Search

Different conclusions have been drawn in literature as using reanalysis rainfall products to drive hydrological models for the simulation of streamflow, which warrant a need of further investigation before a generalised conclusion can be drawn. This paper assesses the utility of two widely used reanalysis rainfall datasets (WFD (developed by the WATCH project) and APHRODITE (Asian Precipitation–Highly-Resolved Observational Data Integration Towards Evaluation of the water resources)) against the gauged rainfall in terms of flood simulation in lumped (Xinanjiang Model) and distributed (SWAT Model) hydrological models in a tributary basin of Yangtze River with 94,660 km 2 drainage area in humid region of southern China. Differences in terms of rainfall accumulation, number of rainy days, spatial patterns of the rainfall amount and frequency distribution of the rain rates are evaluated. The APHRODITE product shows high consistency with the gauged rainfall while WFD data gives large errors in various statistical indices in the study region. Simulated discharges from the gauged and reanalysis rainfall data, respectively, are analysed and compared with the observed discharge in basin outlet over the period 1991–2005. The APHRODITE data show relatively high ability in modelling hydrological responses while the WFD data based models give large error in simulating the discharge. For the assessment of the high flows, both datasets exhibit some skills in flood prediction, however, APHRODITE data perform better than the WFD data when forcing into the lumped Xinanjiang Model than into the distributed SWAT Model in terms of flood duration, Probability of Detection, False Alarm Rate, regressions of annual peaks and partial duration series. [ABSTRACT FROM AUTHOR]

• Intelligent adaptation parameter method improves the hydrological model performance. • LightGBM builds flood characteristics-parameter intelligent adaptation relationship. • The XAJ-IAP model can provide accurate and reliable flood simulation. • LightGBM analysis reveals importance of flood characteristics and parameters. Traditional hydrological modeling methods use a set of parameters to simulate flood processes with complex causes and variable intensity, which can easily lead to parameter instability. To address the problem of parameter instability, this study proposes an approach integrating the hydrological model with Intelligent Adaptation Parameters (IAP), whose intelligent adaptation relationship is established by the light gradient-boosting machine (LightGBM) based on individual calibration parameters by each flood event and flood characteristics including flood-caused rainstorm information and initial soil moisture. A widely used hydrological model, Xin 'anjiang (XAJ) model, is chosen to be integrated with IAP (XAJ-IAP) in this study, which has a relatively complex structure and a total of 15 model parameters. The obtained findings demonstrate that: (1) recalibrating the sensitive runoff concentration and separation parameters with a single flood leads to a notable enhancement in simulation accuracy, while simultaneously considering the model's physical significance; (2) the XAJ overestimates large floods and underestimates small floods. Compared with the XAJ, the XAJ-IAP has a better rain-flood response relationship and simulation accuracy for floods of different magnitudes, solving the problem of parameter instability that exists in XAJ; and (3) evaluated in terms of information gain, sensitive parameters contribute the most to the establishment of the intelligent adaptation relationship in the LightGBM compared to flood-caused rainstorm information and initial soil moisture, indicating that sensitive parameters are the most important input features of the LightGBM. It can be concluded that the intelligent adaptation system can not only solve the problem of parameter instability that exists when traditional hydrological models simulate complex and changeable floods, but also further reveal the relationship between the model and floods. [ABSTRACT FROM AUTHOR]

• Machine learning assists hybrid model to promote flood forecasting and early warning. • Hybridizing MCQRNN with XAJ model for flood probability density forecasting. • XAJ-MCQRNN conquers overfitting and biased-prediction bottlenecks. • XAJ-MCQRNN improves accuracy and reliability of flood probability density forecasts. Making accurate and reliable probability density forecasts of flood processes is fundamentally challenging for machine learning techniques, especially when prediction targets are outside the range of training data. Conceptual hydrological models can reduce rainfall-runoff modelling errors with efficient quasi-physical mechanisms. The Monotone Composite Quantile Regression Neural Network (MCQRNN) is used for the first time to make probability density forecasts of flood processes and serves as a benchmark model, whereas it confronts the drawbacks of overfitting and biased-prediction. Here we propose an integrated model (i.e. XAJ-MCQRNN) that incorporates Xinanjiang conceptual model (XAJ) and MCQRNN to overcome the phenomena of error propagation and accumulation encountered in multi-step-ahead flood probability density forecasts. We consider flood forecasts as a function of rainfall factors and runoff data. The models are evaluated by long-term (2009–2015) 3-hour streamflow series of the Jianxi River catchment in China and rainfall products of the European Centre for Medium-Range Weather Forecasts. Results demonstrated that the proposed XAJ-MCQRNN model can not only outperform the MCQRNN model but also prominently enhance the accuracy and reliability of multi-step-ahead probability density forecasts of flood process. Regarding short-term forecasts in testing stages at four horizons, the XAJ-MCQRNN model achieved higher Nash-Sutcliffe Efficiency but lower Root Mean Square Error values, while improving Coverage Ratio and Relative Bandwidth values in comparison to the MCQRNN model. Consequently, the improvement can benefit the mitigation of the impacts associated with uncertainties of extreme flood and rainfall events as well as promote the accuracy and reliability of flood forecasting and early warning. [ABSTRACT FROM AUTHOR]