Application of newly developed ensemble machine learning models for daily suspended sediment load prediction and related uncertainty analysis     

Ahmad Sharafati  Seyed Babak Haji Seyed Asadollah  Davide Motta 《水文科学杂志》2020,65(12):2022-2042

ABSTRACT

Ensemble machine learning models have been widely used in hydro-systems modeling as robust prediction tools that combine multiple decision trees. In this study, three newly developed ensemble machine learning models, namely gradient boost regression (GBR), AdaBoost regression (ABR) and random forest regression (RFR) are proposed for prediction of suspended sediment load (SSL), and their prediction performance and related uncertainty are assessed. The SSL of the Mississippi River, which is one of the major world rivers and is significantly affected by sedimentation, is predicted based on daily values of river discharge (Q) and suspended sediment concentration (SSC). Based on performance metrics and visualization, the RFR model shows a slight lead in prediction performance. The uncertainty analysis also indicates that the input variable combination has more impact on the obtained predictions than the model structure selection.  相似文献   

    

Yang Hui  Zhang Daomin  Ji Liren 《大气科学进展》2001,18(2):283-293

The approach of getting useful information of monthly dynamical prediction from ensemble forecasts is studied. The extended range ensemble forecasts (8 members, the initial perturbations of the lagged average forecast (LAF)(0000, 0600, 1200 and 1800 GMT in two consecutive days) of the 500 hPa height field with the global spectral model (T63L16) from January to May 1997 are provided by the National Climate Center of China. The relationship between the spread of ensemble measured by root–mean–square deviation of ensemble member from ensemble mean and forecast skill (the anomaly correlation or the root–mean–square distance between the ensemble mean forecast and the observation) is significant. The spread of ensemble can evaluate the useful forecast days N for the best estimate of 30 days mean. Thus, a weighted mean approach based on ensemble spread is put forward for monthly dynamical prediction. The anomaly correlation of the weighted monthly mean by the ensemble spread is higher than that of both the arithmetic mean and the linear weighted mean. Better results of the monthly mean circulation and anomaly are obtained from the ensemble spread weighted mean. Supported by the Excellent National State Key Laboratory Project (49823002), the National Key Project ‘Study on Chinese Short-Term Climate Forecast System’ (96-908-02) and IAP Innovation Foundation (8-1308). The data were provided through the National Climate Center of China. The authors wish to thank Ms. Chen Lijuan for her assistance.  相似文献   

Projection of climate change for daily precipitation: a case study in Shih‐Men reservoir catchment in Taiwan     

Tao‐Chang Yang  Pao‐Shan Yu  Chi‐Ma Wei  Shien‐Tsung Chen 《水文研究》2011,25(8):1342-1354

A statistical downscaling model, based on the outputs of general circulation models (GCMs) as predictors, was proposed to simulate the daily precipitations in the Shih‐Men reservoir catchment in Taiwan. The structure of the proposed downscaling model is composed of two parts: classification and regression. Predictors of classification and regression models were selected from the large‐scale weather variables in the National Centers for Environmental Prediction (NECP) reanalysis data based on statistical tests. Discriminant analysis and support vector regression (SVR) were applied to build the classification and regression models. The outputs of five atmosphere‐ocean GCMs, which are reported to have properly considered tropical cyclone information and East Asian Monsoon modelling, were used for projecting future precipitations. Data from four grids covering Taiwan were used for developing the downscaling model. The potential of the downscaling models in simulating local precipitations was evaluated, and downscaling results reveal that the proposed downscaling model can reproduce local daily precipitations from large‐scale weather variables. Projected local precipitations under two emission scenarios show that the precipitations in the study area tend to decrease. Copyright © 2010 John Wiley & Sons, Ltd.  相似文献   

一个快速海洋三维温盐流分析系统及在亚丁湾临近海域的应用     

闫长香  谢基平  朱江 《气候与环境研究》2011,16(4):419-428

开发了一个能快速估计三维海洋温盐流场的分析系统.这种系统以海洋数值模式多年积分的气候态结果作为背景场,通过多变量的集合最优插值同化方法利用现场观测和遥感卫星高度计及海表温度观测先对背景场进行偏差订正,以订正的背景场产生当前或瞬时的背景场,结合实时或近期观测通过集合最优插值方法得到三维海洋状态的估计.这种分析系统的优点是...  相似文献   

An iterative ensemble Kalman filter for reservoir engineering applications   总被引：1，自引：0，他引：1  

M. V. Krymskaya  R. G. Hanea  M. Verlaan 《Computational Geosciences》2009,13(2):235-244

The study has been focused on examining the usage and the applicability of ensemble Kalman filtering techniques to the history matching procedures. The ensemble Kalman filter (EnKF) is often applied nowadays to solving such a problem. Meanwhile, traditional EnKF requires assumption of the distribution’s normality. Besides, it is based on the linear update of the analysis equations. These facts may cause problems when filter is used in reservoir applications and result in sampling error. The situation becomes more problematic if the a priori information on the reservoir structure is poor and initial guess about the, e.g., permeability field is far from the actual one. The above circumstance explains a reason to perform some further research concerned with analyzing specific modification of the EnKF-based approach, namely, the iterative EnKF (IEnKF) scheme, which allows restarting the procedure with a new initial guess that is closer to the actual solution and, hence, requires less improvement by the algorithm while providing better estimation of the parameters. The paper presents some examples for which the IEnKF algorithm works better than traditional EnKF. The algorithms are compared while estimating the permeability field in relation to the two-phase, two-dimensional fluid flow model.  相似文献   

China summer precipitation simulations using an optimal ensemble of cumulus schemes     

Shuyan Liu  Wei Gao  Min Xu  Xueyuan Wang  Xin-Zhong Liang 《Frontiers of Earth Science》2009,3(2):248-257

RegCM3 (REGional Climate Model) simulations of precipitation in China in 1991 and 1998 are very sensitive to the cumulus parameterization. Among the four schemes available, none has superior skills over the whole of China, but each captures certain observed signals in distinct regions. The Grell scheme with the Fritsch-Chappell closure produces the smallest biases over the North; the Grell scheme with the Arakawa-Schubert closure performs the best over the southeast of 100°E; the Anthes-Kuo scheme is superior over the northeast; and the Emanuel scheme is more realistic over the southwest of 100°E and along the Yangtze River Basin. These differences indicate a strong degree of independence and complementarity between the parameterizations. As such, an ensemble is developed from the four schemes, whose relative contributions or weights are optimized locally to yield overall minimum root-mean-square errors from observed daily precipitation. The skill gain is evaluated by applying the identical distribution of the weights in a different period. It is shown that the ensemble always produces gross biases that are smaller than the individual schemes in both 1991 and 1998. The ensemble, however, cannot eliminate the large rainfall deficits over the southwest of 100°E and along the Yangtze River Basin that are systematic across all schemes. Further improve-ments can be made by a super-ensemble based on more cumulus schemes and/or multiple models.  相似文献   

Recent Advances in Dynamical Extra-Seasonal to Annual Climate Prediction at IAP／CAS   总被引：2，自引：0，他引：2  

LIN Zhaohui  WANG Huijun  ZHOU Guangqing  CHEN Hong  LANG Xianmei  ZHAO Yan  ZENG Qingcun 《大气科学进展》2004,21(3):456-466

Recent advances in dynamical climate prediction at the Institute of Atmospheric Physics, Chinese Academy of Sciences (IAP/CAS) during the last five years have been briefly described in this paper. Firstly,the second generation of the IAP dynamical climate prediction system (IAP DCP-II) has been described,and two sets of hindcast experiments of the summer rainfall anomalies over China for the periods of 1980-1994 with different versions of the IAP AGCM have been conducted. The comparison results show that the predictive skill of summer rainfall anomalies over China is improved with the improved IAP AGCM in which the surface albedo parameterization is modified. Furthermore, IAP DCP-II has been applied to the real-time prediction of summer rainfall anomalies over China since 1998, and the verification results show that IAP DCP-II can quite well capture the large scale patterns of the summer flood/drought situations over China during the last five years (1998-2002). Meanwhile, an investigation has demonstrated the importance of the atmospheric initial conditions on the seasonal climate prediction, along with studies on the influences from surface boundary conditions (e.g., land surface characteristics, sea surface temperature).Certain conclusions have been reached, such as, the initial atmospheric anomalies in spring may play an important role in the summer climate anomalies, and soil moisture anomalies in spring can also have a significant impact on the summer climate anomalies over East Asia. Finally, several practical techniques(e.g., ensemble technique, correction method, etc.), which lead to the increase of the prediction skill for summer rainfall anomalies over China, have also been illustrated. The paper concludes with a list of criticalre quirements needed for the further improvement of dynamical seasonal climate prediction.  相似文献   

Assessing the impact of land use change on hydrology by ensemble modeling (LUCHEM) III: Scenario analysis   总被引：1，自引：0，他引：1  

J.A. Huisman  L. Breuer  H. Bormann  A. Bronstert  B.F.W. Croke  H.-G. Frede  T. Gräff  L. Hubrechts  A.J. Jakeman  G. Kite  J. Lanini  G. Leavesley  D.P. Lettenmaier  G. Lindström  J. Seibert  M. Sivapalan  N.R. Viney  P. Willems 《Advances in water resources》2009

An ensemble of 10 hydrological models was applied to the same set of land use change scenarios. There was general agreement about the direction of changes in the mean annual discharge and 90% discharge percentile predicted by the ensemble members, although a considerable range in the magnitude of predictions for the scenarios and catchments under consideration was obvious. Differences in the magnitude of the increase were attributed to the different mean annual actual evapotranspiration rates for each land use type. The ensemble of model runs was further analyzed with deterministic and probabilistic ensemble methods. The deterministic ensemble method based on a trimmed mean resulted in a single somewhat more reliable scenario prediction. The probabilistic reliability ensemble averaging (REA) method allowed a quantification of the model structure uncertainty in the scenario predictions. It was concluded that the use of a model ensemble has greatly increased our confidence in the reliability of the model predictions.  相似文献   

Comparison of deterministic ensemble Kalman filters for assimilating hydrogeological data     

Alexander Y. Sun  Alan MorrisSitakanta Mohanty 《Advances in water resources》2009

Groundwater models are critical decision support tools for water resources management and environmental remediation. However, limitations in site characterization data and conceptual models can adversely affect the reliability of groundwater models. Therefore, there is a strong need for continuous model uncertainty reduction. Ensemble filters have recently emerged as promising high-dimensional data assimilation techniques. Two general categories of ensemble filters exist in the literature: perturbation-based and deterministic. Deterministic ensemble filters have been extensively studied for their better performance and robustness in assimilating oceanographic and atmospheric data. In hydrogeology, while a number of previous studies demonstrated the usefulness of the perturbation-based ensemble Kalman filter (EnKF) for joint parameter and state estimation, there have been few systematic studies investigating the performance of deterministic ensemble filters. This paper presents a comparative study of four commonly used deterministic ensemble filters for sequentially estimating the hydraulic conductivity parameter in low- and moderately high-dimensional groundwater models. The performance of the filters is assessed on the basis of twin experiments in which the true hydraulic conductivity field is assumed known. The test results indicate that the deterministic ensemble Kalman filter (DEnKF) is the most robust filter and achieves the best performance at relatively small ensemble sizes. Deterministic ensemble filters often make use of covariance inflation and localization to stabilize filter performance. Sensitivity studies demonstrate the effects of covariance inflation, localization, observation density, and conditioning on filter performance.  相似文献   

Regional Climate Change and Uncertainty Analysis based on Four Regional Climate Model Simulations over China   总被引：4，自引：0，他引：4       下载免费PDF全文

WU Jia  GAO Xue-Jie  XU Yin-Long  PAN Jie 《大气和海洋科学快报》2015,8(3):147-152

Four sets of climate change simulations at grid spacing of 50 km were conducted over East Asia with two regional climate models driven at the lateral boundaries by two global models for the period 1981–2050. The focus of the study was on the ensemble projection of climate change in the mid-21 st century(2031–50) over China. Validation of each simulation and the ensemble average showed good performances of the models overall, as well as advantages of the ensemble in reproducing present day(1981–2000) December–February(DJF), June–August(JJA), and annual(ANN) mean temperature and precipitation. Significant warming was projected for the mid-21 st century, with larger values of temperature increase found in the northern part of China and in the cold seasons. The ensemble average changes of precipitation in DJF, JJA, and ANN were determined, and the uncertainties of the projected changes analyzed based on the consistencies of the simulations. It was concluded that the largest uncertainties in precipitation projection are in eastern China during the summer season(monsoon precipitation).  相似文献