River flow forecasting through conceptual models part I — A discussion of principles☆
Abstract
The principles governing the application of the conceptual model technique to river flow forecasting are discussed. The necessity for a systematic approach to the development and testing of the model is explained and some preliminary ideas suggested.
References (3)
- N.H. Crawford et al.
A conceptual model of the hydrologic cycle
Int. Assoc. Sci. Hydr., Publ. No. 63
(1964)
Cited by (18022)
Development of a coupled model to simulate and assess arsenic contamination and impact factors in the Jinsha River Basin, China
2025, Journal of Environmental Sciences (China)With the increasing severity of arsenic (As) pollution, quantifying the environmental behavior of pollutant based on numerical model has become an important approach to determine the potential impacts and finalize the precise control strategies. Taking the industrial-intensive Jinsha River Basin as typical area, a two-dimensional hydrodynamic water quality model coupled with Soil and Water Assessment Tool (SWAT) model was developed to accurately simulate the watershed-scale distribution and transport of As in the terrestrial and aquatic environment at high spatial and temporal resolution. The effects of hydro-climate change, hydropower station construction and non-point source emissions on As were quantified based on the coupled model. The result indicated that higher As concentration areas mainly centralized in urban districts and concentration slowly decreased from upstream to downstream. Due to the enhanced rainfall, the As concentration was significantly higher during the rainy season than the dry season. Hydro-climate change and the construction of hydropower station not only affected the dissolved As concentration, but also affected the adsorption and desorption of As in sediment. Furthermore, As concentration increased with the input of non-point source pollution, with the maximum increase about 30%, resulting that non-point sources contributed important pollutant impacts to waterways. The coupled model used in pollutant behavior analysis is general with high potential application to predict and mitigate water pollution.
A combined deep CNN-RNN network for rainfall-runoff modelling in Bardha Watershed, India
2024, Artificial Intelligence in GeosciencesIn recent years, there has been a growing interest in using artificial intelligence (AI) for rainfall-runoff modelling, as it has shown promising adaptability in this context. The current study involved the use of six distinct AI models to simulate monthly rainfall-runoff modelling in the Bardha watershed, India. These models included the artificial neural network (ANN), k-nearest neighbour regression model (KNN), extreme gradient boosting (XGBoost) regression model, random forest regression model (RF), convolutional neural network (CNN), and CNN-RNN (convolutional recurrent neural network). The years 2003–2007 are classified as the calibration or training period, while the years 2008–2009 are classified as the validation or testing period for the span of time 2003 to 2009. The available rainfall, maximum and minimum temperatures, and discharge data were collected and utilized in the models. To compare the performance of the models, five criteria were employed: R2, NSE, MAE, RMSE, and PBIAS. The CNN-RNN model simulates the rainfall-runoff model in the Bardha watershed best in both the training and testing periods (training: R2 is 0.99, NSE is 0.99, MAE is 1.76, RMSE is 3.11, and PBIAS is −1.45; testing: R2 is 0.97, NSE is 0.97, MAE is 2.05, RMSE is 3.60, and PBIAS is −3.94). These results demonstrate the superior performance of the CNN-RNN model in simulating monthly rainfall-runoff modelling when compared to the other models used in the study. The findings suggest that the CNN-RNN model could be a valuable tool for various applications related to sustainable water resource management, flood control, and environmental planning.
Estimation of aquatic ecosystem health using deep neural network with nonlinear data mapping
2024, Ecological InformaticsEstimation of aquatic ecosystem health indices can assist in reducing the burden of time-consuming, labor-intensive, and cost-effective fieldwork for the sustainable evaluation of freshwater ecosystem status. In this study, we developed a deep neural network to estimate the trophic diatom index (TDI), benthic macroinvertebrate index (BMI), and fish assessment index (FAI) using water quality and hydraulic and hydrological data. A convolutional neural network (CNN) model was built to estimate health indices. In addition, an autoencoder was adopted to produce manifold features that were used as inputs for the CNN model. Conventional machine learning models, including artificial neural networks, support vector machines, random forests, and extreme gradient boosting, have been developed to estimate the TDI, BMI, and FAI. The results showed that the CNN with an autoencoder exhibited the best performance, with validation accuracies of Nash Sutcliffe Efficiency (NSE) and root mean squared error (RMSE) values of 0.592 and 17.249 for TDI, 0.669 and 12.282 for BMI, and 0.638 and 13.897 for FAI, respectively. The autoencoder enhanced the nonlinear feature learning of the time series and static input data, which contributed to improving the CNN feature extraction for accurate estimation of aquatic ecosystem health indices compared to other data-driven approaches. Therefore, deep learning techniques can be used to investigate aquatic ecosystem health by successfully reflecting the quantitative and qualitative features of health indices.
Toward an improved ensemble of multi-source daily precipitation via joint machine learning classification and regression
2024, Atmospheric ResearchAccurate estimation of precipitation at local to global scales can considerably enhance our understanding of climate system dynamics. While numerous precipitation products are available as indispensable tools for investigating precipitation and its associated processes, none can consistently provide the lowest estimation error across environmental conditions. The multiple source precipitation ensemble (MSPE) methods have been considered a vital solution. A new MSPE framework is proposed here, which simultaneously uses machine learning (ML) classification and regression techniques within an automatic workflow (MSPEaml). Six precipitation products and their ensembles based on different MSPE strategies were evaluated at 2365 gauged and 800 randomly selected ungauged sites over China. Results revealed significant precision inconsistencies among the products primarily due to their different data sources and retrieval algorithms; while MSPEaml can effectively reduce the random and classification errors of estimated precipitation according to the Kling-Gupta efficiency and Heidke skill score. The improvements demonstrated the unique features of MSPEaml, particularly the necessity of the joint use of ML classifiers and regressors and assigning spatiotemporal dynamic weights for merging precipitation data. Moreover, MSPEaml can substantially improve its generalizability through a simple binning procedure, making it applicable under more complex conditions. The varying contributions of predictor variables (indicated by Shapely values) in different ML models identified the complexity of the MSPE issue and further the importance of designing proper ML models according to specific targets. The proposed MSPE framework is expected to be a suitable solution for assembling multiple precipitation data sources with different time periods and scales.
Experimental study of wave trains generated by vertical bed movements
2024, Applied Ocean ResearchLaboratory experiments were conducted to explore the wave trains generated by vertical bed movements. The investigation consisted of 32 cases, involving four different water depths with unimodal and bimodal bed movements. Water surface displacement was measured using gauges positioned along a 30m long tank. A PIV system was set up to provide detailed measurement of the fluid velocity field in the vicinity of the bed movement. Generally, a unimodal movement generated a solitary-like wave, followed by a trailing sequence of waves. A bimodal bed movement induced a more complex flow field, with both the first and second extrema being significant. New analytical solutions have been derived, enabling the calculation of velocity fields. The nature of the wave generation and propagation were characterised using the disturbance-amplitude scale (α) and disturbance-size scale (δ). The applicability of linear theory was investigated, by validating the linear solutions of the generated waves against the experimental observations. For α ≤ 0.25, the analytical solutions were in good agreement with observations of the free surface shape, flow field and wave elevation history. For α ≥ 0.5, non-linearity became more pronounced, and the analytical solutions were only capable of reasonably estimating the amplitude of the first extremum in the vicinity of the moving bed. The initial crest maintained its amplitude and shape more effectively in crest-leading waves, whereas the leading trough decayed significantly in trough-leading waves. Non-linear phenomena were observed, such as wave breaking, air entrapment and twisted free surface. Bimodal bed movements with α ≥ 0.5 generated large, steep crests immediately following the initial trough in trough-leading waves.
Characteristics of glacier ice melt runoff in three sub-basins in Urumqi River basin, eastern Tien Shan
2024, Journal of Hydrology: Regional StudiesThe Urumqi River basin located in eastern Tien Shan in Central Aisa
Glacier runoff plays a pivotal role in water resources and stabilizing streamflow in mountainous regions. To assess the characteristics of glacier ice melt runoff in sub-basins within a single basin, three sub-basins with glacier ratios varying from 4% to 46% in the Urumqi River basin are investigated. Through the simulation by HBV light model on the basis of the observed meteorological and hydrological data. The characteristics and behaviour of glacier ice melt runoff in the three sub-basins are analysed.
It was found that both the contribution ratios of ice melt runoff and glacier runoff increase linearly with the increasing glacier ratio for the three catchments, rather than logarithmically or exponentially as observed in previous studies. This is due to the relatively high contributions of ice melt and glacier runoff to river flow in a catchment characterized by high elevation and extensive glacier coverage (Catchment 1), resulting from the coincidence of summer precipitation maxima with snow and ice melt in this region. The coefficient of variations (CV) of river flow tends to decrease with the decreasing glacier ratio in sub-basins in the Urumqi River basin, indicating that river flow becomes more stable as it flows farther from the headwater in the Urumqi River basin. The lowest glacierized Catchment 3 exhibited the minimum CV value, demonstrating a stable outflow.
- ☆
This is the first of a series of papers which it is hoped to publish from time to time reporting the results of the continuing work in this field of the Institute of Hydrology, Wallingford, Berkshire, U.K.