Enhancing Rainfall-Runoff Simulation via Meteorological Variables and a Deep-Conceptual Learning-Based Framework
Accurate streamflow simulation is crucial for many applications, such as optimal reservoir operation and irrigation. Conceptual techniques employ physical ideas and are suitable for representing the physics of the hydrologic model, but they might fail in competition with their more advanced counterp...
Published in: | Atmosphere |
---|---|
Main Authors: | , , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
MDPI AG
2022
|
Subjects: | |
Online Access: | https://lup.lub.lu.se/record/db814ea2-2ac4-4cf7-8618-07f0857f6979 https://doi.org/10.3390/atmos13101688 |
id |
ftulundlup:oai:lup.lub.lu.se:db814ea2-2ac4-4cf7-8618-07f0857f6979 |
---|---|
record_format |
openpolar |
spelling |
ftulundlup:oai:lup.lub.lu.se:db814ea2-2ac4-4cf7-8618-07f0857f6979 2023-05-15T17:45:04+02:00 Enhancing Rainfall-Runoff Simulation via Meteorological Variables and a Deep-Conceptual Learning-Based Framework Achite, Mohammed Mohammadi, Babak Jehanzaib, Muhammad Elshaboury, Nehal Pham, Quoc Bao Duan, Zheng 2022-10 https://lup.lub.lu.se/record/db814ea2-2ac4-4cf7-8618-07f0857f6979 https://doi.org/10.3390/atmos13101688 eng eng MDPI AG https://lup.lub.lu.se/record/db814ea2-2ac4-4cf7-8618-07f0857f6979 http://dx.doi.org/10.3390/atmos13101688 scopus:85140486428 Atmosphere; 13(10), no 1688 (2022) ISSN: 2073-4433 Water Engineering Physical Geography conceptual hydrological model data-driven model deep learning model runoff simulation contributiontojournal/article info:eu-repo/semantics/article text 2022 ftulundlup https://doi.org/10.3390/atmos13101688 2023-02-01T23:39:31Z Accurate streamflow simulation is crucial for many applications, such as optimal reservoir operation and irrigation. Conceptual techniques employ physical ideas and are suitable for representing the physics of the hydrologic model, but they might fail in competition with their more advanced counterparts. In contrast, deep learning (DL) approaches provide a great computational capability for streamflow simulation, but they rely on data characteristics and the physics of the issue cannot be fully understood. To overcome these limitations, the current study provided a novel framework based on a combination of conceptual and DL techniques for enhancing the accuracy of streamflow simulation in a snow-covered basin. In this regard, the current study simulated daily streamflow in the Kalixälven river basin in northern Sweden by integrating a snow-based conceptual hydrological model (MISD) with a DL model. Daily precipitation, air temperature (average, minimum, and maximum), dew point temperature, evapotranspiration, relative humidity, sunshine duration, global solar radiation, and atmospheric pressure data were used as inputs for the DL model to examine the effect of each meteorological variable on the streamflow simulation. Results proved that adding meteorological variables to the conceptual hydrological model underframe of parallel settings can improve the accuracy of streamflow simulating by the DL model. The MISD model simulated streamflow had an MAE = 8.33 (cms), r = 0.88, and NSE = 0.77 for the validation phase. The proposed deep-conceptual learning-based framework also performed better than the standalone MISD model; the DL method had an MAE = 7.89 (cms), r = 0.90, and NSE = 0.80 for the validation phase when meteorological variables and MISD results were combined as inputs for the DL model. The integrated rainfall-runoff model proposed in this research is a new concept in rainfall-runoff modeling which can be used for accurate streamflow simulations. Article in Journal/Newspaper Northern Sweden Lund University Publications (LUP) Kalixälven ENVELOPE(23.217,23.217,65.783,65.783) Atmosphere 13 10 1688 |
institution |
Open Polar |
collection |
Lund University Publications (LUP) |
op_collection_id |
ftulundlup |
language |
English |
topic |
Water Engineering Physical Geography conceptual hydrological model data-driven model deep learning model runoff simulation |
spellingShingle |
Water Engineering Physical Geography conceptual hydrological model data-driven model deep learning model runoff simulation Achite, Mohammed Mohammadi, Babak Jehanzaib, Muhammad Elshaboury, Nehal Pham, Quoc Bao Duan, Zheng Enhancing Rainfall-Runoff Simulation via Meteorological Variables and a Deep-Conceptual Learning-Based Framework |
topic_facet |
Water Engineering Physical Geography conceptual hydrological model data-driven model deep learning model runoff simulation |
description |
Accurate streamflow simulation is crucial for many applications, such as optimal reservoir operation and irrigation. Conceptual techniques employ physical ideas and are suitable for representing the physics of the hydrologic model, but they might fail in competition with their more advanced counterparts. In contrast, deep learning (DL) approaches provide a great computational capability for streamflow simulation, but they rely on data characteristics and the physics of the issue cannot be fully understood. To overcome these limitations, the current study provided a novel framework based on a combination of conceptual and DL techniques for enhancing the accuracy of streamflow simulation in a snow-covered basin. In this regard, the current study simulated daily streamflow in the Kalixälven river basin in northern Sweden by integrating a snow-based conceptual hydrological model (MISD) with a DL model. Daily precipitation, air temperature (average, minimum, and maximum), dew point temperature, evapotranspiration, relative humidity, sunshine duration, global solar radiation, and atmospheric pressure data were used as inputs for the DL model to examine the effect of each meteorological variable on the streamflow simulation. Results proved that adding meteorological variables to the conceptual hydrological model underframe of parallel settings can improve the accuracy of streamflow simulating by the DL model. The MISD model simulated streamflow had an MAE = 8.33 (cms), r = 0.88, and NSE = 0.77 for the validation phase. The proposed deep-conceptual learning-based framework also performed better than the standalone MISD model; the DL method had an MAE = 7.89 (cms), r = 0.90, and NSE = 0.80 for the validation phase when meteorological variables and MISD results were combined as inputs for the DL model. The integrated rainfall-runoff model proposed in this research is a new concept in rainfall-runoff modeling which can be used for accurate streamflow simulations. |
format |
Article in Journal/Newspaper |
author |
Achite, Mohammed Mohammadi, Babak Jehanzaib, Muhammad Elshaboury, Nehal Pham, Quoc Bao Duan, Zheng |
author_facet |
Achite, Mohammed Mohammadi, Babak Jehanzaib, Muhammad Elshaboury, Nehal Pham, Quoc Bao Duan, Zheng |
author_sort |
Achite, Mohammed |
title |
Enhancing Rainfall-Runoff Simulation via Meteorological Variables and a Deep-Conceptual Learning-Based Framework |
title_short |
Enhancing Rainfall-Runoff Simulation via Meteorological Variables and a Deep-Conceptual Learning-Based Framework |
title_full |
Enhancing Rainfall-Runoff Simulation via Meteorological Variables and a Deep-Conceptual Learning-Based Framework |
title_fullStr |
Enhancing Rainfall-Runoff Simulation via Meteorological Variables and a Deep-Conceptual Learning-Based Framework |
title_full_unstemmed |
Enhancing Rainfall-Runoff Simulation via Meteorological Variables and a Deep-Conceptual Learning-Based Framework |
title_sort |
enhancing rainfall-runoff simulation via meteorological variables and a deep-conceptual learning-based framework |
publisher |
MDPI AG |
publishDate |
2022 |
url |
https://lup.lub.lu.se/record/db814ea2-2ac4-4cf7-8618-07f0857f6979 https://doi.org/10.3390/atmos13101688 |
long_lat |
ENVELOPE(23.217,23.217,65.783,65.783) |
geographic |
Kalixälven |
geographic_facet |
Kalixälven |
genre |
Northern Sweden |
genre_facet |
Northern Sweden |
op_source |
Atmosphere; 13(10), no 1688 (2022) ISSN: 2073-4433 |
op_relation |
https://lup.lub.lu.se/record/db814ea2-2ac4-4cf7-8618-07f0857f6979 http://dx.doi.org/10.3390/atmos13101688 scopus:85140486428 |
op_doi |
https://doi.org/10.3390/atmos13101688 |
container_title |
Atmosphere |
container_volume |
13 |
container_issue |
10 |
container_start_page |
1688 |
_version_ |
1766147809891844096 |