Premium
Pioneer use of gene expression programming for predicting seasonal streamflow in Australia using large scale climate drivers
Author(s) -
Esha Rijwana,
Imteaz Monzur Alam
Publication year - 2020
Publication title -
ecohydrology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.982
H-Index - 54
eISSN - 1936-0592
pISSN - 1936-0584
DOI - 10.1002/eco.2242
Subject(s) - streamflow , mean squared error , gene expression programming , climatology , pearson product moment correlation coefficient , indian ocean dipole , correlation coefficient , pacific decadal oscillation , environmental science , genetic programming , linear regression , forecast skill , meteorology , statistics , mathematics , el niño southern oscillation , computer science , geography , drainage basin , geology , machine learning , cartography
This paper presents development of an artificial intelligence (AI)‐based model, genetic expression programming (GEP) to predict long‐term streamflow using large‐scale climate drivers as predictors. GEP is chosen over artificial neural networks (ANNs) model, as ANN is a black‐box model, whereas GEP is able to explain the developed forecast models with mathematical expressions. As a case study, 12 streamflow measuring stations were selected from four different regions of New South Wales (NSW) in eastern Australia. A number of climate indices, Pacific Decadal Oscillation (PDO), Indian Ocean Dipole (IOD), El Nino Southern Oscillation (ENSO) and ENSO Modoki index (EMI), were selected as candidate predictors based on the findings of some preliminary studies. Higher predictabilities of the GEP‐based models are evident from the Pearson correlation ( r ) values ranging between 0.57 and 0.97, which are mostly about twice the values achieved by multiple linear regression (MLR) models in the preliminary study. Performances of the developed models were assessed using standard statistical measures such as root relative squared error (RRSE), relative absolute error (RAE), root mean square error (RMSE), mean absolute error (MAE), Nash–Sutcliffe efficiency (NSE) and Pearson correlation ( r ) values. The developed models are able to predict spring streamflow up to 5 months in advance with significantly high correlation values.