Benchmark dataset of ``Large-scale urban flood modeling and zero-shot high-resolution generalization with LarNO''

This dataset is the official benchmark for LarNO, a memory-efficient, discretization-invariant neural operator for real-time urban flood prediction. LarNO learns the spatiotemporal mapping from dynamic rainfall and static terrain inputs to water depth distributions, and supports zero-shot generalization to spatial resolutions unseen during training.The dataset comprises two urban flood benchmark cases:Futian case (region1_20m): A large-scale benchmark covering the Futian District of Shenzhen, China.UKEA case (ukea_8m_5min / ukea_2m_5min): A small urban catchment from a UK Environment Agency study site, used for transfer learning (fine-tuning from Futian pre-trained weights) and zero-shot super-resolution evaluation (train at 8 m, test at 2 m).