Drought forecasting is crucial for effectively managing water resources. However, streamflow forecasting remains challenging in regions like the Rhine Delta in the Netherlands, where forecasting accuracy and lead time are still limited. To address these issues, we present a machine learning (ML) approach based on the Long Short-Term Memory (LSTM) algorithm. We examine various combinations of univariate and multivariate configurations to improve streamflow forecasts for the Rhine River, focusing on sub-seasonal to seasonal lead times. In various experiments, we explore stacked LSTM setups with layer sizes of 64 and 250 neurons, along with a single dense output layer. In our experimentation, we utilize a variety of input datasets, including streamflow data collected from multiple stations (Lobith, Kolen, Maxau, Kaulb, Worm, and Bassel), as well as meteorological data such as river basin precipitation and average temperature. We employ the Nash-Sutcliffe Efficiency (NSE) and Mean Absolute Percentage Error (MAPE) metrics to quantify the model's performance against actual streamflow data at Lobith. In the univariate experiments, we analyze streamflow at Lobith on daily, weekly average, and weekly minimum scales. As the lead time increases, model prediction performance decreases for both daily and weekly time scales, with a notable decline after seven days. To enhance the model's performance, we investigated eight different combinations of streamflow, precipitation, and temperature inputs, increasing the complexity of the model. In the multivariate experiments, we also tested improving predictions for low flow conditions by multiplying streamflow input data by 0.75. With an increase in input variables, the model performance improves, which is particularly evident in "Exp#6" which forecasts up to lead times of 20 days, and "Exp#8" which forecasts up to 4 weeks in advance. The model was run using streamflow data from all stations, as well as basin-wise spatial precipitation and temperature data on daily and weekly time ...