Predicting Inflow Rate of the Soyang River Dam Using Deep Learning Techniques
The Soyang Dam, the largest multipurpose dam in Korea, faces water resource management challenges due to global warming. Global warming increases the duration and frequency of days with high temperatures and extreme precipitation events. Therefore, it is crucial to accurately predict the inflow rate...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-09-01
|
| Series: | Water |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4441/13/17/2447 |
| _version_ | 1797520729681428480 |
|---|---|
| author | Sangwon Lee Jaekwang Kim |
| author_facet | Sangwon Lee Jaekwang Kim |
| author_sort | Sangwon Lee |
| collection | DOAJ |
| description | The Soyang Dam, the largest multipurpose dam in Korea, faces water resource management challenges due to global warming. Global warming increases the duration and frequency of days with high temperatures and extreme precipitation events. Therefore, it is crucial to accurately predict the inflow rate for water resource management because it helps plan for flood, drought, and power generation in the Seoul metropolitan area. However, the lack of hydrological data for the Soyang River Dam causes a physical-based model to predict the inflow rate inaccurately. This study uses nearly 15 years of meteorological, dam, and weather warning data to overcome the lack of hydrological data and predict the inflow rate over two days. In addition, a sequence-to-sequence (Seq2Seq) mechanism combined with a bidirectional long short-term memory (LSTM) is developed to predict the inflow rate. The proposed model exhibits state-of-the-art prediction accuracy with root mean square error (RMSE) of 44.17 m<sup>3</sup>/s and 58.59 m<sup>3</sup>/s, mean absolute error (MAE) of 14.94 m<sup>3</sup>/s and 17.11 m<sup>3</sup>/s, and Nash–Sutcliffe efficiency (NSE) of 0.96 and 0.94, for forecasting first and second day, respectively. |
| first_indexed | 2024-03-10T08:00:45Z |
| format | Article |
| id | doaj.art-1c48b4cb78474ae0b22a5e58bf4c045d |
| institution | Directory Open Access Journal |
| issn | 2073-4441 |
| language | English |
| last_indexed | 2024-03-10T08:00:45Z |
| publishDate | 2021-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Water |
| spelling | doaj.art-1c48b4cb78474ae0b22a5e58bf4c045d2023-11-22T11:25:59ZengMDPI AGWater2073-44412021-09-011317244710.3390/w13172447Predicting Inflow Rate of the Soyang River Dam Using Deep Learning TechniquesSangwon Lee0Jaekwang Kim1Department of Applied Data Science, Sungkyunkwan University, Suwon 16419, KoreaSchool of Convergence, Sungkyunkwan University, Seoul 03063, KoreaThe Soyang Dam, the largest multipurpose dam in Korea, faces water resource management challenges due to global warming. Global warming increases the duration and frequency of days with high temperatures and extreme precipitation events. Therefore, it is crucial to accurately predict the inflow rate for water resource management because it helps plan for flood, drought, and power generation in the Seoul metropolitan area. However, the lack of hydrological data for the Soyang River Dam causes a physical-based model to predict the inflow rate inaccurately. This study uses nearly 15 years of meteorological, dam, and weather warning data to overcome the lack of hydrological data and predict the inflow rate over two days. In addition, a sequence-to-sequence (Seq2Seq) mechanism combined with a bidirectional long short-term memory (LSTM) is developed to predict the inflow rate. The proposed model exhibits state-of-the-art prediction accuracy with root mean square error (RMSE) of 44.17 m<sup>3</sup>/s and 58.59 m<sup>3</sup>/s, mean absolute error (MAE) of 14.94 m<sup>3</sup>/s and 17.11 m<sup>3</sup>/s, and Nash–Sutcliffe efficiency (NSE) of 0.96 and 0.94, for forecasting first and second day, respectively.https://www.mdpi.com/2073-4441/13/17/2447dam inflowmachine learningbidirectional LSTMSeq2Seqdeep learning |
| spellingShingle | Sangwon Lee Jaekwang Kim Predicting Inflow Rate of the Soyang River Dam Using Deep Learning Techniques Water dam inflow machine learning bidirectional LSTM Seq2Seq deep learning |
| title | Predicting Inflow Rate of the Soyang River Dam Using Deep Learning Techniques |
| title_full | Predicting Inflow Rate of the Soyang River Dam Using Deep Learning Techniques |
| title_fullStr | Predicting Inflow Rate of the Soyang River Dam Using Deep Learning Techniques |
| title_full_unstemmed | Predicting Inflow Rate of the Soyang River Dam Using Deep Learning Techniques |
| title_short | Predicting Inflow Rate of the Soyang River Dam Using Deep Learning Techniques |
| title_sort | predicting inflow rate of the soyang river dam using deep learning techniques |
| topic | dam inflow machine learning bidirectional LSTM Seq2Seq deep learning |
| url | https://www.mdpi.com/2073-4441/13/17/2447 |
| work_keys_str_mv | AT sangwonlee predictinginflowrateofthesoyangriverdamusingdeeplearningtechniques AT jaekwangkim predictinginflowrateofthesoyangriverdamusingdeeplearningtechniques |