Dam inflow prediction using large-scale climate variability and deep learning approach: a case study in South Korea

Accurate prediction of dam inflows is essential for effective water resources management in terms of both water quantity and quality. This study aims to develop a Long Short-Term Memory (LSTM) deep learning-based monthly dam inflow prediction model using large-scale climate indices. Six climate indi...

Full description

Bibliographic Details
Main Authors: Heechan Han, Donghyun Kim, Wonjoon Wang, Hung Soo Kim
Format: Article
Language:English
Published: IWA Publishing 2023-02-01
Series:Water Supply
Subjects:
Online Access:http://ws.iwaponline.com/content/23/2/934
_version_ 1797850652692447232
author Heechan Han
Donghyun Kim
Wonjoon Wang
Hung Soo Kim
author_facet Heechan Han
Donghyun Kim
Wonjoon Wang
Hung Soo Kim
author_sort Heechan Han
collection DOAJ
description Accurate prediction of dam inflows is essential for effective water resources management in terms of both water quantity and quality. This study aims to develop a Long Short-Term Memory (LSTM) deep learning-based monthly dam inflow prediction model using large-scale climate indices. Six climate indices, Atlantic multidecadal oscillation (AMO), El Niño–southern oscillations (ENSO), North Atlantic oscillation (NAO), Pacific decadal oscillation (PDO), Niño 3.4, and Southern Oscillation Index (SOI) for the period of 1981–2020, were used as input variables of the model. The proposed model was trained with 29 years of data (1981–2009) and tested with 12 years of data (2009–2020). We investigated 29 input data combinations to evaluate the predictive performance according to different input datasets. The model showed the average values of metrics ranged from 0.5 to 0.6 for CC and from 40 to 80 cm for root mean square error (RMSE) at three dams. The prediction results from the model showed lower performance as the lead time increased. Also, each dam showed different prediction results for different seasons. For example, Soyangriver/Daecheong dams have better accuracy in prediction for the wet season than the dry season, whereas the Andong dam has a high prediction ability during the dry season. These investigations can be used for better efficient dam management using a data-driven approach. HIGHLIGHTS A dam inflow prediction model was developed using the LSTM-based deep learning method and climate indices.; Six climate indices including AMO, ENSO, NAO, PDO, Niño 3.4, and SOI are considered as input variables.; The proposed model tests 29 different input combinations to find the best combinations for prediction.; The proposed model shows the applicability to predict dam inflow variability in different locations.;
first_indexed 2024-04-09T19:03:48Z
format Article
id doaj.art-93d0931f12be44e7a358790b467cb0b4
institution Directory Open Access Journal
issn 1606-9749
1607-0798
language English
last_indexed 2024-04-09T19:03:48Z
publishDate 2023-02-01
publisher IWA Publishing
record_format Article
series Water Supply
spelling doaj.art-93d0931f12be44e7a358790b467cb0b42023-04-07T15:15:26ZengIWA PublishingWater Supply1606-97491607-07982023-02-0123293494710.2166/ws.2023.012012Dam inflow prediction using large-scale climate variability and deep learning approach: a case study in South KoreaHeechan Han0Donghyun Kim1Wonjoon Wang2Hung Soo Kim3 Department of Civil Engineering, Chosun University, Gwangju, South Korea Institute of Water Resource System, Inha University, Incheon, South Korea Department of Civil Engineering, Inha University, Incheon, South Korea Department of Civil Engineering, Inha University, Incheon, South Korea Accurate prediction of dam inflows is essential for effective water resources management in terms of both water quantity and quality. This study aims to develop a Long Short-Term Memory (LSTM) deep learning-based monthly dam inflow prediction model using large-scale climate indices. Six climate indices, Atlantic multidecadal oscillation (AMO), El Niño–southern oscillations (ENSO), North Atlantic oscillation (NAO), Pacific decadal oscillation (PDO), Niño 3.4, and Southern Oscillation Index (SOI) for the period of 1981–2020, were used as input variables of the model. The proposed model was trained with 29 years of data (1981–2009) and tested with 12 years of data (2009–2020). We investigated 29 input data combinations to evaluate the predictive performance according to different input datasets. The model showed the average values of metrics ranged from 0.5 to 0.6 for CC and from 40 to 80 cm for root mean square error (RMSE) at three dams. The prediction results from the model showed lower performance as the lead time increased. Also, each dam showed different prediction results for different seasons. For example, Soyangriver/Daecheong dams have better accuracy in prediction for the wet season than the dry season, whereas the Andong dam has a high prediction ability during the dry season. These investigations can be used for better efficient dam management using a data-driven approach. HIGHLIGHTS A dam inflow prediction model was developed using the LSTM-based deep learning method and climate indices.; Six climate indices including AMO, ENSO, NAO, PDO, Niño 3.4, and SOI are considered as input variables.; The proposed model tests 29 different input combinations to find the best combinations for prediction.; The proposed model shows the applicability to predict dam inflow variability in different locations.;http://ws.iwaponline.com/content/23/2/934deep learning algorithmlarge-scale climate variabilitymonthly dam inflow prediction
spellingShingle Heechan Han
Donghyun Kim
Wonjoon Wang
Hung Soo Kim
Dam inflow prediction using large-scale climate variability and deep learning approach: a case study in South Korea
Water Supply
deep learning algorithm
large-scale climate variability
monthly dam inflow prediction
title Dam inflow prediction using large-scale climate variability and deep learning approach: a case study in South Korea
title_full Dam inflow prediction using large-scale climate variability and deep learning approach: a case study in South Korea
title_fullStr Dam inflow prediction using large-scale climate variability and deep learning approach: a case study in South Korea
title_full_unstemmed Dam inflow prediction using large-scale climate variability and deep learning approach: a case study in South Korea
title_short Dam inflow prediction using large-scale climate variability and deep learning approach: a case study in South Korea
title_sort dam inflow prediction using large scale climate variability and deep learning approach a case study in south korea
topic deep learning algorithm
large-scale climate variability
monthly dam inflow prediction
url http://ws.iwaponline.com/content/23/2/934
work_keys_str_mv AT heechanhan daminflowpredictionusinglargescaleclimatevariabilityanddeeplearningapproachacasestudyinsouthkorea
AT donghyunkim daminflowpredictionusinglargescaleclimatevariabilityanddeeplearningapproachacasestudyinsouthkorea
AT wonjoonwang daminflowpredictionusinglargescaleclimatevariabilityanddeeplearningapproachacasestudyinsouthkorea
AT hungsookim daminflowpredictionusinglargescaleclimatevariabilityanddeeplearningapproachacasestudyinsouthkorea