Development of Water Level Prediction Models Using Machine Learning in Wetlands: A Case Study of Upo Wetland in South Korea

Changhyun Choi,Jungwook Kim,Daegun Han,Heechan Han,Hung Soo Kim

doi:10.3390/w12010093

Abstract

Wetlands play a vital role in hydrologic and ecologic communities. Since there are few studies conducted for wetland water level prediction due to the unavailability of data, this study developed a water level prediction model using various machine learning models such as artificial neural network (ANN), decision tree (DT), random forest (RF), and support vector machine (SVM). The Upo wetland, which is the largest inland wetland in South Korea, was selected as the study area. The daily water level gauge data from 2009 to 2015 were used as dependent variables, while the meteorological data and upstream water level gauge data were used as independent variables. Predictive performance evaluation using RF as the final model revealed 0.96 value for correlation coefficient (CC), 0.92 for Nash–Sutcliffe efficiency (NSE), 0.09 for root mean square error (RMSE), and 0.19 for persistence index (PI). The results indicate that the water level of the Upo wetland was well predicted, showing superior results compared to that of the ANN, which was used in a previous study. The results intend to provide basic data for development of a wetland management method, using water levels of previously ungauged areas.

Highlights

IntroductionEcological, and hydrological roles, such as maintaining species diversity, providing nutrients, controlling water levels, and reducing floods and droughts [1]
Wetlands play important environmental, ecological, and hydrological roles, such as maintaining species diversity, providing nutrients, controlling water levels, and reducing floods and droughts [1].Hydraulic and hydrological conditions, such as flow rate, water level, and inundation depth, are significant constraints for aquatic environments, including wetlands [2,3]
For the artificial neural network (ANN), the predictive performance is good if the values ranges between 0 and 1 [56]; the dependent and independent variables are standardized to values between 0 and 1 using the re-scaling method as shown in Equation (6)

Summary

Introduction

Ecological, and hydrological roles, such as maintaining species diversity, providing nutrients, controlling water levels, and reducing floods and droughts [1]. Hydraulic and hydrological conditions, such as flow rate, water level, and inundation depth, are significant constraints for aquatic environments, including wetlands [2,3]. Wetland species have their preferred inundation depths or permissible water level limits. Water level measurement and prediction are known to be important for proper wetland management and protection [4,5,6,7]. Environmental engineers and scientists are well-aware of the importance of measuring and predicting water levels in wetlands [8]. Water level measurement is limited, especially in some wetland regions. In South Korea, a concrete example of this is the inadequately monitored

Objectives

Methods

Results

Discussion

Conclusion