A Parsimonious Setup for Streamflow Forecasting using CNN-LSTM

arXiv:2404.07924v1 Announce Type: new
Abstract: Significant strides have been made in advancing streamflow predictions, notably with the introduction of cutting-edge machine-learning models. Predominantly, Long Short-Term Memories (LSTMs) and Convolution Neural Networks (CNNs) have been widely employed in this domain. While LSTMs are applicable in both rainfall-runoff and time series settings, CNN-LSTMs have primarily been utilized in rainfall-runoff scenarios. In this study, we extend the application of CNN-LSTMs to time series settings, leveraging lagged streamflow data in conjunction with precipitation and …

abstract arxiv cnn cnns convolution cs.lg domain edge forecasting introduction lstm machine memories networks neural networks predictions rainfall series setup time series type