EUNMI LEE

POSTECH 

Division of Environmental Science and Engineering

Hydroclimatology Research Lab



 Make a difference for the people, the environment, and society

EUNMI LEE


Present position: Combined Master and Doctor course

Email: eunmi.green@postech.ac.kr

Address: Pohang University of Science and Technology (POSTECH) Pohang, South Korea 

 Education

 Research Interest

: Big Data Processing, Deep Learning Model Development (DNN, RNN, LSTM, GRU), Bayesian Optimization 

Current Research Topic

Deciphering the black box of artificial intelligence: An explainability scenario-based design of deep learning for multi-purpose dam operation modeling

The Gated Recurrent Unit (GRU) algorithm is employed to predict the hourly water level of the dam reservoirs over 2002–2021. 


This study aims to assess the predictability and explainability of a deep learning algorithm-based model for three multi-purpose dam operation (Seomjin River dam, Juam dam, and Juam Control dam) in Seomjin River basin, South Korea. 


- An explainability scenario-based design for multi-purpose dam operation modeling was proposed. 

- The trained GRU models showed diverse responses to altered inflow, precipitation, and outflow 

- The diverse responses were explainable from the observed input-output relationship 



Flood risk assessment and social awareness in South Korea


Conferences

- 'Regional Flood Awareness Vulnerability Based on NAVER DATA LAB'

- 'Utility of deep learning model in hydrologic forecasting water level of dams: A case study of Seomjin River'

Awards, Scholarship, and Honors

 Non-Academic Experiences