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

논문실적

Enhancing Dam Hourly Inflow Prediction Performance using Improved Inflow Data Preprocessing and LSTM: Integration of Event Identification & Exponential Smoothing (IE2S)-LSTM 게시글의 제목, 학술지명, 저자, 발행일, 작성내용을 보여줌
Enhancing Dam Hourly Inflow Prediction Performance using Improved Inflow Data Preprocessing and LSTM: Integration of Event Identification & Exponential Smoothing (IE2S)-LSTM
학술지명 12th International Congress on Environmental Modeling and Software (iEMSS) 저자 최영돈
발표일 2024-06-24

The performance of LSTMs in analyzing rainfall-runoff dynamics has demonstrated better performance over the physically-based hydrological models. However, data quality remains crucial to further improve the performance of LSTM. In this study, we applied the Integration of Event Identification & Exponential Smoothing (IE2S) method to reduce the fluctuations in inflow, which are typically estimated by the Simple Water Balance method. The preprocessed inflow data was then used to train a LSTM, demonstrating a noticeable improvement in reliability and variability for hourly inflow prediction. This research presents not only new deep learning methods but also data-centric research that is critical to improving the performance of deep learning as an example of rainfall-runoff analysis.

목록