Rainfall and runoff time-series trend analysis using LSTM recurrent neural network and wavelet neural network with satellite-based meteorological data: case study of Nzoia hydrologic basin

Abstract

This study compares LSTM neural network and wavelet neural network (WNN) for spatio-temporal prediction of rainfall and runoff time-series trends in scarcely gauged hydrologic basins. Using long-term in situ observed data for 30 years (1980–2009) from ten rain gauge stations and three discharge measurement stations, the rainfall and runoff trends in the Nzoia River basin are predicted through satellite-based meteorological data comprising of: precipitation, mean temperature, relative humidity, wind speed and solar radiation. The prediction modelling was carried out in three sub-basins corresponding to the three discharge stations. LSTM and WNN were implemented with the same deep learning topological structure consisting of 4 hidden layers, each with 30 neurons. In the prediction of the basin runoff with the five meteorological parameters using LSTM and WNN, both models performed well with respective R2 values of 0.8967 and 0.8820. The MAE and RMSE measures for LSTM and WNN predictions ranged between 11–13 m3/s for the mean monthly runoff prediction. With the satellite-based meteorological data, LSTM predicted the mean monthly rainfall within the basin with R2 = 0.8610 as compared to R2 = 0.7825 using WNN. The MAE for mean monthly rainfall trend prediction was between 9 and 11 mm, while the RMSE varied between 15 and 21 mm. The performance of the models improved with increase in the number of input parameters, which corresponded to the size of the sub-basin. In terms of the computational time, both models converged at the lowest RMSE at nearly the same number of epochs, with WNN taking slightly longer to attain the minimum RMSE. The study shows that in hydrologic basins with scarce meteorological and hydrological monitoring networks, the use satellite-based meteorological data in deep learning neural network models are suitable for spatial and temporal analysis of rainfall and runoff trends.

Application of Machine Learning Techniques in Rainfall–Runoff Modelling of the Soan River Basin, Pakistan

“…Likewise, Hussain et al [69] also modelled the rainfall-runoff relation of the region with maximum R 2 value of 0.66. Recently, Ouma et al [70] also modelled the rainfall-runoff relationship in the Nzoia subbasin of Lake Victoria using wavelet-based machine learning models and compared their performance with the long short-term memory (LSTM) deep learning model. Outcomes of our study provide empirical support to their findings corresponding to performance enhancement of machine learning models when coupled with wavelet pre-processing.…”

Application of ANNs for the modeling of streamflow, sediment transport, and erosion rate of a high-altitude river system in Western Himalaya, Uttarakhand

“…An artificial neural network was trained based on observed streamflows. The training process used 70% of the time-series data, while testing and validating processes used 15% of each (Sangiorgio et al, 2021;Gunathilake et al, 2021;Ouma et al, 2021;Singh & Panda, 2022). The training aims to determine the set of connections, weights, and biases that cause the neural network to estimate outputs close to the measured outputs.…”

Prediction of Time Series Gene Expression and Structural Analysis of Gene Regulatory Networks Using Recurrent Neural Networks

“…Predicting the behavior of a stochastic network is an extremely challenging task in modern science. Indeed, the measurable output of many processes, such as the evolution of the stock market, meteorology, transport and biological systems, consists of stochastic time traces [ 21 , 22 , 23 , 24 , 25 ]. Inferring information on the behavior of these systems gives the possibility to predict their future changes, in turn allowing one to have a thorough knowledge of the evolution of the system and, on that basis, make functional decisions.…”