Determination of Deep Learning Model and Optimum Length of Training Data in the River with Large Fluctuations in Flow Rates
Recently, developing countries have steadily been pushing for the construction of stream-oriented smart cities, breaking away from the existing old-town-centered development in the past. Due to the accelerating effects of climate change along with such urbanization, it is imperative for urban rivers...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-12-01
|
Series: | Water |
Subjects: | |
Online Access: | https://www.mdpi.com/2073-4441/12/12/3537 |
id |
doaj-843163b59a124d8dbddef55fa0397a12 |
---|---|
record_format |
Article |
spelling |
doaj-843163b59a124d8dbddef55fa0397a122020-12-17T00:04:05ZengMDPI AGWater2073-44412020-12-01123537353710.3390/w12123537Determination of Deep Learning Model and Optimum Length of Training Data in the River with Large Fluctuations in Flow RatesKidoo Park0Younghun Jung1Kyungtak Kim2Seung Kook Park3Emergency Management Institute, Kyungpook National University, Gyeongbuk 37224, KoreaDepartment of Advanced Science and Technology Convergence, Kyungpook National University, Gyeongbuk 37224, KoreaKorea Institute of Civil Engineering and Building Technology, Goyang-si, Gyeonggi-do 10223, KoreaKorea Research Institute for Construction Policy, Seoul 07071, KoreaRecently, developing countries have steadily been pushing for the construction of stream-oriented smart cities, breaking away from the existing old-town-centered development in the past. Due to the accelerating effects of climate change along with such urbanization, it is imperative for urban rivers to establish a flood warning system that can predict the amount of high flow rates of accuracy in engineering, compared to using the existing Computational Fluid Dynamics (CFD) models for disaster prevention. In this study, in the case of streams where missing data existed or only small observations were obtained, the variation in flow rates could be predicted with only the appropriate deep learning models, using only limited time series flow data. In addition, the selected deep learning model allowed the minimum number of input learning data to be determined. In this study, the time series flow rates were predicted by applying the deep learning models to the Han River, which is a highly urbanized stream that flows through the capital of Korea, Seoul and has a large seasonal variation in the flow rate. The deep learning models used are Convolution Neural Network (CNN), Simple Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), Bidirectional LSTM (Bi-LSTM) and Gated Recurrent Unit (GRU). Sequence lengths for time series runoff data were determined first to assess the accuracy and applicability of the deep learning models. By analyzing the forecast results of the outflow data of the Han River, sequence length for 14 days was appropriate in terms of the predicted accuracy of the model. In addition, the GRU model is effective for deep learning models that use time series data of the region with large fluctuations in flow rates, such as the Han River. Furthermore, through this study, it was possible to propose the minimum number of training data that could provide flood warning system with an effective flood forecasting system although the number of input data such as flow rates secured in new towns developed around rivers was insufficient.https://www.mdpi.com/2073-4441/12/12/3537flood warning systemdeep learning modeltime-series flow rateslarge seasonal variationSimple RNNCNN |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Kidoo Park Younghun Jung Kyungtak Kim Seung Kook Park |
spellingShingle |
Kidoo Park Younghun Jung Kyungtak Kim Seung Kook Park Determination of Deep Learning Model and Optimum Length of Training Data in the River with Large Fluctuations in Flow Rates Water flood warning system deep learning model time-series flow rates large seasonal variation Simple RNN CNN |
author_facet |
Kidoo Park Younghun Jung Kyungtak Kim Seung Kook Park |
author_sort |
Kidoo Park |
title |
Determination of Deep Learning Model and Optimum Length of Training Data in the River with Large Fluctuations in Flow Rates |
title_short |
Determination of Deep Learning Model and Optimum Length of Training Data in the River with Large Fluctuations in Flow Rates |
title_full |
Determination of Deep Learning Model and Optimum Length of Training Data in the River with Large Fluctuations in Flow Rates |
title_fullStr |
Determination of Deep Learning Model and Optimum Length of Training Data in the River with Large Fluctuations in Flow Rates |
title_full_unstemmed |
Determination of Deep Learning Model and Optimum Length of Training Data in the River with Large Fluctuations in Flow Rates |
title_sort |
determination of deep learning model and optimum length of training data in the river with large fluctuations in flow rates |
publisher |
MDPI AG |
series |
Water |
issn |
2073-4441 |
publishDate |
2020-12-01 |
description |
Recently, developing countries have steadily been pushing for the construction of stream-oriented smart cities, breaking away from the existing old-town-centered development in the past. Due to the accelerating effects of climate change along with such urbanization, it is imperative for urban rivers to establish a flood warning system that can predict the amount of high flow rates of accuracy in engineering, compared to using the existing Computational Fluid Dynamics (CFD) models for disaster prevention. In this study, in the case of streams where missing data existed or only small observations were obtained, the variation in flow rates could be predicted with only the appropriate deep learning models, using only limited time series flow data. In addition, the selected deep learning model allowed the minimum number of input learning data to be determined. In this study, the time series flow rates were predicted by applying the deep learning models to the Han River, which is a highly urbanized stream that flows through the capital of Korea, Seoul and has a large seasonal variation in the flow rate. The deep learning models used are Convolution Neural Network (CNN), Simple Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), Bidirectional LSTM (Bi-LSTM) and Gated Recurrent Unit (GRU). Sequence lengths for time series runoff data were determined first to assess the accuracy and applicability of the deep learning models. By analyzing the forecast results of the outflow data of the Han River, sequence length for 14 days was appropriate in terms of the predicted accuracy of the model. In addition, the GRU model is effective for deep learning models that use time series data of the region with large fluctuations in flow rates, such as the Han River. Furthermore, through this study, it was possible to propose the minimum number of training data that could provide flood warning system with an effective flood forecasting system although the number of input data such as flow rates secured in new towns developed around rivers was insufficient. |
topic |
flood warning system deep learning model time-series flow rates large seasonal variation Simple RNN CNN |
url |
https://www.mdpi.com/2073-4441/12/12/3537 |
work_keys_str_mv |
AT kidoopark determinationofdeeplearningmodelandoptimumlengthoftrainingdataintheriverwithlargefluctuationsinflowrates AT younghunjung determinationofdeeplearningmodelandoptimumlengthoftrainingdataintheriverwithlargefluctuationsinflowrates AT kyungtakkim determinationofdeeplearningmodelandoptimumlengthoftrainingdataintheriverwithlargefluctuationsinflowrates AT seungkookpark determinationofdeeplearningmodelandoptimumlengthoftrainingdataintheriverwithlargefluctuationsinflowrates |
_version_ |
1724380691037159424 |