Harnessing Deep Learning and Snow Cover Data for Enhanced Runoff Prediction in Snow-Dominated Watersheds

Predicting streamflow is essential for managing water resources, especially in basins and watersheds where snowmelt plays a major role in river discharge. This study evaluates the advanced deep learning models for accurate monthly and peak streamflow forecasting in the Gilgit River Basin. The models...

Full description

Saved in:
Bibliographic Details
Main Authors: Rana Muhammad Adnan, Wang Mo, Ozgur Kisi, Salim Heddam, Ahmed Mohammed Sami Al-Janabi, Mohammad Zounemat-Kermani
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Atmosphere
Subjects:
Online Access:https://www.mdpi.com/2073-4433/15/12/1407
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846105893143314432
author Rana Muhammad Adnan
Wang Mo
Ozgur Kisi
Salim Heddam
Ahmed Mohammed Sami Al-Janabi
Mohammad Zounemat-Kermani
author_facet Rana Muhammad Adnan
Wang Mo
Ozgur Kisi
Salim Heddam
Ahmed Mohammed Sami Al-Janabi
Mohammad Zounemat-Kermani
author_sort Rana Muhammad Adnan
collection DOAJ
description Predicting streamflow is essential for managing water resources, especially in basins and watersheds where snowmelt plays a major role in river discharge. This study evaluates the advanced deep learning models for accurate monthly and peak streamflow forecasting in the Gilgit River Basin. The models utilized were LSTM, BiLSTM, GRU, CNN, and their hybrid combinations (CNN-LSTM, CNN-BiLSTM, CNN-GRU, and CNN-BiGRU). Our research measured the model’s accuracy through root mean square error (RMSE), mean absolute error (MAE), Nash–Sutcliffe efficiency (NSE), and the coefficient of determination (R<sup>2</sup>). The findings indicated that the hybrid models, especially CNN-BiGRU and CNN-BiLSTM, achieved much better performance than traditional models like LSTM and GRU. For instance, CNN-BiGRU achieved the lowest RMSE (71.6 in training and 95.7 in testing) and the highest R<sup>2</sup> (0.962 in training and 0.929 in testing). A novel aspect of this research was the integration of MODIS-derived snow-covered area (SCA) data, which enhanced model accuracy substantially. When SCA data were included, the CNN-BiLSTM model’s RMSE improved from 83.6 to 71.6 during training and from 108.6 to 95.7 during testing. In peak streamflow prediction, CNN-BiGRU outperformed other models with the lowest absolute error (108.4), followed by CNN-BiLSTM (144.1). This study’s results reinforce the notion that combining CNN’s spatial feature extraction capabilities with the temporal dependencies captured by LSTM or GRU significantly enhances model accuracy. The demonstrated improvements in prediction accuracy, especially for extreme events, highlight the potential for these models to support more informed decision-making in flood risk management and water allocation.
format Article
id doaj-art-0168e59f45f340e0bac281ed1822d1b4
institution Kabale University
issn 2073-4433
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Atmosphere
spelling doaj-art-0168e59f45f340e0bac281ed1822d1b42024-12-27T14:09:39ZengMDPI AGAtmosphere2073-44332024-11-011512140710.3390/atmos15121407Harnessing Deep Learning and Snow Cover Data for Enhanced Runoff Prediction in Snow-Dominated WatershedsRana Muhammad Adnan0Wang Mo1Ozgur Kisi2Salim Heddam3Ahmed Mohammed Sami Al-Janabi4Mohammad Zounemat-Kermani5College of Architecture and Urban Planning, Guangzhou University, Guangzhou 510006, ChinaCollege of Architecture and Urban Planning, Guangzhou University, Guangzhou 510006, ChinaDepartment of Civil Engineering, Lübeck University of Applied Science, 23562 Lübeck, GermanyHydraulics Division, Agronomy Department, Faculty of Science, University20 Août 1955 Skikda, Route El Hadaik, BP 26, Skikda 21024, AlgeriaDepartment of Civil Engineering, Cihan University-Erbil, Kurdistan Region, Erbil 44001, IraqDepartment of Water Engineering, Shahid Bahonar University of Kerman, Kerman 76169-14111, IranPredicting streamflow is essential for managing water resources, especially in basins and watersheds where snowmelt plays a major role in river discharge. This study evaluates the advanced deep learning models for accurate monthly and peak streamflow forecasting in the Gilgit River Basin. The models utilized were LSTM, BiLSTM, GRU, CNN, and their hybrid combinations (CNN-LSTM, CNN-BiLSTM, CNN-GRU, and CNN-BiGRU). Our research measured the model’s accuracy through root mean square error (RMSE), mean absolute error (MAE), Nash–Sutcliffe efficiency (NSE), and the coefficient of determination (R<sup>2</sup>). The findings indicated that the hybrid models, especially CNN-BiGRU and CNN-BiLSTM, achieved much better performance than traditional models like LSTM and GRU. For instance, CNN-BiGRU achieved the lowest RMSE (71.6 in training and 95.7 in testing) and the highest R<sup>2</sup> (0.962 in training and 0.929 in testing). A novel aspect of this research was the integration of MODIS-derived snow-covered area (SCA) data, which enhanced model accuracy substantially. When SCA data were included, the CNN-BiLSTM model’s RMSE improved from 83.6 to 71.6 during training and from 108.6 to 95.7 during testing. In peak streamflow prediction, CNN-BiGRU outperformed other models with the lowest absolute error (108.4), followed by CNN-BiLSTM (144.1). This study’s results reinforce the notion that combining CNN’s spatial feature extraction capabilities with the temporal dependencies captured by LSTM or GRU significantly enhances model accuracy. The demonstrated improvements in prediction accuracy, especially for extreme events, highlight the potential for these models to support more informed decision-making in flood risk management and water allocation.https://www.mdpi.com/2073-4433/15/12/1407streamflow forecastinglong short-term memorybidirectional long short-term memorygated recurrent unitbidirectional gated recurrent unitconvolutional neural network
spellingShingle Rana Muhammad Adnan
Wang Mo
Ozgur Kisi
Salim Heddam
Ahmed Mohammed Sami Al-Janabi
Mohammad Zounemat-Kermani
Harnessing Deep Learning and Snow Cover Data for Enhanced Runoff Prediction in Snow-Dominated Watersheds
Atmosphere
streamflow forecasting
long short-term memory
bidirectional long short-term memory
gated recurrent unit
bidirectional gated recurrent unit
convolutional neural network
title Harnessing Deep Learning and Snow Cover Data for Enhanced Runoff Prediction in Snow-Dominated Watersheds
title_full Harnessing Deep Learning and Snow Cover Data for Enhanced Runoff Prediction in Snow-Dominated Watersheds
title_fullStr Harnessing Deep Learning and Snow Cover Data for Enhanced Runoff Prediction in Snow-Dominated Watersheds
title_full_unstemmed Harnessing Deep Learning and Snow Cover Data for Enhanced Runoff Prediction in Snow-Dominated Watersheds
title_short Harnessing Deep Learning and Snow Cover Data for Enhanced Runoff Prediction in Snow-Dominated Watersheds
title_sort harnessing deep learning and snow cover data for enhanced runoff prediction in snow dominated watersheds
topic streamflow forecasting
long short-term memory
bidirectional long short-term memory
gated recurrent unit
bidirectional gated recurrent unit
convolutional neural network
url https://www.mdpi.com/2073-4433/15/12/1407
work_keys_str_mv AT ranamuhammadadnan harnessingdeeplearningandsnowcoverdataforenhancedrunoffpredictioninsnowdominatedwatersheds
AT wangmo harnessingdeeplearningandsnowcoverdataforenhancedrunoffpredictioninsnowdominatedwatersheds
AT ozgurkisi harnessingdeeplearningandsnowcoverdataforenhancedrunoffpredictioninsnowdominatedwatersheds
AT salimheddam harnessingdeeplearningandsnowcoverdataforenhancedrunoffpredictioninsnowdominatedwatersheds
AT ahmedmohammedsamialjanabi harnessingdeeplearningandsnowcoverdataforenhancedrunoffpredictioninsnowdominatedwatersheds
AT mohammadzounematkermani harnessingdeeplearningandsnowcoverdataforenhancedrunoffpredictioninsnowdominatedwatersheds