Accuracy Of Runoff Prediction Research Articles

Interpretable machine learning on large samples for supporting runoff estimation in ungauged basins

The distribution of flowmeter data and basin characteristic information exhibits substantial disparities, with most flow observations being recorded at a limited number of well-monitored locations. The perennial challenge of achieving reliable and robust hydrological modeling in ungauged catchments through regionalization has persisted. The increasing availability of large-scale hydrological datasets, coupled with recent advancements in machine learning techniques, offers new opportunities to explore patterns of association between basin attributes and hydrological parameters to enhance streamflow predictions. A novel parameter cross-regional transfer approach based on interpretable machine learning (XGBoost) is proposed to accurately predict runoff processes in ungauged regions by leveraging well-trained models across numerous basins within climate zones. We validate the effectiveness of this framework across 5,764 basins in a large sample dataset (Caravan), employing Nash-Sutcliffe Efficiency (NSE), RMSE and bias to assess performance. And a comparison is made with deep transfer learning based on LSTM and Transformer. Results indicate that the proposed method achieves NSE values exceeding 0.2 for 75 % of the ungauged basins, demonstrating superior performance and more stable accuracy compared to pure deep learning models, owing to its incorporation of physical constraints. Furthermore, the response of parameters to basin attributes within different climatic zones in the large-sample context is elucidated through SHAP values, enriching the understanding of hydrological features through data-driven inverse inference. These findings underscore the capability of interpretable machine learning to leverage hydro-physical regularities extracted from abundant basin features, thereby enhancing the accuracy of runoff predictions in ungauged regions.

Incorporating multiple grid-based data in CNN-LSTM hybrid model for daily runoff prediction in the source region of the Yellow River Basin

Study regionThe Source Region of the Yellow River Basin (SRYRB), China Study focusTo improve daily runoff prediction accuracy in data-scarce areas, this study focuses on incorporating multiple grid-based data (precipitation, EVI, soil moisture (SM)) to drive the CNN-LSTM hybrid model. The spatial features of precipitation and underlying surface of the basin can be extracted by CNN, while the temporal features of the input data series can be captured by the LSTM. The hybrid model is compared with the single models (CNN, LSTM), and hybrid model performances under different driven data are also investigated. New hydrological insights for the regionDriven by the in-situ precipitation, grid-based precipitation (GPM) and SM data, the CNN-LSTM hybrid model achieved the best prediction result with NSE of 0.834, outperforming the single LSTM model (NSE=0.510) and the CNN model (NSE=0.612). It indicates that the hybrid model captures the spatiotemporal change features of precipitation and underlying surface of the basin. When using only GPM and SM data as input, the hybrid model achieved comparable result with NSE of 0.827. It implies that GPM could serve as a good alternative of in-situ precipitation and SM could provide additional value to improve prediction. This study highlights the value of using multiple grid-based data to drive the hybrid model, which provides new insights into runoff prediction in data-scarce regions.

An ensemble model for monthly runoff prediction using least squares support vector machine based on variational modal decomposition with dung beetle optimization algorithm and error correction strategy

In order to enhance the runoff prediction accuracy, an ensemble prediction model based on least squares support vector machine (LSSVM) is proposed by including variational mode decomposition (VMD), dung beetle optimization algorithm (DBO), and error correction (EC) strategy. First, the monthly runoff time series is decomposed using DBO-optimized VMD (DVMD), yielding a series of intrinsic mode functions (IMF) series and a residual (Res). Then, the LSSVM based on DBO optimization predicts each sub-series column and residual. The final forecast results are achieved after the preliminary forecast results have been stacked and corrected by the DBO-LSSVM prediction error. To verify the reliability of the proposed model, it is applied to the monthly runoff prediction of the Xiajiang hydrological station in the Ganjiang River Basin, the Hongshanhe hydrological station in the Heihe River Basin, and the Jiayugaun hydrological station in the Heihe River Basin. The proposed model is evaluated using four evaluation indicators: RMSE, MAPE, NSEC, and R, and is compared with SVM, LSSVM, PSO-LSSVM, DBO-LSSVM, EEMD-LSSVM, CEEMDAN-LSSVM, DVMD-LSSVM, EEMD-DBO-LSSVM, CEEMDAN-DBO-LSSVM, and DVMD-DBO-LSSVM. Results show that the DVMD-DBO-LSSVM-EC model has the highest accuracy. During the test period, the NSEC of Xiajiang hydrological station is 0.9829, R is 0.9921, the NSEC of Hongshanhe hydrological station is 0.9981, R is 0.9991, and the NSEC of Jiayugaun hydrological station is 0.9772, R is 0.9897. The prediction effect of the model on the extreme value of the three stations after adding the error correction strategy has increased by 45.14%, 62.22%, and 29.49%, respectively, compared with the previous, which is closer to the actual value. The developed combination model offers a new approach to forecasting monthly runoff and extreme values.

Application, interpretability and prediction of machine learning method combined with LSTM and LightGBM-a case study for runoff simulation in an arid area

The runoff prediction can provide scientific basis for flood control, disaster reduction and water resources planning. Due to a large number of uncertainties in runoff prediction, it is difficult to make precise predictions. To improve the accuracy of runoff prediction, this study combines techniques of Long Short-Term Memory (LSTM) and Light Gradient Boosting Machine (LightGBM) in machine learning with reciprocal error method to develop an integrated data-driven model (i.e., LSTM-LightGBM) for runoff prediction. To demonstrate its applicability, the model is applied to the annual runoff prediction of the Caiqi hydrological monitoring station in the Shiyang River in an arid area. Indicators include Error of Peak (EP), Nash-Sutcliffe Efficiency (NSE), Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE) are adopted to evaluate the prediction performance of the LSTM, LightGBM, and LSTM-LightGBM methods under the same hyperparameter combinations. Then, the interpretability of LSTM and LightGBM models is also explored based on the permutation importance method and Shapley Additive exPlanations (SHAP) values, respectively. Finally, future annual runoff at the Caiqi for the next 50 years (2025–2075) is predicted based on LSTM-LightGBM model under 12 climate scenarios. Therefore, results show that: 1. the integrated model (LSTM-LightGBM) has good performance than two single models in NSE (0.92), RMSE (0.075 million m3) and MAE (0.046 million m3) and EP value (i.e., for bridging the peak-valley runoff). 2. In this case, it is found that four feature variables have the greatest influence on the target variables through the interpretable analysis. 3. The 12 combined climate scenarios used in this investigation produced generally steady predictions. The scenarios with the highest and lowest mean values are GFDL RCP 6.0 (3.12 × 108m3) and IPSL RCP 2.6 (3.04 × 108m3), respectively, with a decrease of 24.09 % and 26.03 % compared to the mean annual runoff of 4.11 × 108m3 in the baseline period (1955–2017). These findings can provide scientific bases for future water resources planning in the downstream of the Shiyang River Basin.

Improving Runoff Prediction Accuracy in a Mountainous Watershed Using a Remote Sensing-Based Approach

Due to the limited number and sparse distribution of meteorological and hydrometric stations in most watersheds, the runoff estimation based on these stations may not be accurate. However, the accurate determination of the Antecedent Soil Moisture (ASM) in watersheds can improve the accuracy of runoff forecasting. The objective of this study is to utilize the ASM derived from satellite imagery to enhance the accuracy of runoff estimation in a mountainous watershed. In this study, a range of Remote Sensing (RS) data, including surface biophysical and topographic features, climate data, hydrometric station flow data, and a ground-based measured SM database for the Balikhli-Chay watershed in Iran, were utilized. The Soil Conservation Service Curve Number (SCS-CN) method was employed to estimate runoff. Two approaches were used for estimating the ASM: (1) using the precipitation data recorded in ground stations, and (2) using the SM data obtained from satellite images. The accuracy of runoff estimation was then calculated for these two scenarios and compared. The mean Nash–Sutcliffe statistic was found to be 0.63 in the first scenario and 0.74 in the second scenario. The inclusion of ASM derived from the satellite imagery in the precipitation–runoff model resulted in a 51% increase in the accuracy of runoff estimation compared to using precipitation data recorded in ground stations. These findings have significant implications for improving the accuracy of ASM and runoff modeling in various applications.

Model and application of annual river runoff prediction based on complementary set empirical mode decomposition combined with particle swarm optimization adaptive neuro-fuzzy system

Abstract Runoff is affected by natural and nonnatural factors in the process of formation, and the runoff series is generally nonstationary time series. How to improve the accuracy of runoff prediction has always been a difficult problem for hydrologists. The key to solve this problem is to reduce the complexity of runoff series and improve the accuracy of runoff prediction model. Based on the aforementioned ideas, this article uses the complementary set empirical mode decomposition to decompose the runoff series into multiple intrinsic components that retain time–frequency information, thus reducing the complexity of the runoff series. The particle swarm optimization (PSO) adaptive neuro-fuzzy system is used to predict each intrinsic component to improve the accuracy of runoff prediction. After that, the trained intrinsic components of the model are reconstructed into the original runoff series. The example shows that the absolute relative error of the runoff forecasting model constructed in this article is 0.039, and the determination coefficient is 0.973. This model can be applied to the annual runoff series forecasting. Comparing the prediction results of this model with empirical mode decomposition algorithm-ANFIS model and ANFIS model, complementary set empirical mode decomposition algorithm-PSO-ANFIS model shows obvious advantages.

A fusion-based data assimilation framework for runoff prediction considering multiple sources of precipitation

ABSTRACT A fusion-based framework, in which a particle filter Markov chain Monte Carlo (PFMCMC) data assimilation method was coupled with the hydrological Sacramento Soil Moisture Accounting Model (SAC-SMA), was developed to improve the model’s capacity to predict one-day-ahead runoff. A case study was applied where mean daily precipitation from multiple sources served as forcing data in the data assimilation procedure, while ground station and multiple bias-corrected satellite-based precipitation datasets served as precipitation input datasets. The model training period used six years (2002–2007) of data to determine optimal weights through a genetic algorithm optimization model, while two years (2008–2009) were used to test the model. The proposed framework, applied to a real case study, improved SAC-SMA runoff prediction accuracy by incorporating precipitation datasets from multiple sources in the data assimilation procedure. On average, the PFMCMC-based data assimilation procedure led to a 13.7% improvement in SAC-SMA model performance metrics (NSE, MAB, RMSE, RMSRE, RMRE).

Application of a New Hybrid Deep Learning Model That Considers Temporal and Feature Dependencies in Rainfall–Runoff Simulation

Runoff forecasting is important for water resource management. Although deep learning models have substantially improved the accuracy of runoff prediction, the temporal and feature dependencies between rainfall–runoff time series elements have not been effectively exploited. In this work, we propose a new hybrid deep learning model to predict hourly streamflow: SA-CNN-LSTM (self-attention, convolutional neural network, and long short-term memory network). The advantages of CNN and LSTM in terms of data extraction from time series data are combined with the self-attention mechanism. By considering interdependences of the rainfall–runoff sequence between timesteps and between features, the prediction performance of the model is enhanced. We explored the performance of the model in the Mazhou Basin, China; we compared its performance with the performances of LSTM, CNN, ANN (artificial neural network), RF (random forest), SA-LSTM, and SA-CNN. Our analysis demonstrated that SA-CNN-LSTM demonstrated robust prediction with different flood magnitudes and different lead times; it was particularly effective within lead times of 1–5 h. Additionally, the performance of the self-attention mechanism with LSTM and CNN alone, respectively, was improved at some lead times; however, the overall performance was unstable. In contrast, the hybrid model integrating CNN, LSTM, and the self-attention mechanism exhibited better model performance and robustness. Overall, this study considers the importance of temporal and feature dependencies in hourly runoff prediction, then proposes a hybrid deep learning model to improve the performances of conventional models in runoff prediction.

Transfer performance of gated recurrent unit model for runoff prediction based on the comprehensive spatiotemporal similarity of catchments

Accurate runoff prediction in data-poor catchments is important for water resource management, flood mitigation, environmental protection, and other tasks. One possible solution is to transfer a runoff prediction model constructed by using a machine learning model for gauged catchments to data-poor catchments. However, the transfer of runoff prediction model must consider the comprehensive spatiotemporal similarities between the catchments; otherwise, the transfer performance can be massively uncertain. Therefore, to improve the accuracy of runoff prediction and eliminate the uncertainty in identifying the differences between catchment environments, this paper proposes a novel measurement approach of comprehensive spatiotemporal similarity. This approach measures the similarities among catchments by fully considering which of the various catchments' spatiotemporal attributes can better represent the geographical similarity. Then, according to the similarities between the catchments, a runoff prediction model trained in gauged catchments is transformed for the most similar data-poor catchments to predict the runoff and the transfer performance is analyzed. To this end, a runoff prediction model is built using a gated recurrent unit (GRU) network based on the CAMELS catchments data set. A framework to extract the comprehensive spatiotemporal features of catchments is designed using three autoencoders. The catchments' similarities can be measured, further, and their spatiotemporal attributes determined once a measurement model of comprehensive spatiotemporal similarity is constructed. Finally, the transfer performance of the GRU runoff prediction model based on comprehensive spatiotemporal and other geographical similarities is evaluated and analyzed. The experimental results demonstrate that the proposed method outperforms comparable approaches.

Stacking ensemble learning models for daily runoff prediction using 1D and 2D CNNs

In recent years, applications of convolutional neural networks (CNNs) to runoff prediction have received some attention due to their excellent feature extraction capabilities. However, existing studies are still limited since merely either 1D or 2D CNNs are developed to predict runoff. In this study, a stacking ensemble learning model for daily runoff prediction based on different types of 1D and 2D CNNs is proposed and applied to the Quinebaug River Basin, Connecticut, USA. The structure of the CNN models is developed with reference to the classic LeNet5 network. Especially, the predictors are reconstructed into 1D vectors and 2D matrices with 10-, 20- and 30-day time steps. Totally 18 member models are constructed through selecting 3 representative 1D and 2D CNN models with 3 time steps. The simple average method (SAM) is used to integrate different CNN member models. The results show that the performance of the same-type SAM based on either 1D or 2D CNNs improves because it can counteract the effects of both positive and negative predicted values by the member models to some extent. Furthermore, the mixed-type SAM models based on both 1D and 2D CNN member models can further improve the prediction accuracy. The optimal model SAM15 consists of two 1D CNNs and four 2D CNNs. Compared with the optimal CNN member models, SAM15 reduces the validation RMSE by about 13% and improves the validation R and NSE by about 3% and 7%, respectively. This study highlights that the proposed stacking ensemble learning model can improve the daily runoff prediction accuracy through integration of the nonlinear fitting ability of 1D and 2D CNN member models.

Combining Standard Artificial Intelligence Models, Pre-Processing Techniques, and Post-Processing Methods to Improve the Accuracy of Monthly Runoff Predictions in Karst-Area Watersheds

The complex and unique topography of karst regions highlights the weaknesses of traditional hydrological models which fail to fully generalize them. The successive proposals of standard artificial intelligence (AI) models, pre-processing techniques, and post-processing methods have provided new opportunities to enhance the accuracy of runoff prediction in karst areas. In this study, first, the BP neural network model and the Elman neural network model were used for runoff prediction. Then, the performance of four coupled models—formed by combining two AI pre-processing techniques, Empirical Modal Decomposition (EMD) and Ensemble Empirical Modal Decomposition (EEMD), with the previously mentioned AI models—was investigated. Finally, the accuracy of triple-coupled models, formed by applying the post-processing method of quantile mapping (QM) to the previous coupled models, was estimated. The Nash–Sutcliffe efficiency (NSE), the mean absolute percentage error (MAPE), the root mean square error (RMSE), and the peak percentage of threshold statistics (PPTS) were selected to evaluate and analyze the forecasting results of the above models. The results demonstrated that the BP model had the best prediction effect of the standard AI models, the coupled forecasting models had better prediction accuracy than the standard AI models, and the triple-coupled QM–EMD–Elman model had the best forecasting effect with an NSE value of 0.73, MAPE value of 0.75, RMSE value of 34.60, and PPTS value of 2.36.

Using thermal UAV imagery to model distributed debris thicknesses and sub-debris melt rates on debris-covered glaciers

AbstractSupraglacial debris cover regulates the melt rates of many glaciers in mountainous regions around the world, thereby modifying the availability and quality of downstream water resources. However, the influence of supraglacial debris is often poorly represented within glaciological models, due to the absence of a technique to provide high-precision, spatially continuous measurements of debris thickness. Here, we use high-resolution UAV-derived thermal imagery, in conjunction with local meteorological data, visible UAV imagery and vertically profiled debris temperature time series, to model the spatially distributed debris thickness across a portion of Llaca Glacier in the Cordillera Blanca of Peru. Based on our results, we simulate daily sub-debris melt rates over a 3-month period during 2019. We demonstrate that, by effectively calibrating the radiometric thermal imagery and accounting for temporal and spatial variations in meteorological variables during UAV surveys, thermal UAV data can be used to more precisely represent the highly heterogeneous patterns of debris thickness and sub-debris melt on debris-covered glaciers. Additionally, our results indicate a mean sub-debris melt rate nearly three times greater than the mean melt rate simulated from satellite-derived debris thicknesses, emphasising the importance of acquiring further high-precision debris thickness data for the purposes of investigating glacier-scale melt processes, calibrating regional melt models and improving the accuracy of runoff predictions.

Climate-informed monthly runoff prediction model using machine learning and feature importance analysis

Accurate runoff prediction can provide a reliable decision-making basis for flood and drought disaster prevention and scientific allocation of water resources. Selecting appropriate predictors is an effective way to improve the accuracy of runoff prediction. However, the runoff process is influenced by numerous local and global hydrometeorological factors, and there is still no universal approach about the selection of suitable predictors from these factors. To address this problem, we proposed a runoff prediction model by combining machine learning (ML) and feature importance analysis (FIA-ML). Specifically, take the monthly runoff prediction of Yingluoxia, China as an example, the FIA-ML model uses mutual information (MI) and feature importance ranking method based on random forest (RF) to screen suitable predictors, from 130 global climate factors and several local hydrometeorological information, as the input of ML models, namely the hybrid kernel support vector machine (HKSVM), extreme learning machine (ELM), generalized regression neural network (GRNN), and multiple linear regression (MLR). An improved particle swarm optimization (IPSO) is used to estimate model parameters of ML. The results indicated that the performance of the FIA-ML is better than widely-used long short-term memory neural network (LSTM) and seasonal autoregressive integrated moving average (SARIMA). Particularly, the Nash-Sutcliffe Efficiency coefficients of the FIA-ML models with HKSVM and ELM were both greater than 0.9. More importantly, the FIA-ML models can explicitly explain which physical factors have significant impacts on runoff, thus strengthening the physical meaning of the runoff prediction model.

Monthly Runoff Interval Prediction Based on Fuzzy Information Granulation and Improved Neural Network

High-precision monthly runoff prediction results are of great significance to regional water resource management. However, with the changes in human activity, climate, and underlying surface conditions, the runoff sequence presents highly nonlinear and random characteristics. In order to improve the accuracy of runoff prediction, this study proposed a runoff prediction model based on fuzzy information granulation (FIG) and back propagation neural network (BPNN) improved with genetic algorithm (FIG-GA-BP). First, FIG was used to process the original runoff data to generate three sequences of minimum, average, and maximum that can reflect the rule of runoff changes. Then, genetic algorithms (GA) were used to obtain the optimal initial weights and thresholds of the BPNN through selection, crossover, and mutation. Finally, BPNN was used to predict the generated three sequences separately to obtain the prediction interval. The proposed model was applied to the monthly runoff interval prediction of Linjiacun and Weijiabu hydrological stations in the main stream of the Wei River and Zhangjiashan hydrological station on Jing River, a tributary of the Wei River. Compared with the interval prediction model FIG-BP, FIG-WNN, and traditional BP model. The results show that the FIG-GA-BP interval prediction model had a good prediction effect, with higher prediction accuracy and a narrower range of prediction intervals. Therefore, this model has superiority and practicability in monthly runoff interval prediction.

LSTM-Based Model for Predicting Inland River Runoff in Arid Region: A Case Study on Yarkant River, Northwest China

Inland river runoff variations in arid regions play a decisive role in maintaining regional ecological stability. Observation data of inland river runoff in arid regions have short time series and imperfect attributes due to limitations in the terrain environment and other factors. These shortages not only restrict the accurate simulation of inland river runoff in arid regions significantly, but also influence scientific evaluation and management of the water resources of a basin in arid regions. In recent years, research and applications of machine learning and in-depth learning technologies in the hydrological field have been developing gradually around the world. However, the simulation accuracy is low, and it often has over-fitting phenomenon in previous studies due to influences of complicated characteristics such as “unsteady runoff”. Fortunately, the circulation layer of Long-Short Term Memory (LSTM) can explore time series information of runoffs deeply to avoid long-term dependence problems. In this study, the LSTM algorithm was introduced and improved based on the in-depth learning theory of artificial intelligence and relevant meteorological factors that were monitored by coupling runoffs. The runoff data of the Yarkant River was chosen for training and test of the LSTM model. The results demonstrated that Mean Absolute Error (MAE) and Root Mean Square error (RMSE) of the LSTM model were 3.633 and 7.337, respectively. This indicates that the prediction effect and accuracy of the LSTM model were significantly better than those of the convolution neural network (CNN), Decision Tree Regressor (DTR) and Random Forest (RF). Comparison of accuracy of different models made the research reliable. Hence, time series data was converted into a problem of supervised learning through LSTM in the present study. The improved LSTM model solved prediction difficulties in runoff data to some extent and it applied to hydrological simulation in arid regions under several climate scenarios. It not only decreased runoff prediction uncertainty brought by heterogeneity of climate models and increased inland river runoff prediction accuracy in arid regions, but also provided references to basin water resource management in arid regions. In particular, the LSTM model provides an effective solution to runoff simulation in regions with limited data.

The value of satellite soil moisture and snow cover data for the transfer of hydrological model parameters to ungauged sites

Abstract. The recent advances in remote sensing provide opportunities for estimating the parameters of conceptual hydrologic models more reliably. However, the question of whether and to what extent the use of satellite data in model calibration may assist in transferring model parameters to ungauged catchments has not been fully resolved. The aim of this study is to evaluate the efficiency of different methods for transferring model parameters obtained by multiple-objective calibrations to ungauged sites and to assess the model performance in terms of runoff, soil moisture, and snow cover predictions relative to existing regionalization approaches. The model parameters are calibrated to daily runoff, satellite soil moisture (Advanced Scatterometer – ASCAT), and snow cover (Moderate Resolution Imaging Spectroradiometer – MODIS) data. The assessment is based on 213 catchments situated in different physiographic and climate zones of Austria. For the transfer of model parameters, eight methods (global and local variants of arithmetic mean, regression, spatial proximity, and similarity) are examined in two periods, i.e., the period in which the model is calibrated (2000–2010) and an independent validation period (2010–2014). The predictive accuracy is evaluated by the leave-one-out cross-validation. The results show that the method by which the model is calibrated in the gauged catchment has a larger impact on runoff prediction accuracy in the ungauged catchments than the choice of the parameter transfer method. The best transfer methods are global and local similarity and the kriging approach. The performance of the transfer methods differs between lowland and alpine catchments. While the soil moisture and snow cover prediction efficiencies are higher in lowland catchments, the runoff prediction efficiency is higher in alpine catchments. A comparison of the model transfer methods, based on parameters calibrated to runoff, snow cover, and soil moisture with those based on parameters calibrated to runoff, only indicates that the former outperforms the latter in terms of simulating soil moisture and snow cover. The performance of simulating runoff is similar, and the accuracy depends mainly on the weight given to the runoff objective in the multiple-objective calibrations.

Which one is more important in daily runoff forecasting using data driven models: Input data, model type, preprocessing or data length?

Rainfall-runoff modeling is of great importance in hydrological sciences. Several different models have been developed for runoff modeling in three main categories i.e. physically-based, conceptual and empirical models. Data driven models are of the most widely used models in runoff modeling besides process based models. Different studies have been done to assess the performance of various models and the effect of input datasets, data length and disparate signal processing methods on the modeling performance. However, each of these studies has examined one of these factors separately and didn’t assess the effect of these factors on the accuracy of runoff forecasting. Therefore, assessing the importance of each of the mentioned factors as well as determining the optimum structure that produces the best accuracy is still challenging. The main aim of this study was to determine the importance and the optimal combination of these factors in daily runoff modeling. In order to achieve this goal, Taguchi method was used. First, five levels were defined for each of the abovementioned factors. Five different input data combinations, five data driven models i.e. Adaptive Neuro-Fuzzy Inference System (ANFIS), Support Vector Regression (SVR), Group Method of Data Handling (GMDH), Random Forest (RF) and Partial Least Square Regression (PLS), four different signal processing methods i.e. normalization, wavelet, ensemble empirical mode decomposition (EEMD) andsingular spectrum analysis(SSA) as well as no pre-processing condition, and five data lengths i.e. 2, 5, 10, 15 and 20 years were considered. The L25 Taguchi orthogonal array was selected accordingly. The required 25 tests were implemented according to the L25 Taguchi orthogonal array in three different basins to achieve more generalizable results. The results were then used in Taguchi analysis in order to attain the optimal combination of the levels of the mentioned factors and the importance of these factors in accurate prediction of runoff. Results showed that the hybrid wavelet-GMDH model with a complete dataset as input and 20-year data length provides the highest accuracy. It was also shown that the order of mentioned factors in terms of their importance and effect on runoff prediction accuracy is as follow: input dataset, data length, preprocessing and model type. GMDH and SVR had the best performance and wavelet and EEMD signal processing methods had the highest effect on the data driven models performance.

Effects of initial abstraction ratios in SCS-CN method on runoff prediction of green roofs in a semi-arid region

The widespread adoption of green roof technology in urban stormwater management practices requires the use of adequate modelling and evaluating tools. Soil Conservation Service-Curve Number (SCS-CN) method is the most common adopted and simple method for runoff prediction of green roofs. However, the standard initial abstraction ratio is the most ambiguous assumption and requires dedicated adjustments in runoff prediction. In this study, the initial abstraction ratios of green roofs in SCS-CN method were determined using rainfall-runoff event analysis from the simulated rainfall experiments for runoff plots of green roofs. Influences of the standard and modified initial abstraction ratios on runoff estimation of green roofs were investigated and evaluated. Results showed that the calculated Ia/S ratios varied from 0.18 to 0.89, with a median of 0.51. The SCS-CN method for initial abstraction ratios using 0.5 and 0.2 values were underestimated runoff volume, thus they were not appropriately used for runoff prediction of green roofs. However, evaluated results revealed that runoff prediction using Ia/S = 0.05 was significantly improved than that predicted using Ia/S = 0.2. The estimation of green roof runoff using Ia/S = 0.05 provided the best model efficiency MAE, RMSE, NSE and WI among the predictions using the modified initial abstraction ratios of 0.2, 0.5, 0.05 and 0.02. Particularly, the NSE and WI values of Ia/S = 0.05 were improved to 0.88 and 0.97 respectively. Accordingly, the median CN value was modified to 96 while using Ia/S = 0.05. A significantly negative relationship was found between antecedent substrate moisture and Ia/S ratios of green roofs. These results suggested that an optimal initial abstraction ratio of 0.05 with modified CN values used in the SCS-CN method can highly improve the accuracy of runoff prediction for green roofs.

An adaptive daily runoff forecast model using VMD-LSTM-PSO hybrid approach

ABSTRACT To cope with the nonlinear and nonstationarity challenges faced by conventional runoff forecasting models and improve daily runoff prediction accuracy, a hybrid model-based “feature decomposition-component prediction-result reconstruction” named VMD-LSTM-PSO was proposed. First, variational mode decomposition (VMD) was used to decompose the original daily runoff series into a discrete number of intrinsic mode functions (IMFs) to produce clearer signals. Then, for each IMF, a long short-term memory (LSTM) network was applied to establish the prediction model, and a particle swarm optimization (PSO) algorithm was utilised to optimise the number of hidden layer nodes and the learning rate of the LSTM. The model was applied in three hydrologic stations in the main stream of the Yellow River of China and compared with the complementary ensemble empirical mode decomposition coupled long short-term memory and particle swarm optimization (CEEMD-LSTM-PSO), wavelet transform coupled long short-term memory and particle swarm optimization (WT-LSTM-PSO) and LSTM-PSO models. Based on its high predictive accuracy and stability, the novel model promises to be a preferred data-driven tool for hydrological forecasting in practice.

Evaluation and Application of Quantitative Precipitation Forecast Products for Mainland China Based on TIGGE Multimodel Data

AbstractWe evaluated 24-h control forecast products from The International Grand Global Ensemble center over the 10 first-class water resource regions of Mainland China in 2013–18 from the perspective of precipitation processes (continuous) and precipitation events (discrete). We evaluated the forecasts from the China Meteorological Administration (CMA), the Centro de Previsão de Tempo e Estudos Climáticos (CPTEC), the Canadian Meteorological Centre (CMC), the European Centre for Medium-Range Weather Forecasts (ECMWF), the Japan Meteorological Agency (JMA), the Korea Meteorological Administration (KMA), the United Kingdom Met Office (UKMO), and the National Centers for Environmental Prediction (NCEP). We analyzed the differences among the numerical weather prediction (NWP) models in predicting various types of precipitation events and showed the spatial variations in the quantitative precipitation forecast efficiency of the NWP models over Mainland China. Meanwhile, we also combined four hydrological models to conduct meteo-hydrological runoff forecasting in three typical basins and used the Bayesian model averaging (BMA) method to perform the ensemble forecast of different scenarios. Our results showed that the models generally underestimate and overestimate precipitation in northwestern China and southwestern China, respectively. This tendency became increasingly clear as the lead time rose. Each model has a high reliability for the forecast of no-rain and light rain in the next 10 days, whereas the NWP model only has high reliability on the next day for moderate and heavy rain events. In general, each model showed different capabilities of capturing various precipitation events. For example, the CMA and CMC forecasts had a better prediction performance for heavy rain but greater errors for other events. The CPTEC forecast performed well for long lead times for no-rain and light rain but had poor predictability for moderate and heavy rains. The KMA, UKMO, and NCEP forecasts performed better for no-rain and light rain. However, their forecasting ability was average for moderate and heavy rain. Although the JMA model performed better in terms of errors and accuracy, it seriously underestimated heavy rain events. The extreme rainstorm and flood forecast results of the coupled JMA model should be treated with caution. Overall, the ECMWF had the most robust performance. Discrepancies in the forecasting effects of various models on different precipitation events vary with the lead time and region. When coupled with hydrological models, NWP models not only control the accuracy of runoff prediction directly but also increase the difference among the prediction results of different hydrological models with the increase in NWP error significantly. Among all the single models, ECMWF, JMA, and NCEP have better effects than the other models. Moreover, the ensemble forecast based on BMA is more robust than the single model, which can improve the quality of runoff prediction in terms of accuracy and reliability.