Runoff Prediction Based on the Discharge of Pump Stations in an Urban Stream Using a Modified Multi-Layer Perceptron Combined with Meta-Heuristic Optimization

Runoff in urban streams is the most important factor influencing urban inundation. It also affects inundation in other areas as various urban streams and rivers are connected. Current runoff predictions obtained using a multi-layer perceptron (MLP) exhibit limited accuracy. In this study, the runoff of urban streams was predicted by applying an MLP using a harmony search (MLPHS) to overcome the shortcomings of MLPs using existing optimizers and compared with the observed runoff and the runoff predicted by an MLP using a real-coded genetic algorithm (RCGA). Furthermore, the results of the MLPHS were compared with the results of the MLP with existing optimizers such as the stochastic gradient descent, adaptive gradient, and root mean squared propagation. The runoff of urban steams was predicted based on the discharge of each pump station and rainfall information. The results obtained with the MLPHS exhibited the smallest error of 39.804 m3/s when compared to the peak value of the observed runoff. The MLPHS gave more accurate runoff prediction results than the MLP using the RCGA and that using existing optimizers. The accurate prediction of the runoff in an urban stream using an MLPHS based on the discharge of each pump station is possible.

Prediction of annual runoff using Artificial Neural Network and Regression approaches

Prediction of runoff is often important for optimal design of water storage and drainage works andmanagement of extreme events like floods and droughts. Rainfall-runoff (RR) models are considered to be most effectiveand expedient tool for runoff prediction. Number of models like stochastic, conceptual, deterministic, black-box, etc. iscommonly available for RR modelling. This paper details a study involving the use of Artificial Neural Network (ANN)and Regression (REG) approaches for prediction of runoff for Betwa and Chambal regions. Model performanceindicators such as model efficiency, correlation coefficient, root mean square error and root mean absolute error are usedto evaluate the performance of ANN and REG for runoff prediction. Statistical parameters are employed to find theaccuracy in prediction by ANN and REG for the data under study. The paper presents that ANN approach is found to besuitable for prediction of runoff for Betwa and Chambal regions.

Surface runoff prediction and comparison using IHACRES and GR4J lumped models in the Mono catchment, West Africa

This study aims to assess simulated surface runoff before and after dam construction in the Mono catchment (West Africa) using two lumped models: GR4J (Rural Engineering with 4 Daily Parameters) and IHACRES (Identification of unit Hydrographs and Component flows from Rainfall, Evapotranspiration and Stream data) over two different periods (1964–1986 and 1988–2010). Daily rainfall, mean temperature, evapotranspiration and discharge in situ data were collected for the period 1964–2010. After the model's initialization, calibration and validation; performances analysis have been carried out using multi-objectives functions developed in R software (version 3.5.3). The results indicate that statistical metrics such as the coefficient of determination (R2), the Kling–Gupta Efficiency (KGE), the Nash–Sutcliffe coefficient (NSE) and the Percent of Bias (PBIAS) provide satisfactory insights over the first period of simulation (1964–1986) and low performances over the second period of simulation (1988–2010). In particular, IHACRES model underestimates extreme high runoff of Mono catchment between 1964 and 1986. Conversely, GR4J model overestimates extreme high runoff and has been found to be better for runoff prediction of the river only between 1964 and 1986. Moreover, the study deduced that the robustness of runoff simulation between 1964 and 1986 is better than between 1988 and 2010. Therefore, the weakness of simulated runoff between 1988 and 2010 was certainly due to dam management in the catchment. The study suggests that land cover changes impacts, soil proprieties and climate may also affect surface runoff in the catchment.

Runoff Prediction Model Based on Improved Convolutional Neural Network

Due to the influence of human regulation and storage factors, the runoff series monitored at the hydropower stations often show the characteristics of non-periodicity, which makes runoff prediction simulation difficult. This paper attempts to construct an improved one-dimensional convolutional neural network (CNN) model for runoff prediction simulation. The improved CNN model consists of two convolution layers and a full connection layer and uses LeakyRelu as the activation function. Based on the historical rainfall and runoff data of the ZheXi reservoir in Hunan Province, this paper uses the improved CNN model to simulate runoff prediction and compares the results with the traditional ANN model and the traditional CNN model. The results show that the improved CNN model is superior to the traditional ANN model and the traditional CNN model. It proves that the improved CNN model is suitable for the non-periodic runoff prediction simulation, and it can avoid the data problems such as gradient disappearance that may occur in the traditional neural network model.