Prediction of river water temperature using machine learning algorithms: a tropical river system of India
Machine learning (ML) has been increasingly adopted due to its ability to model complex and non-linearities between river water temperature (RWT) and its predictors (e.g., Air Temperature, AT). Most of these ML approaches have been applied using average AT without any detailed sensitivity analysis o...
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
IWA Publishing
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/8e87599fbcb04e42b095638b11ea54c9 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| Sumario: | Machine learning (ML) has been increasingly adopted due to its ability to model complex and non-linearities between river water temperature (RWT) and its predictors (e.g., Air Temperature, AT). Most of these ML approaches have been applied using average AT without any detailed sensitivity analysis of other forms of AT (e.g., maximum and minimum). The present study demonstrates how new ML approaches, such as ridge regression (RR), K-nearest neighbors (KNN) regressor, random forest (RF) regressor, and support vector regression (SVR), can be coupled with Sobol’ global sensitivity analysis (GSA) to predict accurate RWT estimates with the most appropriate form of AT. Furthermore, the proposed ML approaches have been combined with the Ensemble Kalman Filter (EnKF), a data assimilation (DA) technique to improve the predicted values based on the measured data. The proposed modelling framework's effectiveness is demonstrated with a tropical river system of India, Tunga-Bhadra River, as a case study. The SVR has been noted as the most robust ML model to predict RWT at a monthly time scale compared with daily and seasonal. The study demonstrates how ML methods can be coupled with a global sensitivity algorithm and DA techniques to generate accurate RWT predictions in river water quality modelling. HIGHLIGHTS
Machine learning models coupled with global sensitivity analysis to predict RWT.;
Ridge regression, KNN, random forest, SVR, along with Sobol’ sensitivity analysis were explored.;
Maximum AT as the most sensitive variable in RWT prediction.;
The SVR as the most robust ML model to predict RWT at monthly time scale.;
Application on a tropical river system of India.; |
|---|