Accurate Runoff Estimation Research Articles

A hybrid rainfall-runoff model: integrating initial loss and LSTM for improved forecasting

Accurate rainfall-runoff modeling is crucial for disaster prevention, mitigation, and water resource management. This study aims to enhance precision and reliability in predicting runoff patterns by integrating physical-based models like HEC-HMS with data-driven models, such as LSTM. We present a novel hybrid model, Ia-LSTM, which combines the strengths of HEC-HMS and LSTM to improve hydrological modeling. By optimizing the “initial loss” (Ia) with HEC-HMS and utilizing LSTM to capture the effective rainfall-runoff relationship, the model achieves a substantial improvement in precision. Tested in the Yufuhe basin in Jinan City, Shandong province, the Ia-LSTM consistently outperforms individual HEC-HMS and LSTM models, achieving notable average Nash-Sutcliffe Efficiency (NSE) values of 0.873 and 0.829, and average R2 values of 0.916 and 0.870 for calibration and validation, respectively. The study shows the potential of integrating physical mechanisms to enhance the efficiency of data-driven rainfall-runoff modeling. The Ia-LSTM model holds promise for more accurate runoff estimation, with wide applications in flood forecasting, water resource management, and infrastructure planning.

Improving streamflow prediction using a new hybrid ELM model combined with hybrid particle swarm optimization and grey wolf optimization

Accurate runoff estimation is crucial for optimal reservoir operation and irrigation purposes. In this study, a novel hybrid method is proposed for monthly runoff prediction in Mangla watershed in northern Pakistan by integrating particle swarm optimization (PSO) and grey wolf optimization (GWO) with extreme learning machine (ELM) as ELM-PSOGWO. The proposed method was compared with the standalone ELM, hybrid of ELM-PSO, and binary hybrid PSOGSA (hybrid of PSO with gravitational search algorithm) methods. Monthly precipitation and runoff data were used as inputs to the models to examine their accuracy in terms of different statistical indexes. Test results showed that the proposed ELM-PSOGWO provided more accurate results than the standalone ELM, hybrid ELM-PSO, ELM-GWO nd binary hybrid PSOGSA methods in monthly runoff prediction. ELM-PSOGWO reduced the RMSE in prediction of ELM, ELM-PSO, ELM-GWO and ELM-PSOGSA by 38.2, 22.8, 22.4 and 16.7%, respectively. The PSO and GWO based ELM models also performed better than standalone ELM models, with an improvement in RMSE by 19.9 to 20.3%, respectively. Results also showed that adding precipitation as input enhanced the prediction accuracy of models. ELM-PSOGWO was also able to provide more precise estimates of peak runoff with the lowest absolute mean relative error compared to other methods. The results indicate the potential of ELM-PSOGWO model to be recommended for monthly runoff prediction.

Estimativa de escoamento em captação urbana utilizando modelos de rede neural artificial

Many types of physical models have been developed for runoff estimation with successful results. However, accurate runoff estimation remains a challenging problem owing to the lack of field data and the complexity of its hydrological process. In this paper, a machine learning method for runoff estimation is presented as an alternative approach to the physical model. Various types of input variables and Artificial Neural Network (ANN) architectures were examined in this study. Results showed that a two-layer network with the tansig activation function and the Levenberg–Marquardt learning algorithm had the best performance. For this architecture, the most effective input vector consists of a catchment perimeter, canal length, slope, runoff coefficient, and rainfall intensity. However, results of multivariate analysis of variance indicated the significant interaction effect of input data and the ANN architecture. Thus, to create a suitable ANN model for runoff estimation, a systematic determination of the input vector is necessary.

A Hybrid Approach Combining Conceptual Hydrological Models, Support Vector Machines and Remote Sensing Data for Rainfall-Runoff Modeling

Understanding catchment response to rainfall events is important for accurate runoff estimation in many water-related applications, including water resources management. This study introduced a hybrid model, the Tank-least squared support vector machine (LSSVM), that incorporated intermediate state variables from a conceptual tank model within the least squared support vector machine (LSSVM) framework in order to describe aspects of the rainfall-runoff (RR) process. The efficacy of the Tank-LSSVM model was demonstrated with hydro-meteorological data measured in the Yongdam Catchment between 2007 and 2016, South Korea. We first explored the role of satellite soil moisture (SM) data (i.e., European Space Agency (ESA) CCI) in the rainfall-runoff modeling. The results indicated that the SM states inferred from the ESA CCISWI provided an effective means of describing the temporal dynamics of SM. Further, the Tank-LSSVM model’s ability to simulate daily runoff was assessed by using goodness of fit measures (i.e., root mean square error, Nash Sutcliffe coefficient (NSE), and coefficient of determination). The Tank-LSSVM models’ NSE were all classified as “very good” based on their performance during the training and testing periods. Compared to individual LSSVM and Tank models, improved daily runoff simulations were seen in the proposed Tank-LSSVM model. In particular, low flow simulations demonstrated the improvement of the Tank-LSSVM model compared to the conventional tank model.

Potential implications of pre-storm soil moisture on hydrological prediction

Numerous hydrological models with various complexities, strengths, and weaknesses are available. Despite technological development, the association of runoff accuracy with the underlying model's parameters in watersheds with limited data remains elusive. Evaluating the soil moisture impacts at the watershed scale is often a difficult task, but it can be vital to optimally managing water resources. Incorporating pre-storm soil moisture accounting (PSMA) procedures into hydrologic models affects the watershed response to generate runoff from storm rainfall. This study demonstrated the impact of pre-storm and post-storm soil moisture in order to circumvent major obstacles in accurate runoff estimation from watersheds employing the conventional curve number (CN) model. The proposed hydrological lumped model was tested on a data set (1,804 rainfall-runoff events) from 39 watersheds in South Korea. Its superior performance indicates that the reconciliation of pre- and post-storm conceptualization has the potential to be a solution for efficient hydrological predictions and to demonstrate the complex and dynamic nature of tractable hydrological processes. The statistically significant results reveal that the proposed model can more effectively predict runoff from watersheds in the study area than the conventional CN model and its previously proposed modifications.

Simulating climate change scenarios using an improved K-nearest neighbor model

An improved weather-generating model that allows nearest neighbour resampling with perturbation of the historic data is applied to generate weather data based upon plausible climate scenarios. The intent is to create an ensemble of climate scenarios that can be used for the assessment of the vulnerability of a watershed to extreme events, including both floods and droughts. Analysis of the results clearly indicates that the model adequately simulated extreme unprecedented events for five different climate change scenarios. Based on the simulation results, the increasing precipitation scenario is identified as the critical scenario for the assessment of risks associated with the occurrence of floods in the basin. The increasing temperature scenario appears to be the critical scenario for the analysis of droughts in the basin. Frequency analysis was carried out to determine the impact of potential climatic change on the occurrence of storm depths of any given magnitude. A promising potential application of the model is in rainfall-runoff modelling where the storms depths could be related to the occurrence of extreme events in the basin. The proposed model, in conjunction with a rainfall-runoff model, has the potential of providing valuable aid in developing efficient management strategies for a watershed. The model produces spatially correlated data, which is crucial for accurate runoff estimation. Although the model is applied to the Upper Thames River Basin in the Canadian province of Ontario, it is generic and transportable to any other watershed with minimal changes.

GIUH based Clark and Nash models for runoff estimation for an ungauged basin and their uncertainty analysis

Runoff estimation is an important aspect of river basin planning, development and management. Geomorphological instantaneous unit hydrograph (GIUH) approach holds a great potential for estimation of runoff from ungauged basins because of its direct application to ungauged basins, without going for cumbersome procedure of regionalization. In this study, GIUH is derived from the geomorphological characteristics of a basin and it is related to the parameters of the Clark instantaneous unit hydrograph (IUH) model as well as Nash IUH model for deriving its complete shape. The developed GIUH based Clark and Nash models are applied for simulation of the direct surface runoff (DSRO) hydrographs for ten rainfall‐runoff events of the Ajay basin upto Sarath gauging site of eastern India. The geomorphological characteristics of the Ajay basin are evaluated using the GIS package, Integrated Land and Water Information System (ILWIS). A comparison of the performances of the GIUH based Clark and Nash models in simulating the DSRO hydrographs by employing some of the commonly used error functions reveals that the DSRO hydrographs are computed with reasonable accuracy by both the models, which simulate the DSRO hydrographs of the basin considering it to be ungauged. The relative sensitivity and the degree of uncertainty associated with each of the input parameters of the GIUH based Clark and Nash models have been quantified. The uncertainty analysis reveals that apart from the velocity (V) parameter, the length of the highest order stream (LO) is the only geomorphological parameter which results in higher degree of uncertainty in derivation of unit hydrograph using the GIUH based Clark and Nash models, and hence, it is to be evaluated with greater precision for accurate runoff estimation from ungauged basins.

Kalman Filter Empirical Fitting on Monthly Rainfall-Runoff Responses

The majority of the methods for fitting rainfall-runoff Kalman filters use the statistical characteristics of the input (rainfall) and the output (runoff) series according to the systems analysis and control theory methodology. The problem arising with these techniques is essentially related with their inabilityto describe variations of the basin runoff response when the relevant information concerning the causes of such variations is not contained into the input to the filter. The presented empirical method of fitting solves this problem by taking into account additional input information and improving the knowledge about the hydrological system, but without changing the simple two-variable structure of the filter. This information consists of the percentage of snowfall into the monthly basin rainfall, the magnitude of basin rainfall at month t in comparison to the rainfall at month t-1 (increasing, constant, or decreasing) and the amount of basin rainfall associated with basin's moisture and runoff characteristics. The Kalman filter empirically fitted on monthly rainfall-runoff responses of the Aliakmon and Acheloos river basins in Greece is shown to be more accurate and adequate than the automatically fitted filter by using conventional statistical methods. The filter has been used in hydroelectric energy studies of the area, where accurate runoff estimation from rainfall was necessary.