Deep Learning with Long Short Term Memory Based Sequence-to-Sequence Model for Rainfall-Runoff Simulation
Accurate runoff prediction is one of the important tasks in various fields such as agriculture, hydrology, and environmental studies. Recently, with massive improvements of computational system and hardware, the deep learning-based approach has recently been applied for more accurate runoff predicti...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-02-01
|
| Series: | Water |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4441/13/4/437 |
| _version_ | 1797412717262274560 |
|---|---|
| author | Heechan Han Changhyun Choi Jaewon Jung Hung Soo Kim |
| author_facet | Heechan Han Changhyun Choi Jaewon Jung Hung Soo Kim |
| author_sort | Heechan Han |
| collection | DOAJ |
| description | Accurate runoff prediction is one of the important tasks in various fields such as agriculture, hydrology, and environmental studies. Recently, with massive improvements of computational system and hardware, the deep learning-based approach has recently been applied for more accurate runoff prediction. In this study, the long short-term memory model with sequence-to-sequence structure was applied for hourly runoff predictions from 2015 to 2019 in the Russian River basin, California, USA. The proposed model was used to predict hourly runoff with lead time of 1–6 h using runoff data observed at upstream stations. The model was evaluated in terms of event-based performance using the statistical metrics including root mean square error, Nash-Sutcliffe Efficiency, peak runoff error, and peak time error. The results show that proposed model outperforms support vector machine and conventional long short-term memory models. In addition, the model has the best predictive ability for runoff events, which means that it can be effective for developing short-term flood forecasting and warning systems. The results of this study demonstrate that the deep learning-based approach for hourly runoff forecasting has high predictive power and sequence-to-sequence structure is effective method to improve the prediction results. |
| first_indexed | 2024-03-09T05:07:13Z |
| format | Article |
| id | doaj.art-a15559cb0e75490bace41f3500ba6ee9 |
| institution | Directory Open Access Journal |
| issn | 2073-4441 |
| language | English |
| last_indexed | 2024-03-09T05:07:13Z |
| publishDate | 2021-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Water |
| spelling | doaj.art-a15559cb0e75490bace41f3500ba6ee92023-12-03T12:53:44ZengMDPI AGWater2073-44412021-02-0113443710.3390/w13040437Deep Learning with Long Short Term Memory Based Sequence-to-Sequence Model for Rainfall-Runoff SimulationHeechan Han0Changhyun Choi1Jaewon Jung2Hung Soo Kim3Department of Civil and Environmental Engineering, Colorado State University, Fort Collins, CO 80523, USARisk Management Office, KB Claims Survey and Adjusting, Seoul 04027, KoreaInstitute of Water Resources System, Inha University, Incheon 22212, KoreaDepartment of Civil Engineering, Inha University, Incheon 22212, KoreaAccurate runoff prediction is one of the important tasks in various fields such as agriculture, hydrology, and environmental studies. Recently, with massive improvements of computational system and hardware, the deep learning-based approach has recently been applied for more accurate runoff prediction. In this study, the long short-term memory model with sequence-to-sequence structure was applied for hourly runoff predictions from 2015 to 2019 in the Russian River basin, California, USA. The proposed model was used to predict hourly runoff with lead time of 1–6 h using runoff data observed at upstream stations. The model was evaluated in terms of event-based performance using the statistical metrics including root mean square error, Nash-Sutcliffe Efficiency, peak runoff error, and peak time error. The results show that proposed model outperforms support vector machine and conventional long short-term memory models. In addition, the model has the best predictive ability for runoff events, which means that it can be effective for developing short-term flood forecasting and warning systems. The results of this study demonstrate that the deep learning-based approach for hourly runoff forecasting has high predictive power and sequence-to-sequence structure is effective method to improve the prediction results.https://www.mdpi.com/2073-4441/13/4/437deep learninghourly runoff predictionsequence-to-sequence structure |
| spellingShingle | Heechan Han Changhyun Choi Jaewon Jung Hung Soo Kim Deep Learning with Long Short Term Memory Based Sequence-to-Sequence Model for Rainfall-Runoff Simulation Water deep learning hourly runoff prediction sequence-to-sequence structure |
| title | Deep Learning with Long Short Term Memory Based Sequence-to-Sequence Model for Rainfall-Runoff Simulation |
| title_full | Deep Learning with Long Short Term Memory Based Sequence-to-Sequence Model for Rainfall-Runoff Simulation |
| title_fullStr | Deep Learning with Long Short Term Memory Based Sequence-to-Sequence Model for Rainfall-Runoff Simulation |
| title_full_unstemmed | Deep Learning with Long Short Term Memory Based Sequence-to-Sequence Model for Rainfall-Runoff Simulation |
| title_short | Deep Learning with Long Short Term Memory Based Sequence-to-Sequence Model for Rainfall-Runoff Simulation |
| title_sort | deep learning with long short term memory based sequence to sequence model for rainfall runoff simulation |
| topic | deep learning hourly runoff prediction sequence-to-sequence structure |
| url | https://www.mdpi.com/2073-4441/13/4/437 |
| work_keys_str_mv | AT heechanhan deeplearningwithlongshorttermmemorybasedsequencetosequencemodelforrainfallrunoffsimulation AT changhyunchoi deeplearningwithlongshorttermmemorybasedsequencetosequencemodelforrainfallrunoffsimulation AT jaewonjung deeplearningwithlongshorttermmemorybasedsequencetosequencemodelforrainfallrunoffsimulation AT hungsookim deeplearningwithlongshorttermmemorybasedsequencetosequencemodelforrainfallrunoffsimulation |