Hybrid models to improve the monthly river flow prediction: Integrating artificial intelligence and non-linear time series models

Fathian, Farshad; Mehdizadeh, Saeid; Sales, Ali Kozekalani; Safari, Mir Jafar Sadegh

doi:10.1016/j.jhydrol.2019.06.025

Cited by 100 publications

(37 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Here, a feed‐forward ANN‐based model with two hidden layers was used to estimate ω. The role of the hidden layer is to determine the network parameters to achieve the best fit between the observed and predicted variables (Fathian, Mehdizadeh, Kozekalani Sales, & Safari, ). Here the optimal number of neurons in the hidden layers was determined by analysing the change in root mean squared error (RMSE) with the number of neurons.…”

Section: Methodsmentioning

confidence: 99%

Estimation of the Budyko model parameter for small basins in China

Bai

Liu

Zhang

et al. 2019

Hydrological Processes

View full text Add to dashboard Cite

At the mean annual scale, water availability of a basin is substantially determined by how much precipitation will be partitioned into evapotranspiration and run-off. The Budyko framework provides a simple but efficient tool to estimate precipitation partitioning at the basin scale. As one form of the Budyko framework, Fu's equation has been widely used to model long-term basin-scale water balance. The major difficulty in applications of Fu's equation is determining how to estimate the curve shape parameter ω efficiently. Previous studies have suggested that the parameter ω is closely related to the long-term vegetation coverage on large river basins globally. However, on small basins, the parameter ω is difficult to estimate due to the diversity of controlling factors. Here, we focused on the estimation of ω for small basins in China. We identified the major factors controlling the basin-specific (calibrated) ω from nine catchment attributes based on a dataset from 206 small basins (≤50,000 km 2 ) across China. Next, we related the calibrated ω to the major factors controlling ω using two statistical models, that is, the multiple linear regression (MLR) model and artificial neural network (ANN) model. We compared and validated the two statistical models using an independent dataset of 80 small basins. The results indicated that in addition to vegetation, other landscape factors (e.g., topography and human activity) need to be considered to capture the variability of ω on small basins better. Contrary to previous findings reached on large basins worldwide, the basin-specific ω and remote sensing-based vegetation greenness index exhibit a significant negative correlation. Compared with the default ω value of 2.6 used in the Budyko curve method, the two statistical models significantly improved the mean annual ET simulations on validation basins by reducing the root mean square error from 114 mm/year to 74.5 mm/year for the MLR model and 70 mm/year for the ANN model. In comparison, the ANN model can provide a better ω estimation than the MLR model.

show abstract

Section: Methodsmentioning

confidence: 99%

Estimation of the Budyko model parameter for small basins in China

Bai

Liu

Zhang

et al. 2019

Hydrological Processes

View full text Add to dashboard Cite

show abstract

“…(2017c, 2018b, 2019), and Fathian et al . (2019). The authors developed different types of the hybrid models through hybridization of the different time‐series‐ and AI‐based models for improving the modelling efficiency of classical models in modelling hydrological variables.…”

Section: Resultsmentioning

confidence: 99%

Modelling daily soil temperature at different depths via the classical and hybrid models

Mehdizadeh

Ahmadi

Sales³

2020

Meteorological Applications

Self Cite

View full text Add to dashboard Cite

Soil temperature (ST) is one of the crucial variables of soil and it plays a fundamental role in different research scopes such as underground soil physical and agricultural applications. The study explores the modelling performance of a time series‐based model (i.e. bi‐linear, BL), and an artificial intelligence‐based approach including adaptive neuro‐fuzzy inference system (ANFIS), for modelling the daily ST of different soil depths (5, 10, 50 and 100 cm). The study also develops and proposes two diverse types of the hybrid models through coupling the ANFIS with the BL and wavelet analysis (W) to improve the accuracy of the ST modelling. Two stations in Iran (i.e. Isfahan and Urmia) were selected as the study locations. The results demonstrated that the ANFIS generally presented better results than the BL. Furthermore, the hybrid models (i.e. W‐ANFIS and ANFIS‐BL) gave superior performances than the classical ANFIS and BL for modelling the daily ST of the studied areas at various soil depths. In addition to the local evaluation of the ANFIS (i.e. modelling the ST at a specific depth by using the original ST data at that depth), an external analysis was also conducted. In doing so, the daily ST data at a 5 cm depth were modelled via the corresponding ST data at a 10 cm depth, and vice versa. The results denoted the applicability of the ST data at another depth for modelling the ST of each specific/target depth.

show abstract

“…Several other studies also encouraged the researchers to use MARS and M5T models for the prediction of runoff e.g. [31][32][33][34][35][36][37]. Apart from runoff prediction, MARS and M5T models were also used for the prediction of evapotranspiration (ET) and Pan Evaporation (Ep).…”

Section: Introductionmentioning

confidence: 99%

Prediction of Relative Humidity in a High Elevated Basin of Western Karakoram by Using Different Machine Learning Models

Adnan¹,

Adnan²,

Liu³

et al. 2021

Weather Forecasting

View full text Add to dashboard Cite

Accurate and reliable prediction of relative humidity is of great importance in all fields concerning global climate change. The current study has employed Multivariate Adaptive Regression Spline (MARS) and M5 Tree (M5T) models to predict the relative humidity in the Hunza River basin, Pakistan. Both the models provided the best prediction for the input scenario S6 (RHt-1, RHt-2, RHt-3, Tt-1, Tt-2, Tt-3). The statistical analysis displayed that the MARS model provided a better prediction of relative humidity as compared to M5T at all meteorological stations, especially, at Ziarat followed by Khunjerab and Naltar. The values of root mean square error (RMSE), mean absolute error (MAE), and coefficient of determination (R2) were (5.98%, 5.43%, and 0.808) for Khunjerab; (6.58%, 5.08%, and 0.806) for Naltar; and (5.86%, 4.97%, 0.815) for Ziarat during the testing of MARS model whereas, the values were (6.14%, 5.56%, and 0.772) for Khunjerab; (6.19%, 5.58% and 0.762) for Naltar and (6.08%, 5.46%, 0.783) for Ziarat during the testing of M5T model. Both the models performed slightly better in training as compared to the testing stage. The current study encourages future research to be conducted at high altitude basins for the prediction of other meteorological variables using machine learning tools.

show abstract

Hybrid models to improve the monthly river flow prediction: Integrating artificial intelligence and non-linear time series models

Cited by 100 publications

References 39 publications

Estimation of the Budyko model parameter for small basins in China

Estimation of the Budyko model parameter for small basins in China

Modelling daily soil temperature at different depths via the classical and hybrid models

Prediction of Relative Humidity in a High Elevated Basin of Western Karakoram by Using Different Machine Learning Models

Contact Info

Product

Resources

About