, whether they are out of phase with the annual QSW or strongly lagged. The SST anomaly between 5°N and 20°N plays a key role in the maturation of the events out of phase. The events in phase (10% of the total population) are characterized by a negative SST anomaly in the central-eastern Pacific that reverses just before the maturation stage of ENSO. Sea water temperature 125 m deep in the central-eastern Pacific carries the earliest relevant information with a lead time of one year for forecasting the amplitude of unlagged ENSO while reporting how SST anomalies will develop until ENSO is fully developed. Besides, long-term forecast of the resumption of La Niña can be achieved accurately when weakly lagged events in phase with the annual QSW occur. The well differentiated typology of events vs. their time lag is the best clue to prove the leading role of the quadrennial QSW in the genesis of ENSO, while the related dynamic of the atmosphere ensues.  相似文献   

12.
Lake water level forecasting is very important for an accurate and reliable management of local and regional water resources. In the present study two nonlinear approaches, namely phase-space reconstruction and self-exciting threshold autoregressive model (SETAR) were compared for lake water level forecasting. The modeling approaches were applied to high-quality lake water level time series of the three largest lakes in Sweden; Vänern, Vättern, and Mälaren. Phase-space reconstruction was applied by the k-nearest neighbor (k-NN) model. The k-NN model parameters were determined using autocorrelation, mutual information functions, and correlation integral. Jointly, these methods indicated chaotic behavior for all lake water levels. The correlation dimension found for the three lakes was 3.37, 3.97, and 4.44 for Vänern, Vättern, and Mälaren, respectively. As a comparison, the best SETAR models were selected using the Akaike Information Criterion. The best SETAR models in this respect were (10,4), (5,8), and (7,9) for Vänern, Vättern, and Mälaren, respectively. Both model approaches were evaluated with various performance criteria. Results showed that both modeling approaches are efficient in predicting lake water levels but the phase-space reconstruction (k-NN) is superior to the SETAR model.  相似文献   

13.
The present study aims to develop a hybrid multi‐model using the soft computing approach. The model is a combination of a fuzzy logic, artificial neural network (ANN) and genetic algorithm (GA). While neural networks are low‐level computational structures that perform well dealing with raw data, fuzzy logic deal with reasoning on a higher level by using linguistic information acquired from domain experts. However, fuzzy systems lack the ability to learn and cannot adjust themselves to a new environment. Moreover, experts occasionally make mistakes and thus some rules used in a system may be false. A network type structure of the present hybrid model is a multi‐layer feed‐forward network, the main part is a fuzzy system based on the first‐order Sugeno fuzzy model with a fuzzification and a defuzzification processes. The consequent parameters are determined by least square method. The back‐propagation is applied to adjust weights of network. Then, the antecedent parameters of the membership function are updated accordingly by the gradient descent method. The GA was applied to select the fuzzy rule. The hybrid multi‐model was used to forecast the flood level at Chiang Mai (under the big flood 2005) and the Koriyama flood (2003) in Japan. The forecasting results are evaluated using standard global goodness of fit statistic, efficient index (EI), the root mean square error (RMSE) and the peak flood error. Moreover, the results are compared to the results of a neuro‐genetic model (NGO) and ANFIS model using the same input and output variables. It was found that the hybrid multi‐model can be used successfully with an efficiency index (EI) more than 0·95 (for Chiang Mai flood up to 12 h ahead forecasting) and more than 0·90 (for Koriyama flood up to 8 h ahead forecasting). In general, all of three models can predict the water level with satisfactory results. However, the hybrid model gave the best flood peak estimation among the three models. Therefore, the use of fuzzy rule base, which is selected by GA in the hybrid multi‐model helps to improve the accuracy of flood peak. Copyright © 2009 John Wiley & Sons, Ltd.  相似文献   

14.
In order to maintain the scenic and eco-environmental values of a lake, we need to characterize its water interactions. Shahu Lake was used as a case study to show the interactions among replenishment water, lake water and groundwater in an arid region. Shahu Lake is located in the Ningxia Hui Autonomous Region of northwest China and has an area of 13.96 km2 and an average depth of 2.2 m. The groundwater modelling software MODFLOW was used. The analysis results show that hydraulic connectivity among replenishment water, lake water and groundwater is the crucial driving factor that affects the water level in Shahu Lake. The lake water level is highly sensitive to the volume of replenishment water. The groundwater is of great importance in balancing the water level in the lake and preventing it from drying up. It was determined that 13.8 × 106 m3/yr is the optimal volume of replenishment water for Shahu Lake in order to maintain the lake level at its normal state and also to make the best use of available water resources on a long-term basis. Understanding of the water interactions can promote effective management of water resources in Shahu Lake.
EDITOR D. Koutsoyiannis

ASSOCIATE EDITOR D. Hughes  相似文献   

15.
A drastic change in lake water color from blue-green to brown was observed in the summit crater lake of Mt. Shinmoe-dake, Kirishima Volcano about 8 months after its 2008 eruption. The color change lasted for about 2 months (April–June 2009). The discoloration was attributed to a brownish color suspension that had formed in the lake water. X-ray fluorescence and Fourier transform infrared analyses of a sample of the suspension identified schwertmannite (Fe8O8(OH)6(SO4)). A cultivation test of iron-oxidizing bacteria for the sampled lake water with lakebed sediment revealed that the crater lake hosts iron-oxidizing bacteria, which likely participated in schwertmannite formation. We suggest that pyrite (FeS2) provided an energy source for the iron-oxidizing bacteria since the mineral was identified in hydrothermally altered tephra ejected by the August 2008 eruption. From consideration of these and other factors, the brownish discoloration of the summit crater lake of Mt. Shinmoe-dake was inferred to have resulted from a combined volcanic–microbial process.  相似文献   

16.
ABSTRACT

Evaporation is one of the most important components in the energy and water budgets of lakes and is a primary process of water loss from their surfaces. An artificial neural network (ANN) technique is used in this study to estimate daily evaporation from Lake Vegoritis in northern Greece and is compared with the classical empirical methods of Penman, Priestley-Taylor and the mass transfer method. Estimation of the evaporation over the lake is based on the energy budget method in combination with a mathematical model of water temperature distribution in the lake. Daily datasets of air temperature, relative humidity, wind velocity, sunshine hours and evaporation are used for training and testing of ANN models. Several input combinations and different ANN architectures are tested to detect the most suitable model for predicting lake evaporation. The best structure obtained for the ANN evaporation model is 4-4-1, with root mean square error (RMSE) from 0.69 to 1.35 mm d?1 and correlation coefficient from 0.79 to 0.92.
EDITOR M.C. Acreman

ASSOCIATE EDITOR not assigned  相似文献   

17.
Accurate and reliable river flow forecasts attained with data-intelligent models can provide significant information about future water resources management. In this study we employed a 50-model ensemble of three data-driven predictive models, namely the support vector regression (SVR), multivariate adaptive regression spline (MARS) and M5 model tree (M5Tree) to forecast river flow data in a semiarid and ecologically significant mountainous region of Pailugou catchment in northwestern China. To attain stable and accurate forecast results, 50 different models were trained by randomly sampling the entire river flow data into 80% for training and 20% for testing subsets. To attain a complete evaluation of the ensemble-model based results, the global mean of six quantitative statistical performance evaluation measures: the coefficient of correlation (R), mean absolute relative error (MAE), root mean squared error (RMSE), Nash–Sutcliffe efficiency coefficient (NS), relative RMSE, and the Willmott’s Index (WI), and Taylor diagrams, including skill scores relative to a persistence model, were selected to assess the performances of the developed predictive models. The results indicated that all of the averaged R value attained was higher than 0.900 and all of the averaged NS values were higher than 0.800, representing good performance of the SVR, MARS and M5Tree models applied in the 1-, 2- and 3-day ahead modeling horizon, and this also accorded with the deductions made through an assessment of the Willmott’s Index. However, the M5Tree model outperformed both the SVR and MARS models (with NS?=?0.917 vs. 0.904 and 0.901 for 1-day, 0.893 vs. 0.854 and 0.845 for 2-day, and 0.850 vs. 0.828 and 0.810 for 3-day forecasting horizons, respectively), which was in concurrence with the high value of WI. Therefore, based on the ensemble of 50 models, the performance of the M5Tree can be considered as superior to the SVR and MARS models when applied in a problem of river flow forecasting at multiple forecast horizon. A detailed comparison of the overall performance of all three models evaluated through Taylor diagrams and boxplots indicated that the 1-day ahead forecasting results were more accurate for all of the predictive models compared to the 2- and 3-day ahead forecasting horizons. Data-intelligent models designed in this study indicate that the M5Tree method could successfully be explored for short-term river flow forecasting in semiarid mountainous regions, which may have useful implications in water resources management, ecological sustainability and assessment of river systems.  相似文献   

18.
Evapotranspiration (ET) is one of the main components of the hydrological cycle. It is a complex process driven mainly by weather parameters, and as such, is characterized by high non-linearity and non-stationarity. This paper introduces a methodology combining wavelet multiresolution analysis with a machine learning algorithm, the multivariate relevance vector machine (MVRVM), in order to predict 16 days of future daily reference evapotranspiration (ETo). This methodology lays the ground for forecasting the spatial distribution of ET using Landsat satellite imagery, hence the choice of 16 days, which corresponds with the Landsat overpass cycle. An accurate prediction of daily ETo is needed to improve the management of irrigation schedules as well as the operations of water supply facilities like canals and reservoirs. In this paper, various wavelet decompositions were performed and combined with MVRVM to develop hybrid models to predict ETo over a 16-days period. These models were compared to a MVRVM model, and models accuracy and robustness were evaluated. The addition of 10 days of forecasted air temperature as additional inputs to the forecasting models was also investigated. The results of the wavelet-MVRVM hybrid modeling methodology showed that a reliable forecast of ETo up to 16 days ahead is possible.  相似文献   

19.
Information on regional snow water equivalent (SWE) is required for the management of water generated from snowmelt. Modeling of SWE in the mountainous regions of eastern Turkey, one of the major headwaters of Euphrates–Tigris basin, has significant importance in forecasting snowmelt discharge, especially for optimum water usage. An assimilation process to produce daily SWE maps is developed based on Helsinki University of Technology (HUT) model and AMSR‐E passive microwave data. The characteristics of the HUT emission model are analyzed in depth and discussed with respect to the extinction coefficient function. A new extinction coefficient function for the HUT model is proposed to suit models for snow over mountainous areas. Performance of the modified model is checked against the original, other modified cases and ground truth data covering the 2003–2007 winter periods. A new approach to calculate grain size and density is integrated inside the developed data assimilation process. An extensive validation was successfully performed by means of snow data measured at ground stations during the 2008–2010 winter periods. The root mean square error of the data set for snow depth and SWE between January and March of the 2008–2010 periods compared with the respective AMSR‐E footprints indicated that errors for estimated snow depth and predicted SWE values were 16.92 cm and 40.91 mm, respectively, for the 3‐year period. Validation results were less satisfactory for SWE less than 75.0 mm and greater than 150.0 mm. An underestimation for SWE greater than 150 mm could not be resolved owing to the microwave signal saturation that is observed for dense snowpack. Copyright © 2012 John Wiley & Sons, Ltd.  相似文献   

20.
Abstract

New wavelet and artificial neural network (WA) hybrid models are proposed for daily streamflow forecasting at 1, 3, 5 and 7 days ahead, based on the low-frequency components of the original signal (approximations). The results show that the proposed hybrid models give significantly better results than the classical artificial neural network (ANN) model for all tested situations. For short-term (1-day ahead) forecasts, information on higher-frequency signal components was essential to ensure good model performance. However, for forecasting more days ahead, lower-frequency components are needed as input to the proposed hybrid models. The WA models also proved to be effective for eliminating the lags often seen in daily streamflow forecasts obtained by classical ANN models. 

Editor D. Koutsoyiannis; Associate editor L. See

Citation Santos, C.A.G. and Silva, G.B.L., 2013. Daily streamflow forecasting using a wavelet transform and artificial neural network hybrid models. Hydrological Sciences Journal, 59 (2), 312–324.  相似文献   

设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号