Developing a Discharge Estimation Model for Ungauged Watershed Using CNN and Hydrological Image

This study aimed to estimate the discharge in ungauged watersheds. To this end, we herein deviated from the model development methodology of previous studies and used convolution neural network (CNN), a deep training algorithm, and hydrological images. As the CNN model was developed for solving classification issues in general, it is unsuitable for simulating the discharge, which is a continuous variable. Therefore, the fully connected layer of the CNN model was improved. Moreover, images reflecting the hydrological conditions rather than a general photograph were used as input data for the CNN model. Three study areas that have discharge gauged data were set for the model’s training and testing. The data from two of the three study areas were used for CNN model training, and the data of the other were used to evaluate model prediction performance. The results of this study demonstrate a moderate predictive success of the discharge of an ungauged watershed using the CNN model and hydrological images. Therefore, it can be suitable as a methodology for the discharge estimation of ungauged watersheds. Simultaneously, it is expected that our methodology can be applied to the field of remote sensing or to the field of real-time discharge simulation using satellite imagery on a global scale or across a wide area.

Development of simple distributed hydrological model based on soil moisture simulation

<p>One of challenges to hydrologists is to estimate runoff from ungauged watershed. Hydrologic estimation through modelling is a reasonable, economical and useful approach to quantity and quality management of watershed. The model framework has been comprehensive and complex to reproduce natural phenomena more realistically with the development of computer hardware. However, driving a complex model requires a lot of effort and time, and the use of many parameters reduces the accessibility of end users and the applicability to the ungauged watershed. In this study, we developed a distributed hydrologic model based on soil moisture simulation using simple composition and fewer parameters. Instead of minimizing the number of parameters, GIS data were used to reflect the watershed characteristics into the model. The proposed model was applied to the four dam watersheds in Korea to assess its performance. As a result, it is confirmed that reasonable hydrologic components simulation is possible through the simulation of soil moisture, even though it was a simple model with only three input parameters. If spatial data such as satellite data is additionally applied, the performance of the model is expected to improve further.</p><p><strong>Acknowledgment:</strong> This work was supported by Korea Environment Industry & Technology Institute(KEITI) through Public Technology Program based on Environmental Policy Project, funded by Korea Ministry of Environment(MOE)(2016000200002).</p><p><strong>Keywords</strong>: Distributed hydrological model; Hydrologic components simulation; Soil moisture; Simple hydrological model.</p>