Publication:
Effect of Gradient Descent Optimizers and Dropout Technique on Deep Learning LSTM Performance in Rainfall‑runoff Modeling
Effect of Gradient Descent Optimizers and Dropout Technique on Deep Learning LSTM Performance in Rainfall‑runoff Modeling
| dc.contributor.author | "Duong Tran Anh, Dat Vi Thanh, Hoang Minh Le, Bang Tran Sy, Ahad Hasan Tanim, Quoc Bao Pham, Thanh Duc Dang, Son T. Mai, Nguyen Mai Dang." | |
| dc.date.accessioned | 2023-12-19T02:32:14Z | |
| dc.date.available | 2023-12-19T02:32:14Z | |
| dc.date.issued | 2023 | |
| dc.description.abstract | Machine learning and deep learning (ML-DL) based models are widely used for rainfall runof prediction and they have potential to substitute process-oriented physics based numerical models. However, developing an ML model has also performance uncertainty because of inaccurate choices of hyperparameters and neural networks architectures. Thus, this study aims to search for best optimization algorithms to be used in ML-DL models namely, RMSprop, Adagrad, Adadelta, and Adam optimizers, as well as dropout tech niques to be integrated into the Long Short Term Memory (LSTM) model to improve forecasting accuracy of rainfall-runof modeling. A deep learning LSTMs were developed using 480 model architectures at two hydro-meteorological stations of the Mekong Delta, Vietnam, namely Chau Doc and Can Tho. The model performance is tested with the most ideally suited LSTM optimizers utilizing combinations of four dropout percentages respec tively, 0%, 10%, 20%, and 30%. The Adagrad optimizer shows the best model performance in the model testing. Deep learning LSTM models with 10% dropout made the best predic tion results while signifcantly reducing overftting tendency of the forecasted time series. The fndings of this study are valuable for ML-based hydrological models set up by identi fying a suitable gradient descent (GD) optimizer and optimal dropout ratio to enhance the performance and forecasting accuracy of the ML model. | |
| dc.identifier.uri | http://repository.vlu.edu.vn:443/handle/123456789/11114 | |
| dc.language.iso | en_US | |
| dc.relation.ispartof | Water Resources Management | |
| dc.relation.issn | 1573-1650 | |
| dc.subject | Optimizers · Dropout technique · LSTM · Rainfall-runof · Mekong delta | |
| dc.title | Effect of Gradient Descent Optimizers and Dropout Technique on Deep Learning LSTM Performance in Rainfall‑runoff Modeling | |
| dc.type | Resource Types::text::journal::journal article | |
| dspace.entity.type | Publication | |
| oairecerif.author.affiliation | #PLACEHOLDER_PARENT_METADATA_VALUE# |
Files
Original bundle
1 - 1 of 1