Streamflow Predictions in Ungauged Basins Using Recurrent Neural Network and Decision Tree-Based Algorithm: Application to the Southern Region of the Korean Peninsula
Jeongeun Won,
Jiyu Seo,
Jeonghoon Lee,
Jeonghyeon Choi,
Yoonkyung Park,
Okjeong Lee,
Sangdan Kim
Affiliations
Jeongeun Won
Major of Environmental Engineering, Division of Earth Environmental System Science, Pukyong National University, Busan 48513, Republic of Korea
Jiyu Seo
Major of Environmental Engineering, Division of Earth Environmental System Science, Pukyong National University, Busan 48513, Republic of Korea
Jeonghoon Lee
Major of Environmental Engineering, Division of Earth Environmental System Science, Pukyong National University, Busan 48513, Republic of Korea
Jeonghyeon Choi
Department of Hydro Science and Engineering Research, Korea Institute of Civil Engineering and Building Technology (KICT), Goyang 10223, Republic of Korea
Yoonkyung Park
Department of Environmental Research, Korea Institute of Civil Engineering and Building Technology (KICT), Goyang 10223, Republic of Korea
Okjeong Lee
Forecast and Control Division, Nakdong River Flood Control Office, Busan 49300, Republic of Korea
Sangdan Kim
Major of Environmental Engineering, Division of Earth Environmental System Science, Pukyong National University, Busan 48513, Republic of Korea
River runoff predictions in ungauged basins are one of the major challenges in hydrology. In the past, the approach using a physical-based conceptual model was the main approach, but recently, a solution using a data-driven model has been evaluated as more appropriate through several studies. In this study, a new data-driven approach combining various recurrent neural networks and decision tree-based algorithms is proposed. An advantage of recurrent neural networks is that they can learn long-term dependencies between inputs and outputs provided to the network. Decision tree-based algorithms, combined with recurrent neural networks, serve to reflect topographical information treated as constants and can identify the importance of input features. We tested the proposed approach using data from 25 watersheds publicly available on the Korean government’s website. The potential of the proposed approach as a regional hydrologic model is evaluated in the view that one regional model predicts river runoff in various watersheds using the leave-one-out cross-validation regionalization setup.