SF$^2$Bench: Evaluating Data-Driven Models for Compound Flood Forecasting in South Florida

2025-06-04

AI Summary

Composite flood forecasting is highly challenging due to strong couplings among meteorological, hydrological, and oceanic processes, compounded by anthropogenic interventions. Existing datasets suffer from sparsity, incomplete feature coverage, and the absence of systematic evaluation benchmarks. To address these limitations, this work introduces SF²Bench—the first benchmark time-series dataset for composite flooding in South Florida—uniquely integrating four heterogeneous, multi-source temporal data modalities: tides, rainfall, groundwater levels, and gate-pump control operations. Building upon SF²Bench, we establish a comprehensive multi-paradigm model evaluation framework, systematically assessing the capability of diverse architectures—including MLP, CNN, RNN, GNN, Transformer, and LLM—to capture spatiotemporal dependencies. Empirical results identify gate-pump operations and tidal signals as the most critical predictive factors. Our framework substantially improves both forecasting accuracy and computational efficiency, enabling reproducible and scalable, data-driven flood modeling research.

Technology Category

• Machine Learning: Time-Series/Data Streams
• Natural Language Processing: Language Grounding & Multi-modal NLP
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Forecasting compound floods presents a significant challenge due to the intricate interplay of meteorological, hydrological, and oceanographic factors. Analyzing compound floods has become more critical as the global climate increases flood risks. Traditional physics-based methods, such as the Hydrologic Engineering Center's River Analysis System, are often time-inefficient. Machine learning has recently demonstrated promise in both modeling accuracy and computational efficiency. However, the scarcity of comprehensive datasets currently hinders systematic analysis. Existing water-related datasets are often limited by a sparse network of monitoring stations and incomplete coverage of relevant factors. To address this challenge, we introduce SF2Bench, a comprehensive time series collection on compound floods in South Florida, which integrates four key factors: tide, rainfall, groundwater, and human management activities (gate and pump controlling). This integration allows for a more detailed analysis of the individual contributions of these drivers to compound flooding and informs the development of improved flood forecasting approaches. To comprehensively evaluate the potential of various modeling paradigms, we assess the performance of six categories of methods, encompassing Multilayer Perceptrons, Convolutional Neural Networks, Recurrent Neural Networks, Graph Neural Networks, Transformers, and Large Language Models. We verified the impact of different key features on flood forecasting through experiments. Our analysis examines temporal and spatial aspects, providing insights into the influence of historical data and spatial dependencies. The varying performance across these approaches underscores the diverse capabilities of each in capturing complex temporal and spatial dependencies inherent in compound floods.

Problem

• Evaluating data-driven models for compound flood forecasting challenges
• Addressing scarcity of comprehensive datasets for flood analysis
• Assessing performance of diverse ML models in flood prediction

Innovation

• SF2Bench integrates tide, rainfall, groundwater, human activities
• Evaluates ML models like CNNs, RNNs, GNNs, Transformers
• Analyzes temporal and spatial flood dependencies comprehensively