The increasing frequency and severity of floods due to climate change underscores the need for precise flood forecasting systems. This study focuses on the region surrounding Wuppertal in Germany, known for its high precipitation levels, as a case study to evaluate the effectiveness of flood prediction through deep learning models. Our primary objectives are twofold: (1) to establish a robust dataset from the Wupper river basin, containing over 19 years of time series data from three sensor types such as water level, discharge, and precipitation at multiple locations, and (2) to assess the predictive performance of nine advanced machine learning algorithms, including Pyraformer, TimesNet, and SegRNN, in providing reliable flood warnings 6 to 48 h in advance, based on 48 h of input data. Our models, trained and validated using k-fold cross-validation, achieved high quantitative performance metrics, with an accuracy reaching up to 99.7% and F1-scores up to 91%. Additionally, we analyzed model performance relative to the number of sensors by systematically reducing the sensor count, which led to a noticeable decline in both accuracy and F1-score. These findings highlight critical trade-offs between sensor coverage and predictive reliability. By publishing this comprehensive dataset alongside performance benchmarks, we aim to drive further innovation in flood risk management and resilience strategies, addressing urgent needs in climate adaptation.