물 자연 그리고 사람 - 물로 더 행복한 세상을 만들어가겠습니다.
HOMER&D성과논문실적

논문실적

Autonomous calibration of EFDC for predicting chlorophyll-a using reinforcement learning and a real-time monitoring system 게시글의 제목, 학술지명, 저자, 발행일, 작성내용을 보여줌
Autonomous calibration of EFDC for predicting chlorophyll-a using reinforcement learning and a real-time monitoring system
학술지명 Environmental Modelling and Software 저자 Ather Abbas,Daeun Yun,Do Hyuck Kwon,JongCheol Pyo,Kyung Hwa Cho,Nakyung Yoon,Seok Min Hong,Soobin Kim,Yakov Pachepsky,이상욱
발표일 2023-08-21

Cyanobacterial blooms cause critical damage to aquatic ecosystems and water resources. Therefore, numerical models have been utilized to simulate cyanobacteria by calibrating model parameters for accurate simulation. While conventional calibration, which uses fixed water quality parameters throughout the simulation period, is commonly utilized, it may lead to  inaccurate modeling results. To address it, this study proposed a reinforcement learning and environmental fluid dynamics code (EFDC-RL) model that uses real-time pontoon monitoring data and hyperspectral images to autonomously control water quality parameters. The EFDC-RL model showed impressive performance, with an R2 value of 0.7406 and 0.4126 for the  raining and test datasets, respectively. In comparison, the Chlorophyll-a simulation of conventional calibration had an R2 of 0.2133 and 0.0220, respectively. This study shows that the EFDC-RL model is a suitable framework for autonomous calibration of water quality parameters and real-time spatiotemporal simulation of cyanobacteria distribution.

목록