共查询到20条相似文献，搜索用时 578 毫秒
1.
Ani Shabri 《水文科学杂志》2013,58(7):1275-1293
Abstract This paper investigates the ability of a least-squares support vector machine (LSSVM) model to improve the accuracy of streamflow forecasting. Cross-validation and grid-search methods are used to automatically determine the LSSVM parameters in the forecasting process. To assess the effectiveness of this model, monthly streamflow records from two stations, Tg Tulang and Tg Rambutan of the Kinta River in Perak, Peninsular Malaysia, were used as case studies. The performance of the LSSVM model is compared with the conventional statistical autoregressive integrated moving average (ARIMA), the artificial neural network (ANN) and support vector machine (SVM) models using various statistical measures. The results of the comparison indicate that the LSSVM model is a useful tool and a promising new method for streamflow forecasting. Editor D. Koutsoyiannis; Associate editor L. See Citation Shabri, A. and Suhartono, 2012. Streamflow forecasting using least-squares support vector machines. Hydrological Sciences Journal, 57 (7), 1275–1293. 相似文献
2.
Comparison of daily streamflow forecasts using extreme learning machines and the random forest method 总被引：1，自引：0，他引：1
《水文科学杂志》2012,57(15):1857-1866
ABSTRACTDaily streamflow forecasting is a challenging and essential task for water resource management. The main goal of this study was to compare the accuracy of five data-driven models: extreme learning machine (basic ELM), extreme learning machine with kernels (ELM-kernel), random forest (RF), back-propagation neural network (BPNN) and support vector machine (SVR). The results show that the ELM-kernel model provided a superior alternative to the other models, and the basic ELM model had the poorest performance. To further evaluate the predictive capacities of the five models, the estimations of low flow and high flow in the testing dataset were compared. The RF model was slightly superior to the other models in predicting the peak flows, and the ELM-kernel model showed the highest prediction precision of low flows. There was no single model that showed obvious advantages over the other models in this study. Therefore, further exploration is required for the hydrological forecasting problems. 相似文献
3.
《水文科学杂志》2012,57(1):57-70
ABSTRACTLeading patterns of observed seasonal extreme and mean streamflow on the Korean peninsula were estimated using an empirical orthogonal teleconnection (EOT) technique. In addition, statistical correlations on a seasonal basis were calculated using correlation and regression analyses between the leading streamflow patterns and various climate indices based on atmospheric–ocean circulation. The spatio-temporal patterns of the leading EOT modes for extreme and mean streamflow indicate an upstream mode for the Han River, with increasing trends in summer, and a downstream mode for the Nakdong River, with oscillations mainly on inter-decadal time scales in winter. The tropical ENSO (El Niño Southern Oscillation) forcing for both extreme and mean streamflow is coherently associated with summer to winter streamflow patterns. The western North Pacific monsoon has a negative correlation with winter streamflow variability, and tropical cyclone indices also exhibit significant positive correlation with autumn streamflow. Leading patterns of autumn and winter streamflow time series show predictability up to two seasons in advance from the Pacific sea-surface temperatures. 相似文献
4.
Hydrological and statistical models are playing an increasing role in hydrological forecasting, particularly for river basins with data of different temporal scales. In this study, statistical models, e.g. artificial neural networks, adaptive network-based fuzzy inference system, genetic programming, least squares support vector machine, multiple linear regression, were developed, based on parametric optimization methods such as particle swarm optimization (PSO), genetic algorithm (GA), and data-preprocessing techniques such as wavelet decomposition (WD) for river flow modelling using daily streamflow data from four hydrological stations for a period of 1954–2009. These models were used for 1-, 3- and 5-day streamflow forecasting and the better model was used for uncertainty evaluation using bootstrap resampling method. Meanwhile, a simple conceptual hydrological model GR4J was used to evaluate parametric uncertainty based on generalized likelihood uncertainty estimation method. Results indicated that: (1) GA and PSO did not help improve the forecast performance of the model. However, the hybrid model with WD significantly improved the forecast performance; (2) the hybrid model with WD as a data preprocessing procedure can clarify hydrological effects of water reservoirs and can capture peak high/low flow changes; (3) Forecast accuracy of data-driven models is significantly influenced by the availability of streamflow data. More human interferences from the upper to the lower East River basin can help to introduce greater uncertainty in streamflow forecasts; (4) The structure of GR4J may introduce larger parametric uncertainty at the Longchuan station than at the Boluo station in the East river basin. This study provides a theoretical background for data-driven model-based streamflow forecasting and a comprehensive view about data and parametric uncertainty in data-scarce river basins. 相似文献
5.
In mountainous river basins of the Pacific Northwest, climate models predict that winter warming will result in increased precipitation falling as rain and decreased snowpack. A detailed understanding of the spatial and temporal dynamics of water sources across river networks will help illuminate climate change impacts on river flow regimes. Because the stable isotopic composition of precipitation varies geographically, variation in surface water isotope ratios indicates the volume-weighted integration of upstream source water. We measured the stable isotope ratios of surface water samples collected in the Snoqualmie River basin in western Washington over June and September 2017 and the 2018 water year. We used ordinary least squares regression and geostatistical Spatial Stream Network models to relate surface water isotope ratios to mean watershed elevation (MWE) across seasons. Geologic and discharge data was integrated with water isotopes to create a conceptual model of streamflow generation for the Snoqualmie River. We found that surface water stable isotope ratios were lowest in the spring and highest in the dry, Mediterranean summer, but related strongly to MWE throughout the year. Low isotope ratios in spring reflect the input of snowmelt into high elevation tributaries. High summer isotope ratios suggest that groundwater is sourced from low elevation areas and recharged by winter precipitation. Overall, our results suggest that baseflow in the Snoqualmie River may be relatively resilient to predicted warming and subsequent changes to snowpack in the Pacific Northwest. 相似文献
6.
Statistical downscaling of GCM simulations to streamflow using relevance vector machine 总被引：1，自引：0，他引：1
General circulation models (GCMs), the climate models often used in assessing the impact of climate change, operate on a coarse scale and thus the simulation results obtained from GCMs are not particularly useful in a comparatively smaller river basin scale hydrology. The article presents a methodology of statistical downscaling based on sparse Bayesian learning and Relevance Vector Machine (RVM) to model streamflow at river basin scale for monsoon period (June, July, August, September) using GCM simulated climatic variables. NCEP/NCAR reanalysis data have been used for training the model to establish a statistical relationship between streamflow and climatic variables. The relationship thus obtained is used to project the future streamflow from GCM simulations. The statistical methodology involves principal component analysis, fuzzy clustering and RVM. Different kernel functions are used for comparison purpose. The model is applied to Mahanadi river basin in India. The results obtained using RVM are compared with those of state-of-the-art Support Vector Machine (SVM) to present the advantages of RVMs over SVMs. A decreasing trend is observed for monsoon streamflow of Mahanadi due to high surface warming in future, with the CCSR/NIES GCM and B2 scenario. 相似文献
7.
Kwabena Kankam-Yeboah Emmanuel Obuobie Barnabas Amisigo Yaw Opoku-Ankomah 《水文科学杂志》2013,58(4):773-788
Abstract This study uses the Soil and Water Assessment Tool (SWAT) and downscaled climate projections from the ensemble of two global climate models (ECHAM4 and CSIRO) forced by the A1FI greenhouse-gas scenario to estimate the impact of climate change on streamflow in the White Volta and Pra river basins, Ghana. The SWAT model was calibrated for the two basins and subsequently driven by downscaled future climate projections to estimate the streamflow for the 2020s (2006–2035) and 2050s (2036–2075). Relative to the baseline, the mean annual streamflow estimated for the White Volta basin for the 2020s and 2050s showed a decrease of 22 and 50%, respectively. Similarly, the estimated streamflow for the 2020s and 2050s for the Pra basin showed a decrease of 22 and 46%, respectively. These results underscore the need to put in place appropriate adaptation measures to foster resilience to climate change in order to enhance water security within the two basins. Citation Kankam-Yeboah, K., Obuobie, E., Amisigo, B., and Opoku-Ankomah, Y., 2013. Impact of climate change on streamflow in selected river basins in Ghana. Hydrological Sciences Journal, 58 (4), 773–788. 相似文献
8.
Predictions of river flow dynamics provide vital information for many aspects of water management including water resource planning, climate adaptation, and flood and drought assessments. Many of the subjective choices that modellers make including model and criteria selection can have a significant impact on the magnitude and distribution of the output uncertainty. Hydrological modellers are tasked with understanding and minimising the uncertainty surrounding streamflow predictions before communicating the overall uncertainty to decision makers. Parameter uncertainty in conceptual rainfall-runoff models has been widely investigated, and model structural uncertainty and forcing data have been receiving increasing attention. This study aimed to assess uncertainties in streamflow predictions due to forcing data and the identification of behavioural parameter sets in 31 Irish catchments. By combining stochastic rainfall ensembles and multiple parameter sets for three conceptual rainfall-runoff models, an analysis of variance model was used to decompose the total uncertainty in streamflow simulations into contributions from (i) forcing data, (ii) identification of model parameters and (iii) interactions between the two. The analysis illustrates that, for our subjective choices, hydrological model selection had a greater contribution to overall uncertainty, while performance criteria selection influenced the relative intra-annual uncertainties in streamflow predictions. Uncertainties in streamflow predictions due to the method of determining parameters were relatively lower for wetter catchments, and more evenly distributed throughout the year when the Nash-Sutcliffe Efficiency of logarithmic values of flow (lnNSE) was the evaluation criterion. 相似文献
9.
Comparison of local and global approximators in multivariate chaotic forecasting of daily streamflow
Hakan Tongal 《水文科学杂志》2020,65(7):1129-1144
ABSTRACTAlthough it is conceptually assumed that global models are relatively ineffective in modelling the highly unstable structure of chaotic hydrologic dynamics, there is not a detailed study of comparing the performances of local and global models in a hydrological context, especially with new emerging machine learning models. In this study, the performance of a local model (k-nearest neighbour, k-nn) and, as global models, several recent machine learning models – artificial neural network (ANN), least square-support vector regression (LS-SVR), random forest (RF), M5 model tree (M5), multivariate adaptive regression splines (MARS) – was analysed in multivariate chaotic forecasting of streamflow. The models were developed for Australia’s largest river, the River Murray. The results indicate that the k-nn model was more successful than the global models in capturing the streamflow dynamics. Furthermore, coupled with the multivariate phase-space, it was shown that the global models can be successfully used for obtaining reliable uncertainty estimates for streamflow. 相似文献
10.
GREGORY J. McCABE JR 《水文科学杂志》2013,58(6):873-887
Abstract Winter mean 700-hectoPascal (hPa) height anomalies, representing the average atmospheric circulation during the snow season, are compared with annual streamflow measured at 140 streamgauges in the western United States. Correlation and anomaly pattern analyses are used to identify relationships between winter mean atmospheric circulation and temporal and spatial variability in annual streamflow. Results indicate that variability in winter mean 700-Hpa height anomalies accounts for a statistically significant portion of the temporal variability in annual streamflow in the western United States. In general, above-average annual streamflow is associated with negative winter mean 700-Hpa height anomalies over the eastern North Pacific Ocean and/or the western United States. The anomalies produce an anomalous flow of moist air from the eastern North Pacific Ocean into the western United States that increases winter precipitation and snowpack accumulations, and subsequently streamflow. Winter mean 700-hPa height anomalies also account for statistically significant differences in spatial distributions of annual streamflow. As part of this study, winter mean atmospheric circulation patterns for the 40 years analysed were classified into five winter mean 700-hPa height anomaly patterns. These patterns are related to statistically significant and physically meaningful differences in spatial distributions of annual streamflow. 相似文献
11.
《水文科学杂志》2013,58(1):183-197
Abstract Abstract Correct estimation of the sediment volume carried by a river is important with respect to pollution, channel navigability, reservoir filling, hydroelectric equipment longevity, fish habitat, river aesthetics and scientific interests. However, conventional sediment rating curves are not able to provide sufficiently accurate results. In this study, models incorporating fuzzy logic are developed as a superior alternative to the sediment rating curve technique for determining the daily suspended sediment concentration for a given river cross-section. This study provides forecasting benchmarks for sediment concentration prediction in the form of a numerical and graphical comparison between fuzzy and rating curve models. Benchmarking was based on a five-year period of continuous streamflow and sediment concentration data from the Quebrada Blanca Station operated by the United States Geological Survey (USGS). Nine different fuzzy models were developed to estimate sediment concentration from streamflow. Each fuzzy model has a different number of membership functions. The parameters of the membership functions were found using a differential evolution algorithm. The benchmark results showed that the fuzzy models were able to produce much better results than rating curve models for the same data inputs. 相似文献
12.
Dendroclimatological data were used to reconstruct the discharge history of Chilko River, which drains a glacierized watershed in the Coast Mountains of British Columbia. We correlated ring‐width records from Engelmann spruce (ES) (Picea engelmanni) and mountain hemlock (MH) (Tsuga mertensiana) trees to historical hydroclimate data. Over the period of record, spruce and hemlock radial growth correlates significantly with temperature and snow depth, respectively. We found that a multi‐species approach provided a better model fit and reconstructive power. Using these relationships, we developed generalized linear models for mean June, July, and June‐July discharge. The proxy records provide insights into streamflow variability of a typical Coast Mountains river over the past 240 years and confirm the long‐term influence of the Pacific Decadal Oscillation (PDO) on hydroclimatic regimes in the region. A relationship also exists between the reconstructed June‐July discharge record and the North Pacific (NP) Index, suggesting that winter atmospheric patterns over the North Pacific influence the hydrology of coastal British Columbia. Copyright © 2010 John Wiley & Sons, Ltd. 相似文献
13.
Abstract Experimental work on electromagnetic streamflow measurements on the tidal Fraser River in British Columbia shows that the method of using the earth's magnetic field has two advantages: it gives an instantaneous value of the water velocity integrated over the entire cross section of the river and it is independent of temperature. In the Canadian climate both factors are important. The instrumentation is relatively inexpensive and it consists of a digital to analog converter, strip chart recorder, cable and silver electrodes. The instrumentation is essential for noise filtering and signal amplification. However, the final interpretation of the measured signal is quite difficult; it requires measurements from an electronic analog of the river cross section, resistivity of the ground below, conductivity of the water and a numerical hydrodynamic model. The flow velocities obtained from the measurements of induced potentials, caused by the Fraser River flowing across the earth's magnetic field, compared favourably with velocities computed from a proven hydrodynamic numerical model. 相似文献
14.
《水文科学杂志》2013,58(6):1006-1020
AbstractThis paper aims to compare the shift in frequency distribution and skill of seasonal climate forecasting of both streamflow and rainfall in eastern Australia based on the Southern Oscillation Index (SOI) Phase system. Recent advances in seasonal forecasting of climate variables have highlighted opportunities for improving decision making in natural resources management. Forecasting of rainfall probabilities for different regions in Australia is available, but the use of similar forecasts for water resource supply has not been developed. The use of streamflow forecasts may provide better information for decision-making in irrigation supply and flow management for improved ecological outcomes. To examine the relative efficacy of seasonal forecasting of streamflow and rainfall, the shift in probability distributions and the forecast skill were evaluated using the Wilcoxon rank-sum test and the linear error in probability space (LEPS) skill score, respectively, at three river gauging stations in the Border Rivers Catchment of the Murray-Darling Basin in eastern Australia. A comparison of rainfall and streamflow distributions confirms higher statistical significance in the shift of streamflow distribution than that in rainfall distribution. Moreover, streamflow distribution showed greater skill of forecasting with 0–3 month lead time, compared to rainfall distribution. 相似文献
15.
This study evaluates changes in streamflow, temperature and precipitation over a time span of 105 years (1906–2010) in the Colorado River Basin (CRB). Monthly precipitation and temperature data for 29 climate divisions, and streamflow data for 29 naturalized gauges were analyzed. Two variations of the Mann-Kendall test, considering lag-1 auto correlation and long-term persistence, and the Pettitt test were employed to assess trends and shifts, respectively. Results indicated that streamflow increased during the winter–spring months and decreased during the summer– autumn period. Decreasing trends in winter precipitation were identified over snow-dominated regions in the upper basin. Significant increases in temperature were detected over several months. Major shifts were noticed in 1964, 1968 and in the late 1920s. Increasing temperature while decreasing streamflow and precipitation were noticed after major shifts in the 1930s, and these shifts coincided with coupled phases of El Niño Southern Oscillation and Pacific Decadal Oscillation.
EDITOR A. Castellarin; ASSOCIATE EDITOR R. Hirsch 相似文献
16.
Maryam Pournasiri Poshtiri Indrani Pal Upmanu Lall Philippe Naveau Erin Towler 《水文研究》2019,33(11):1569-1578
Low‐flow events can cause significant impacts to river ecosystems and water‐use sectors; as such, it is important to understand their variability and drivers. In this study, we characterise the variability and timing of annual total frequency of low‐streamflow days across a range of headwater streams within the continental United States. To quantify this, we use a metric that counts the annual number of low‐flow days below a given threshold, defined as the cumulative dry days occurrence (CDO). First, we identify three large clusters of stream gauge locations using a Partitioning Around Medoids (PAM) clustering algorithm. In terms of timing, results reveal that for most clusters, the majority of low‐streamflow days occur from the middle of summer until early fall, although several locations in Central and Western United States also experience low‐flow days in cold seasons. Further, we aim to identify the regional climate and larger scale drivers for these low‐streamflow days. Regionally, we find that precipitation deficits largely associate with low‐streamflow days in the Western United States, whereas within the Central and Eastern U.S. clusters, high temperature indicators are also linked to low‐streamflow days. In terms of larger scale, we examine sea surface temperature (SST) anomalies, finding that extreme dry years exhibit a high degree of co‐occurrence with different patterns of warmer SST anomalies across the Pacific and Northern Atlantic Oceans. The linkages identified with regional climate and SSTs offer promise towards regional prediction of changing conditions of low‐streamflow events. 相似文献
17.
Abstract A river flow regime describes an average seasonal behaviour of flow and reflects the climatic and physiographic conditions in a basin. Differences in the regularity (stability) of the seasonal patterns reflect different dimensionality of the flow regimes, which can change subject to changes in climate conditions. The empirical orthogonal functions (EOF) approach can be used to describe the intrinsic dimension of river flow regimes and is also an adopted method for reducing the phase space in connection to climate change studies, especially in studies of nonlinear dynamic systems with preferred states. A large data set of monthly river flow for the Nordic countries has been investigated in the phase space reduced to the first few amplitude functions to trace a possible signature of climate change on the seasonal flow patterns. The probability density functions (PDF) of the weight coefficients and their possible change over time were used as an indicator of climate change. Two preferred states were identified connected to stable snowmelt-fed and rainfed flow regimes. The results indicate changes in the PDF patterns with time towards higher frequencies of rainfed regime types. The dynamics of seasonal patterns studied in terms of PDF renders it an adequate and convenient characterization, helping to avoid bias connected to flow regime classifications as well as uncertainties inferred by a modelling approach. 相似文献
18.
Distinguishing the effects of climate on discharge in a tropical river highly impacted by large dams
Abstract The hydrological regime of a river is defined by variables or representative curves that in turn have characteristics related to fluctuations in flow rates resulting from climate variability. Distinguishing between the causes of streamflow variations, i.e. those resulting from human intervention in the watershed and those due to climate variability, is not trivial. To discriminate the alterations resulting from climate variation from those due to regulation by dams, a reference hydrological regime was established using the classification of events based on mean annual streamflow anomalies and inferred climatic conditions. The applicability of this approach was demonstrated by analysis of the streamflow duration curves. An assessment of the hydrological regime in the lower reaches of the São Francisco River, Brazil, after the implementation of hydropower plants showed that the operation of the dams has been responsible for 59% of the hydrological changes, while the climate (in driest conditions) has contributed to 41% of the total changes. Editor Z.W. Kundzewicz Citation Genz, F. and Luz, L.D., 2012. Distinguishing the effects of climate on discharge in a tropical river highly impacted by large dams. Hydrological Sciences Journal, 57 (5), 1020–1034. 相似文献
19.
M. PAUL MOSLEY 《水文科学杂志》2013,58(2):249-267
Abstract The response of monthly 7-day low flow, monthly instantaneous peak flow, and monthly frequency of flood events to El Niño and La Niña episodes is investigated for 18 rivers that represent a diverse range of climatic types throughout New Zealand. A significant positive or negative deviation from the long-term average was observed in over half the possible combinations of river, streamflow index, and type of ENSO episode; significant deviations were most frequent in the case of low flow, especially during La Niña episodes. Patterns of streamflow response differ widely between rivers, and the response of a given river to individual ENSO episodes is very variable. The patterns of streamflow response to ENSO are consistent to some extent with the climatic effects of ENSO already identified by meteorologists. Two core regions can be defined in which streamflow tends to respond in the same way. These are in the northeast of the North Island, and in the axial ranges of the South Island, where there are significant effects of ENSO on the frequency and duration of rain-bearing northeasterly and westerly winds respectively. The patterns of response strongly reflect topography, and the exposure of catchments to predominant air masses. 相似文献
20.
Response of hydrology to climate change in the southern Appalachian Mountains using Bayesian inference 总被引：1，自引：0，他引：1 
下载免费PDF全文
下载免费PDF全文 Predicting long‐term consequences of climate change on hydrologic processes has been limited due to the needs to accommodate the uncertainties in hydrological measurements for calibration, and to account for the uncertainties in the models that would ingest those calibrations and uncertainties in climate predictions as basis for hydrological predictions. We implemented a hierarchical Bayesian (HB) analysis to coherently admit multiple data sources and uncertainties including data inputs, parameters, and model structures to identify the potential consequences of climate change on soil moisture and streamflow at the head watersheds ranging from low to high elevations in the southern Appalachian region of the United States. We have considered climate change scenarios based on three greenhouse gas emission scenarios of the Interovernmental Panel on Climate Change: A2, A1B, and B1 emission scenarios. Full predictive distributions based on HB models are capable of providing rich information and facilitating the summarization of prediction uncertainties. With predictive uncertainties taken into account, the most pronounced change in soil moisture and streamflow would occur under the A2 scenario at both low and high elevations, followed by the A1B scenario and then by the B1 scenario. Uncertainty in the change of soil moisture is less than that of streamflow for each season, especially at high elevations. A reduction of soil moisture in summer and fall, a reduction or slight increase of streamflow in summer, and an increase of streamflow in winter are predicted for all three scenarios at both low and high elevations. The hydrological predictions with quantified uncertainties from a HB model could aid more‐informed water resource management in developing mitigation plans and dealing with water security under climate change. Copyright © 2012 John Wiley & Sons, Ltd. 相似文献