Supporting M5 model trees with sensitivity information derived from conceptual hydrological models

The main objective of this paper is assessing the usefulness of parameter sensitivity information from conceptual hydrological models for data-driven models, an approach which might allow us to take advantage of the strengths of both data-based and process-based models. This study uses the parameter sensitivity of three widely used conceptual hydrological models (GR4J, Hymod and SAC-SMA) and combines them with M5 model trees. The study was carried out for three case studies dealing with different problems to which model trees are applied: one using model trees as error correctors and two case studies in which model trees were used as rainfall–runoff models and which differ in how the sensitivity information is used. The results show that sensitivity time series can improve the predictions of M5 model trees, especially when they do not include the time series of previous discharge as predictor variables. The use of parameter sensitivity information for clustering the time series resulted in model trees that had a structure consistent with the hydrological processes that were taking place in the considered cluster, indicating that the use of sensitivity indices could be a viable way of introducing hydrological knowledge into data-based models.

Download Full-text

Identification of Hydrologic Models, Optimized Parameters, and Rainfall Inputs Consistent with In Situ Streamflow and Rainfall and Remotely Sensed Soil Moisture

Journal of Hydrometeorology ◽

10.1175/jhm-d-17-0240.1 ◽

2018 ◽

Vol 19 (8) ◽

pp. 1305-1320 ◽

Cited By ~ 6

Author(s):

Ashley J. Wright ◽

Jeffrey P. Walker ◽

Valentijn R. N. Pauwels

Keyword(s):

Time Series ◽

Soil Moisture ◽

Input Data ◽

Remotely Sensed ◽

Model Parameters ◽

Rainfall Time Series ◽

Hydrological Models ◽

Rainfall Runoff ◽

Model Input ◽

Rainfall Estimates

Abstract An increased understanding of the uncertainties present in rainfall time series can lead to improved confidence in both short- and long-term streamflow forecasts. This study presents an analysis that considers errors arising from model input data, model structure, model parameters, and model states with the objective of finding a self-consistent set that includes hydrological models, model parameters, streamflow, remotely sensed (RS) soil moisture (SM), and rainfall. This methodology can be used by hydrologists to aid model and satellite selection. Taking advantage of model input data reduction and model inversion techniques, this study uses a previously developed methodology to estimate areal rainfall time series for the study catchment of Warwick, Australia, for multiple rainfall–runoff models. RS SM observations from the Soil Moisture Ocean Salinity (SMOS) and Advanced Microwave Scanning Radiometer for Earth Observing System (AMSR-E) satellites were assimilated into three different rainfall–runoff models using an ensemble Kalman filter (EnKF). Innovations resulting from the observed and predicted SM were analyzed for Gaussianity. The findings demonstrate that consistency between hydrological models, model parameters, streamflow, RS SM, and rainfall can be found. Joint estimation of rainfall time series and model parameters consistently improved streamflow simulations. For all models rainfall estimates are less than the observed rainfall, and rainfall estimates obtained using the Sacramento Soil Moisture Accounting (SAC-SMA) model are the most consistent with gauge-based observations. The SAC-SMA model simulates streamflow that is most consistent with observations. EnKF innovations obtained when SMOS RS SM observations were assimilated into the SAC-SMA model demonstrate consistency between SM products.

Download Full-text

Evaluation of the appearing changes in water regime at Ráztoka and Červík basins in the Beskydy Mts.

Beskydy ◽

10.11118/beskyd201306020135 ◽

2013 ◽

Vol 6 (2) ◽

pp. 135-148

Author(s):

M. Tesař ◽

J. Buchtele

Keyword(s):

Time Series ◽

Water Regime ◽

Significant Contribution ◽

River Basins ◽

Hydrological Models ◽

Rainfall Runoff ◽

Clear Cutting ◽

Daily Time Series ◽

Large Floods ◽

Daily Time

The influence of vast salvage clear cutting in some hilly regions induced by acid rains is sometimes considered as a significant contribution to the disastrous character of the recent floods. Then the considerations having also partly emotional character, appeared, namely after large floods in the Morava and Odra Rivers in the July 1997 and in the Labe River basins in August 2002. The simulations of rainfall-runoff process for several experimental catchments have been carried out using daily time series up to 50 years long. The outputs of hydrological models SAC-SMA and BROOK´90 provide naturally the differences between observed and simulated discharge, which could show the tendencies in the runoff. They have been analysed and findings indicate the increases of runoff after deforestation. The differences between observed and simulated flows can be helpful also for the assessment of changes in evapotranspiration demands as the significant long-termed phenomenon.

Download Full-text

Rainfall-Runoff Modelling Using Hydrological Connectivity Index and Artificial Neural Network Approach

Water ◽

10.3390/w11020212 ◽

2019 ◽

Vol 11 (2) ◽

pp. 212 ◽

Cited By ~ 5

Author(s):

Haniyeh Asadi ◽

Kaka Shahedi ◽

Ben Jarihani ◽

Roy Sidle

Keyword(s):

Time Series ◽

Model Performance ◽

Connectivity Index ◽

Data Driven ◽

Hydrological Connectivity ◽

Rainfall Runoff ◽

Ann Model ◽

Climatic Parameters ◽

River Catchment ◽

Monthly Runoff

The input selection process for data-driven rainfall-runoff models is critical because input vectors determine the structure of the model and, hence, can influence model results. Here, hydro-geomorphic and biophysical time series inputs, including Normalized Difference Vegetation Index (NDVI) and Index of Connectivity (IC; a type of hydrological connectivity index), in addition to climatic and hydrologic inputs were assessed. Selected inputs were used to develop Artificial Neural Networks (ANNs) in the Haughton River catchment and the Calliope River catchment, Queensland, Australia. Results show that incorporating IC as a hydro-geomorphic parameter and remote sensing NDVI as a biophysical parameter, together with rainfall and runoff as hydro-climatic parameters, can improve ANN model performance compared to ANN models using only hydro-climatic parameters. Comparisons amongst different input patterns showed that IC inputs can contribute to further improvement in model performance, than NDVI inputs. Overall, ANN model simulations showed that using IC along with hydro-climatic inputs noticeably improved model performance in both catchments, especially in the Calliope catchment. This improvement is indicated by a slight increase (9.77% and 11.25%) in the Nash–Sutcliffe efficiency and noticeable decrease (24.43% and 37.89%) in the root mean squared error of monthly runoff from Haughton River and Calliope River, respectively. Here, we demonstrate the significant effect of hydro-geomorphic and biophysical time series inputs for estimating monthly runoff using ANN data-driven models, which are valuable for water resources planning and management.

Download Full-text

Experimental investigation of the predictive capabilities of data driven modeling techniques in hydrology - Part 2: Application

Hydrology and Earth System Sciences ◽

10.5194/hess-14-1943-2010 ◽

2010 ◽

Vol 14 (10) ◽

pp. 1943-1961 ◽

Cited By ~ 107

Author(s):

A. Elshorbagy ◽

G. Corzo ◽

S. Srinivasulu ◽

D. P. Solomatine

Keyword(s):

Soil Moisture ◽

Case Studies ◽

Data Driven ◽

Modeling Technique ◽

Actual Evapotranspiration ◽

Support Vector ◽

Rainfall Runoff ◽

Highly Nonlinear ◽

Modeling Techniques ◽

Data Driven Modeling

Abstract. In this second part of the two-part paper, the data driven modeling (DDM) experiment, presented and explained in the first part, is implemented. Inputs for the five case studies (half-hourly actual evapotranspiration, daily peat soil moisture, daily till soil moisture, and two daily rainfall-runoff datasets) are identified, either based on previous studies or using the mutual information content. Twelve groups (realizations) were randomly generated from each dataset by randomly sampling without replacement from the original dataset. Neural networks (ANNs), genetic programming (GP), evolutionary polynomial regression (EPR), Support vector machines (SVM), M5 model trees (M5), K-nearest neighbors (K-nn), and multiple linear regression (MLR) techniques are implemented and applied to each of the 12 realizations of each case study. The predictive accuracy and uncertainties of the various techniques are assessed using multiple average overall error measures, scatter plots, frequency distribution of model residuals, and the deterioration rate of prediction performance during the testing phase. Gamma test is used as a guide to assist in selecting the appropriate modeling technique. Unlike two nonlinear soil moisture case studies, the results of the experiment conducted in this research study show that ANNs were a sub-optimal choice for the actual evapotranspiration and the two rainfall-runoff case studies. GP is the most successful technique due to its ability to adapt the model complexity to the modeled data. EPR performance could be close to GP with datasets that are more linear than nonlinear. SVM is sensitive to the kernel choice and if appropriately selected, the performance of SVM can improve. M5 performs very well with linear and semi linear data, which cover wide range of hydrological situations. In highly nonlinear case studies, ANNs, K-nn, and GP could be more successful than other modeling techniques. K-nn is also successful in linear situations, and it should not be ignored as a potential modeling technique for hydrological applications.

Download Full-text

Evaluating Regional and Global Hydrological Models against Streamflow and Evapotranspiration Measurements

Journal of Hydrometeorology ◽

10.1175/jhm-d-15-0107.1 ◽

2016 ◽

Vol 17 (3) ◽

pp. 995-1010 ◽

Cited By ~ 35

Author(s):

Yongqiang Zhang ◽

Hongxing Zheng ◽

Francis H. S. Chiew ◽

Jorge Peña Arancibia ◽

Xinyao Zhou

Keyword(s):

Time Series ◽

Time Scale ◽

Land Surface ◽

Land Surface Model ◽

Daily Rainfall ◽

Surface Model ◽

Hydrological Models ◽

Rainfall Runoff ◽

Runoff Variability ◽

Global Water

Abstract Land surface and global hydrological models are often used to characterize global water and energy fluxes and stores and to model their future trajectories. This study evaluates estimates of streamflow and evapotranspiration (ET) obtained with a priori parameterization from a land surface model [CSIRO Atmosphere Biosphere Land Exchange (CABLE)] and a global hydrological model (H08) against a global dataset of streamflow from 644 largely unregulated catchments and ET from 98 flux towers and benchmarks their performance against two lumped conceptual daily rainfall–runoff models [modèle du Génie Rural à 4 paramètres Journalier (GR4J) and a simplified version of the HYDROLOG model (SIMHYD)]. The results show that all four models perform poorly in simulating the monthly and annual runoff values, with the rainfall–runoff models outperforming both CABLE and H08. The model biases in runoff are generally reflected as a complementary opposite bias in ET. All models can generally reproduce the observed seasonal and interannual runoff variability. The correlations between the modeled and observed runoff time series are reasonable, with the rainfall–runoff models performing slightly better than CABLE and H08 at the monthly time scale and all four models performing similarly at the annual time scale. The results suggest that while the land surface and global hydrological models cannot adequately simulate the actual runoff time series and long-term average volumes, they can reasonably simulate the monthly and interannual runoff variability and trends and can therefore be reliably used for broadscale or comparative regional and global water and energy balance assessments and simulations of future trajectories. They can be improved through validating the models or calibrating some of the more sensitive and less physically based parameters.

Download Full-text

Data mining based on wavelet and decision tree for rainfall-runoff simulation

Hydrology Research ◽

10.2166/nh.2018.049 ◽

2018 ◽

Vol 50 (1) ◽

pp. 75-84 ◽

Cited By ~ 7

Author(s):

Vahid Nourani ◽

Ali Davanlou Tajbakhsh ◽

Amir Molajou

Keyword(s):

Time Series ◽

Wavelet Transforms ◽

Rainfall Runoff ◽

Runoff Simulation ◽

M5 Model Tree ◽

Model Tree ◽

Four Seasons ◽

Runoff Modeling ◽

Training Stage ◽

M5 Model

Abstract This study introduced a new hybrid model (Wavelet-M5 model) which combines the wavelet transforms and M5 model tree for rainfall-runoff modeling. For this purpose, the main time series were decomposed to several sub-signals by the wavelet transform, at first. Then, the obtained sub-time series were imposed as input data to M5 model tree, and finally, the related linear regressions were presented by M5 model tree. This new technique was applied on the monthly time series of Sardrud catchment and the results were also compared with other models like WANN and sole M5 model tree. The results showed that the accuracy of the proposed model is better than the previous models and also indicated the effect of data pre-processing on the performance of M5 model tree. The determination coefficient of the training stage was 0.80 and improved 31% than the M5 model tree for Sardrud catchment which is recognized as a normal watershed with a regular four seasons' pattern.

Download Full-text

Experimental investigation of the predictive capabilities of data driven modeling techniques in hydrology – Part 2: Application

Hydrology and Earth System Sciences Discussions ◽

10.5194/hessd-6-7095-2009 ◽

2009 ◽

Vol 6 (6) ◽

pp. 7095-7142 ◽

Cited By ~ 6

Author(s):

A. Elshorbagy ◽

G. Corzo ◽

S. Srinivasulu ◽

D. P. Solomatine

Keyword(s):

Soil Moisture ◽

Case Studies ◽

Data Driven ◽

Modeling Technique ◽

Actual Evapotranspiration ◽

Support Vector ◽

Rainfall Runoff ◽

Highly Nonlinear ◽

Modeling Techniques ◽

Data Driven Modeling

Abstract. In this second part of the two-part paper, the data driven modeling (DDM) experiment, presented and explained in the first part, is implemented. Inputs for the five case studies (half-hourly actual evapotranspiration, daily peat soil moisture, daily till soil moisture, and two daily rainfall-runoff datasets) are identified, either based on previous studies or using the mutual information content. Twelve groups (realizations) were randomly generated from each dataset by randomly sampling without replacement from the original dataset. Neural networks (ANNs), genetic programming (GP), evolutionary polynomial regression (EPR), Support vector machines (SVM), M5 model trees (M5), K nearest neighbors (K-nn), and multiple linear regression (MLR) techniques are implemented and applied to each of the 12 realizations of each case study. The predictive accuracy and uncertainties of the various techniques are assessed using multiple average overall error measures, scatter plots, frequency distribution of model residuals, and the deterioration rate of prediction performance during the testing phase. Gamma test is used as a guide to assist in selecting the appropriate modeling technique. Unlike the two nonlinear soil moisture case studies, the results of the experiment conducted in this research study show that ANNs were a sub-optimal choice for the actual evapotranspiration and the two rainfall-runoff case studies. GP is the most successful technique due to its ability to adapt the model complexity to the modeled data. EPR performance could be close to GP with datasets that are more linear than nonlinear. SVM is sensitive to the kernel choice and if appropriately selected, the performance of SVM can improve. M5 performs very well with linear and semi linear data, which cover wide range of hydrological situations. In highly nonlinear case studies, ANNs, K-nn, and GP could be more successful than other modeling techniques. K-nn is also successful in linear situations, and it should not be ignored as a potential modeling technique for hydrological applications.

Download Full-text

Interactive comment on “Identifying rainfall-runoff events in discharge time series: A data-driven method based on Information Theory” by Stephanie Thiesen et al.

10.5194/hess-2018-427-rc1 ◽

2018 ◽

Author(s):

Yiwen Mei

Keyword(s):

Information Theory ◽

Time Series ◽

Data Driven ◽

Rainfall Runoff ◽

Discharge Time ◽

Runoff Events

Download Full-text

Practical experience and framework for sensitivity analysis of hydrological models: six methods, three models, three criteria

10.5194/hess-2018-78 ◽

2018 ◽

Cited By ~ 1

Author(s):

Anqi Wang ◽

Dimitri P. Solomatine

Keyword(s):

Sensitivity Analysis ◽

Comparative Analysis ◽

Practical Experience ◽

Ease Of Use ◽

Hydrological Models ◽

Rainfall Runoff ◽

Sensitivity Indices ◽

Kolmogorov Smirnov ◽

Better Than

Abstract. Sensitivity Analysis (SA) and Uncertainty Analysis (UA) are important steps for better understanding and evaluation of hydrological models. The aim of this paper is to briefly review main classes of SA methods, and to presents the results of the practical comparative analysis of applying them. Six different global SA methods: Sobol, eFAST, Morris, LH-OAT, RSA and PAWN are tested on three conceptual rainfall-runoff models with varying complexity: (GR4J, Hymod and HBV) applied to the case study of Bagmati basin (Nepal), and also initially tested on the case of Dapoling-Wangjiaba catchment in China. The methods are compared with respect to effectiveness, efficiency and convergence. A practical framework of selecting and using the SA methods is presented. The result shows that, first of all, all the six SA methods are effective. Morris and LH-OAT methods are the most efficient methods in computing SI and ranking. eFAST performs better than Sobol, thus can be seen as its viable alternative for Sobol. PAWN and RSA methods have issues of instability which we think are due to the ways CDFs are built, and using Kolmogorov-Smirnov statistics to compute Sensitivity Indices. All the methods require sufficient number of runs to reach convergence. Difference in efficiency of different methods is an inevitable consequence of the differences in the underlying principles. For SA of hydrological models, it is recommended to apply the presented practical framework assuming the use of several methods, and to explicitly take into account the constraints of effectiveness, efficiency (including convergence), ease of use, as well as availability of software.

Download Full-text