Understanding changes in sediment dynamics can significantly impact the sustainable development of the world. Modelling suspended sediment plays a crucial role because it allows decision makers and managers to formulate solutions that can avert the blockage of the sediments in a watershed. Estimates of suspended sediment is useful for global ecosystem service assessments and identify vulnerable aspects under climate change. In this study, it is suggested that the suspended sediment concentration at the Vu Gia-Thu Bon catchment in Vietnam be predicted using Long Short-Term Memory (LSTM) networks. Both the monthly suspended sediment concentration at the Thanh My station and the monthly runoff data are inputs. The findings compare the actual data to the predicted concentrations of suspended sediment. The training and testing sets use monthly data from 1978 to 2005 and from 2006 to 2019, respectively. To determine the best LSTM model for the catchment, the research analyzes different scenarios with various hyperparameters. The contrast demonstrates that the LSTM model can forecast suspended sediment concentration time series at the catchment.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.