Water Level Forecasting Using Deep Learning Time-Series Analysis: A Case Study of Red River of the North
The Red River of the North is vulnerable to floods, which have caused significant damage and economic loss to inhabitants. A better capability in flood-event prediction is essential to decision-makers for planning flood-loss-reduction strategies. Over the last decades, classical statistical methods...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-06-01
|
Series: | Water |
Subjects: | |
Online Access: | https://www.mdpi.com/2073-4441/14/12/1971 |
_version_ | 1797481196492423168 |
---|---|
author | Vida Atashi Hamed Taheri Gorji Seyed Mojtaba Shahabi Ramtin Kardan Yeo Howe Lim |
author_facet | Vida Atashi Hamed Taheri Gorji Seyed Mojtaba Shahabi Ramtin Kardan Yeo Howe Lim |
author_sort | Vida Atashi |
collection | DOAJ |
description | The Red River of the North is vulnerable to floods, which have caused significant damage and economic loss to inhabitants. A better capability in flood-event prediction is essential to decision-makers for planning flood-loss-reduction strategies. Over the last decades, classical statistical methods and Machine Learning (ML) algorithms have greatly contributed to the growth of data-driven forecasting systems that provide cost-effective solutions and improved performance in simulating the complex physical processes of floods using mathematical expressions. To make improvements to flood prediction for the Red River of the North, this paper presents effective approaches that make use of a classical statistical method, a classical ML algorithm, and a state-of-the-art Deep Learning method. Respectively, the methods are seasonal autoregressive integrated moving average (SARIMA), Random Forest (RF), and Long Short-Term Memory (LSTM). We used hourly level records from three U.S. Geological Survey (USGS), at Pembina, Drayton, and Grand Forks stations with twelve years of data (2007–2019), to evaluate the water level at six hours, twelve hours, one day, three days, and one week in advance. Pembina, at the downstream location, has a water level gauge but not a flow-gauging station, unlike the others. The floodwater-level-prediction results show that the LSTM method outperforms the SARIMA and RF methods. For the one-week-ahead prediction, the RMSE values for Pembina, Drayton, and Grand Forks are 0.190, 0.151, and 0.107, respectively. These results demonstrate the high precision of the Deep Learning algorithm as a reliable choice for flood-water-level prediction. |
first_indexed | 2024-03-09T22:11:03Z |
format | Article |
id | doaj.art-176a9154342447c791f98d8c3f3bd4e7 |
institution | Directory Open Access Journal |
issn | 2073-4441 |
language | English |
last_indexed | 2024-03-09T22:11:03Z |
publishDate | 2022-06-01 |
publisher | MDPI AG |
record_format | Article |
series | Water |
spelling | doaj.art-176a9154342447c791f98d8c3f3bd4e72023-11-23T19:30:37ZengMDPI AGWater2073-44412022-06-011412197110.3390/w14121971Water Level Forecasting Using Deep Learning Time-Series Analysis: A Case Study of Red River of the NorthVida Atashi0Hamed Taheri Gorji1Seyed Mojtaba Shahabi2Ramtin Kardan3Yeo Howe Lim4Department of Civil Engineering, University of North Dakota, Grand Forks, ND 58202, USADepartment of Biomedical Engineering, University of North Dakota, Grand Forks, ND 58202, USASchool of Electrical Engineering & Computer Science, University of North Dakota, Grand Forks, ND 58202, USADepartment of Mechanical Engineering, University of North Dakota, Grand Forks, ND 58202, USADepartment of Civil Engineering, University of North Dakota, Grand Forks, ND 58202, USAThe Red River of the North is vulnerable to floods, which have caused significant damage and economic loss to inhabitants. A better capability in flood-event prediction is essential to decision-makers for planning flood-loss-reduction strategies. Over the last decades, classical statistical methods and Machine Learning (ML) algorithms have greatly contributed to the growth of data-driven forecasting systems that provide cost-effective solutions and improved performance in simulating the complex physical processes of floods using mathematical expressions. To make improvements to flood prediction for the Red River of the North, this paper presents effective approaches that make use of a classical statistical method, a classical ML algorithm, and a state-of-the-art Deep Learning method. Respectively, the methods are seasonal autoregressive integrated moving average (SARIMA), Random Forest (RF), and Long Short-Term Memory (LSTM). We used hourly level records from three U.S. Geological Survey (USGS), at Pembina, Drayton, and Grand Forks stations with twelve years of data (2007–2019), to evaluate the water level at six hours, twelve hours, one day, three days, and one week in advance. Pembina, at the downstream location, has a water level gauge but not a flow-gauging station, unlike the others. The floodwater-level-prediction results show that the LSTM method outperforms the SARIMA and RF methods. For the one-week-ahead prediction, the RMSE values for Pembina, Drayton, and Grand Forks are 0.190, 0.151, and 0.107, respectively. These results demonstrate the high precision of the Deep Learning algorithm as a reliable choice for flood-water-level prediction.https://www.mdpi.com/2073-4441/14/12/1971flood predictionwater levelRed RiverSARIMARFLSTM |
spellingShingle | Vida Atashi Hamed Taheri Gorji Seyed Mojtaba Shahabi Ramtin Kardan Yeo Howe Lim Water Level Forecasting Using Deep Learning Time-Series Analysis: A Case Study of Red River of the North Water flood prediction water level Red River SARIMA RF LSTM |
title | Water Level Forecasting Using Deep Learning Time-Series Analysis: A Case Study of Red River of the North |
title_full | Water Level Forecasting Using Deep Learning Time-Series Analysis: A Case Study of Red River of the North |
title_fullStr | Water Level Forecasting Using Deep Learning Time-Series Analysis: A Case Study of Red River of the North |
title_full_unstemmed | Water Level Forecasting Using Deep Learning Time-Series Analysis: A Case Study of Red River of the North |
title_short | Water Level Forecasting Using Deep Learning Time-Series Analysis: A Case Study of Red River of the North |
title_sort | water level forecasting using deep learning time series analysis a case study of red river of the north |
topic | flood prediction water level Red River SARIMA RF LSTM |
url | https://www.mdpi.com/2073-4441/14/12/1971 |
work_keys_str_mv | AT vidaatashi waterlevelforecastingusingdeeplearningtimeseriesanalysisacasestudyofredriverofthenorth AT hamedtaherigorji waterlevelforecastingusingdeeplearningtimeseriesanalysisacasestudyofredriverofthenorth AT seyedmojtabashahabi waterlevelforecastingusingdeeplearningtimeseriesanalysisacasestudyofredriverofthenorth AT ramtinkardan waterlevelforecastingusingdeeplearningtimeseriesanalysisacasestudyofredriverofthenorth AT yeohowelim waterlevelforecastingusingdeeplearningtimeseriesanalysisacasestudyofredriverofthenorth |