Deep learning model on rates of change for multi-step ahead streamflow forecasting
Water security and urban flooding have become major sustainability issues. This paper presents a novel method to introduce rates of change as the state-of-the-art approach in artificial intelligence model development for sustainability agenda. Multi-layer perceptron (MLP) and deep learning long sho...
Saved in:
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IWA Publishing
2023
|
Subjects: | |
Online Access: | http://ir.unimas.my/id/eprint/44852/5/Deep%20learning.pdf http://ir.unimas.my/id/eprint/44852/ https://iwaponline.com/jh/article/25/5/1667/96790/Deep-learning-model-on-rates-of-change-for-multi |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my.unimas.ir.44852 |
---|---|
record_format |
eprints |
spelling |
my.unimas.ir.448522024-05-27T01:37:40Z http://ir.unimas.my/id/eprint/44852/ Deep learning model on rates of change for multi-step ahead streamflow forecasting Tan, Woon Yang Lai, Sai Hin Kumar, Pavitra Teo, Fang Yenn Ahmed, El-Shafie TC Hydraulic engineering. Ocean engineering Water security and urban flooding have become major sustainability issues. This paper presents a novel method to introduce rates of change as the state-of-the-art approach in artificial intelligence model development for sustainability agenda. Multi-layer perceptron (MLP) and deep learning long short-term memory (LSTM) models were considered for flood forecasting. Historical rainfall data from 2008 to 2021 at 11 telemetry stations were obtained to predict flow at the confluence between Klang River and Ampang River. The initial results of MLP yielded poor performance beneath normal expectations, which was R ¼ 0.4465, MAE ¼ 3.7135, NSE ¼ 0.1994 and RMSE ¼ 8.8556. Meanwhile, the LSTM model generated a 45% improvement in its R-value up to 0.9055. Detailed investigations found that the redundancy of data input that yielded multiple target values had distorted the model performance. Qt was introduced into input parameters to solve this issue, while Qtþ0.5 was the target value. A significant improvement in the results was detected with R ¼ 0.9359, MAE ¼ 0.7722, NSE ¼ 0.8756 and RMSE ¼ 3.4911. When the rates of change were employed, an impressive improvement was seen for the plot of actual vs. forecasted flow. Findings showed that the rates of change could reduce forecast errors and were helpful as an additional layer of early flood detection. IWA Publishing 2023 Article PeerReviewed text en http://ir.unimas.my/id/eprint/44852/5/Deep%20learning.pdf Tan, Woon Yang and Lai, Sai Hin and Kumar, Pavitra and Teo, Fang Yenn and Ahmed, El-Shafie (2023) Deep learning model on rates of change for multi-step ahead streamflow forecasting. Journal of Hydroinformatics, 25 (5). pp. 1667-1689. ISSN 1465-1734 https://iwaponline.com/jh/article/25/5/1667/96790/Deep-learning-model-on-rates-of-change-for-multi doi: 10.2166/hydro.2023.001 |
institution |
Universiti Malaysia Sarawak |
building |
Centre for Academic Information Services (CAIS) |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Malaysia Sarawak |
content_source |
UNIMAS Institutional Repository |
url_provider |
http://ir.unimas.my/ |
language |
English |
topic |
TC Hydraulic engineering. Ocean engineering |
spellingShingle |
TC Hydraulic engineering. Ocean engineering Tan, Woon Yang Lai, Sai Hin Kumar, Pavitra Teo, Fang Yenn Ahmed, El-Shafie Deep learning model on rates of change for multi-step ahead streamflow forecasting |
description |
Water security and urban flooding have become major sustainability issues. This paper presents a novel method to introduce rates of change as the state-of-the-art approach in artificial intelligence model development for sustainability agenda. Multi-layer perceptron (MLP) and deep
learning long short-term memory (LSTM) models were considered for flood forecasting. Historical rainfall data from 2008 to 2021 at 11 telemetry stations were obtained to predict flow at the confluence between Klang River and Ampang River. The initial results of MLP yielded poor
performance beneath normal expectations, which was R ¼ 0.4465, MAE ¼ 3.7135, NSE ¼ 0.1994 and RMSE ¼ 8.8556. Meanwhile, the LSTM model generated a 45% improvement in its R-value up to 0.9055. Detailed investigations found that the redundancy of data input that yielded multiple target values had distorted the model performance. Qt was introduced into input parameters to solve this issue, while Qtþ0.5 was the
target value. A significant improvement in the results was detected with R ¼ 0.9359, MAE ¼ 0.7722, NSE ¼ 0.8756 and RMSE ¼ 3.4911. When the rates of change were employed, an impressive improvement was seen for the plot of actual vs. forecasted flow. Findings showed that the rates of change could reduce forecast errors and were helpful as an additional layer of early flood detection. |
format |
Article |
author |
Tan, Woon Yang Lai, Sai Hin Kumar, Pavitra Teo, Fang Yenn Ahmed, El-Shafie |
author_facet |
Tan, Woon Yang Lai, Sai Hin Kumar, Pavitra Teo, Fang Yenn Ahmed, El-Shafie |
author_sort |
Tan, Woon Yang |
title |
Deep learning model on rates of change for multi-step ahead streamflow forecasting |
title_short |
Deep learning model on rates of change for multi-step ahead streamflow forecasting |
title_full |
Deep learning model on rates of change for multi-step ahead streamflow forecasting |
title_fullStr |
Deep learning model on rates of change for multi-step ahead streamflow forecasting |
title_full_unstemmed |
Deep learning model on rates of change for multi-step ahead streamflow forecasting |
title_sort |
deep learning model on rates of change for multi-step ahead streamflow forecasting |
publisher |
IWA Publishing |
publishDate |
2023 |
url |
http://ir.unimas.my/id/eprint/44852/5/Deep%20learning.pdf http://ir.unimas.my/id/eprint/44852/ https://iwaponline.com/jh/article/25/5/1667/96790/Deep-learning-model-on-rates-of-change-for-multi |
_version_ |
1800728209493327872 |
score |
13.18916 |