FIDLAR: Forecast-Informed Deep Learning Architecture for Flood Mitigation

2024-02-20

arXiv.org

AI Summary

Coastal river networks face severe flood control challenges under compound events of storm surges and spring tides, where conventional rule-based methods suffer from low accuracy and model predictive control (MPC) incurs prohibitive computational overhead. Method: This paper proposes Flood Manager/Evaluator, a dual-module deep scheduling framework. The Manager employs a meteorology-driven deep neural network to generate real-time preemptive release strategies; the Evaluator incorporates differentiable physics-informed constraints to provide gradient feedback, enabling MPC-inspired joint training and seamless integration of forecast information. Contribution/Results: The framework overcomes the limitations of empirical rules and the real-time bottlenecks of MPC. Evaluated on real-world data from South Florida, it achieves scheduling speeds several orders of magnitude faster than traditional physics-based models, while significantly outperforming both rule-based approaches and baseline deep learning models in preemptive release accuracy.

Technology Category

• Planning, Routing, and Scheduling: Model-Based Reasoning
• Search and Optimization: Learning to Search
• Machine Learning: Time-Series/Data Streams

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

In coastal river systems, frequent floods, often occurring during major storms or king tides, pose a severe threat to lives and property. However, these floods can be mitigated or even prevented by strategically releasing water before extreme weather events with hydraulic structures such as dams, gates, pumps, and reservoirs. A standard approach used by local water management agencies is the"rule-based"method, which specifies predetermined pre-releases of water based on historical and time-tested human experience, but which tends to result in excess or inadequate water release. The model predictive control (MPC), a physics-based model for prediction, is an alternative approach, albeit involving computationally intensive calculations. In this paper, we propose a Forecast Informed Deep Learning Architecture, FIDLAR, to achieve rapid and optimal flood management with precise water pre-releases. FIDLAR seamlessly integrates two neural network modules: one called the Flood Manager, which is responsible for generating water pre-release schedules, and another called the Flood Evaluator, which assesses these generated schedules. The Evaluator module is pre-trained separately, and its gradient-based feedback is used to train the Manager model, ensuring optimal water pre-releases. We have conducted experiments using FIDLAR with data from a flood-prone coastal area in South Florida, particularly susceptible to frequent storms. Results show that FIDLAR is several orders of magnitude faster than currently used physics-based approaches while outperforming baseline methods with improved water pre-release schedules.

Problem

• Flood Control
• Storm Surge
• Model Predictive Control

Innovation

• FIDLAR
• Deep Learning
• Flood Disaster Management