Streamflow Predictions in Ungauged Basins Using Recurrent Neural Network and Decision Tree-Based Algorithm: Application to the Southern Region of the Korean Peninsula

Abstract

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.

Understanding and mitigating global change with aquatic sensors: current challenges and future prospects

“…While automated sensors can collect orders of magnitude more environmental data, which is an enormous benefit, there is also the enormous challenge of storing and handling the data, which may be beyond the experience of many researchers. This requires access to an appropriate cyberinfrastructure to communicate the data to a central server with the storage capacity, which could occupy terabytes of storage space (Schmidt and Kerkez, 2023;Yousif et al, 2022;Won et al, 2023). As the data arrive in large quantities, most research groups may find it overwhelming to check the quality of the massive inputs of data generated without appropriate ITliterate staff.…”

Feature Extraction from Satellite-Derived Hydroclimate Data: Assessing Impacts on Various Neural Networks for Multi-Step Ahead Streamflow Prediction

“…Hydrological models are broadly classified into two categories: physical-driven and data-driven models [15][16][17]. Physical models face limitations in dealing with straightforward hydrological processes because of the intricate relationships between environmental variables and streamflow [18]. However, the latter involves statistical and artificial intelligence (AI) approaches without the need for an explicit physics-based scheme [19].…”