Comparative analysis of deep learning and machine learning models for one-day-ahead streamflow forecasting in the Krishna River basin

Study region: Karad, Keesara, Sarati and T.Ramapuram catchments located in the Krishna River basin, India Study focus: This study focused on 1-day ahead streamflow forecasting in four distinct catchments using a wide array of Deep Learning (DL) and Machine Learning (ML) models. A comprehensive evalu...

Full description

Saved in:
Bibliographic Details
Main Authors: Sukhsehaj Kaur, Sagar Rohidas Chavan
Format: Article
Language:English
Published: Elsevier 2025-08-01
Series:Journal of Hydrology: Regional Studies
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S221458182500374X
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849731457800470528
author Sukhsehaj Kaur
Sagar Rohidas Chavan
author_facet Sukhsehaj Kaur
Sagar Rohidas Chavan
author_sort Sukhsehaj Kaur
collection DOAJ
description Study region: Karad, Keesara, Sarati and T.Ramapuram catchments located in the Krishna River basin, India Study focus: This study focused on 1-day ahead streamflow forecasting in four distinct catchments using a wide array of Deep Learning (DL) and Machine Learning (ML) models. A comprehensive evaluation of eleven models was conducted to assess their strengths and limitations across different datasets. New hydrological insights: The study implemented Long Short-Term Memory (LSTM), Bidirectional LSTM (Bi-LSTM), Gated Recurrent Unit (GRU), Bidirectional GRU, Convolutional Neural Network, WaveNet, K-Nearest Neighbours, Random Forest (RF), Support Vector Regression, Adaptive Boosting, and Extreme Gradient Boosting (XGBoost) to forecast streamflow at each site. Lagged precipitation and antecedent streamflow emerged as key predictors. Model performance was assessed using multiple evaluation metrics and visualization techniques. Bi-LSTM achieved the highest performance in three catchments with Nash-Sutcliffe efficiency (NSE) of 0.864 in Karad, 0.708 in Keesara, and 0.702 in T. Ramapuram, while GRU performed best in Sarati with NSE close to 0.7. The best model achieved ''very good'' accuracy in one catchment and ''good'' in three, as indicated by performance metrics. However, even the best-performing DL models struggled to capture peak flow events, revealing limitations in extrapolation. The study also highlights the potential of ML models based on ensemble techniques, such as RF and XGBoost, which demonstrated performance comparable to that of complex DL architectures.
format Article
id doaj-art-a104ef6385db41cc8b442d2f653eb3d4
institution DOAJ
issn 2214-5818
language English
publishDate 2025-08-01
publisher Elsevier
record_format Article
series Journal of Hydrology: Regional Studies
spelling doaj-art-a104ef6385db41cc8b442d2f653eb3d42025-08-20T03:08:32ZengElsevierJournal of Hydrology: Regional Studies2214-58182025-08-016010254910.1016/j.ejrh.2025.102549Comparative analysis of deep learning and machine learning models for one-day-ahead streamflow forecasting in the Krishna River basinSukhsehaj Kaur0Sagar Rohidas Chavan1Department of Civil Engineering, Indian Institute of Technology Ropar, 140001, IndiaCorresponding author.; Department of Civil Engineering, Indian Institute of Technology Ropar, 140001, IndiaStudy region: Karad, Keesara, Sarati and T.Ramapuram catchments located in the Krishna River basin, India Study focus: This study focused on 1-day ahead streamflow forecasting in four distinct catchments using a wide array of Deep Learning (DL) and Machine Learning (ML) models. A comprehensive evaluation of eleven models was conducted to assess their strengths and limitations across different datasets. New hydrological insights: The study implemented Long Short-Term Memory (LSTM), Bidirectional LSTM (Bi-LSTM), Gated Recurrent Unit (GRU), Bidirectional GRU, Convolutional Neural Network, WaveNet, K-Nearest Neighbours, Random Forest (RF), Support Vector Regression, Adaptive Boosting, and Extreme Gradient Boosting (XGBoost) to forecast streamflow at each site. Lagged precipitation and antecedent streamflow emerged as key predictors. Model performance was assessed using multiple evaluation metrics and visualization techniques. Bi-LSTM achieved the highest performance in three catchments with Nash-Sutcliffe efficiency (NSE) of 0.864 in Karad, 0.708 in Keesara, and 0.702 in T. Ramapuram, while GRU performed best in Sarati with NSE close to 0.7. The best model achieved ''very good'' accuracy in one catchment and ''good'' in three, as indicated by performance metrics. However, even the best-performing DL models struggled to capture peak flow events, revealing limitations in extrapolation. The study also highlights the potential of ML models based on ensemble techniques, such as RF and XGBoost, which demonstrated performance comparable to that of complex DL architectures.http://www.sciencedirect.com/science/article/pii/S221458182500374XStreamflow forecastingDeep LearningMachine LearningKrishna River Basin
spellingShingle Sukhsehaj Kaur
Sagar Rohidas Chavan
Comparative analysis of deep learning and machine learning models for one-day-ahead streamflow forecasting in the Krishna River basin
Journal of Hydrology: Regional Studies
Streamflow forecasting
Deep Learning
Machine Learning
Krishna River Basin
title Comparative analysis of deep learning and machine learning models for one-day-ahead streamflow forecasting in the Krishna River basin
title_full Comparative analysis of deep learning and machine learning models for one-day-ahead streamflow forecasting in the Krishna River basin
title_fullStr Comparative analysis of deep learning and machine learning models for one-day-ahead streamflow forecasting in the Krishna River basin
title_full_unstemmed Comparative analysis of deep learning and machine learning models for one-day-ahead streamflow forecasting in the Krishna River basin
title_short Comparative analysis of deep learning and machine learning models for one-day-ahead streamflow forecasting in the Krishna River basin
title_sort comparative analysis of deep learning and machine learning models for one day ahead streamflow forecasting in the krishna river basin
topic Streamflow forecasting
Deep Learning
Machine Learning
Krishna River Basin
url http://www.sciencedirect.com/science/article/pii/S221458182500374X
work_keys_str_mv AT sukhsehajkaur comparativeanalysisofdeeplearningandmachinelearningmodelsforonedayaheadstreamflowforecastinginthekrishnariverbasin
AT sagarrohidaschavan comparativeanalysisofdeeplearningandmachinelearningmodelsforonedayaheadstreamflowforecastinginthekrishnariverbasin