The Power of Explainability in Forecast-Informed Deep Learning Models for Flood Mitigation

TL;DR

This paper introduces FIDLAR, a deep learning model for flood mitigation that leverages explainability tools to optimize pre-release water schedules, outperforming current methods in speed and effectiveness for real-time flood management.

Contribution

The paper presents a novel Forecast Informed Deep Learning Architecture that integrates explainability to enhance flood management decisions and demonstrates superior performance over existing approaches.

Findings

FIDLAR achieves several orders of magnitude speedup over state-of-the-art methods.

FIDLAR provides provably better pre-release schedules for flood mitigation.

Explainability tools help understand environmental factors influencing flood management decisions.

Abstract

Floods can cause horrific harm to life and property. However, they can be mitigated or even avoided by the effective use of hydraulic structures such as dams, gates, and pumps. By pre-releasing water via these structures in advance of extreme weather events, water levels are sufficiently lowered to prevent floods. In this work, we propose FIDLAR, a Forecast Informed Deep Learning Architecture, achieving flood management in watersheds with hydraulic structures in an optimal manner by balancing out flood mitigation and unnecessary wastage of water via pre-releases. We perform experiments with FIDLAR using data from the South Florida Water Management District, which manages a coastal area that is highly prone to frequent storms and floods. Results show that FIDLAR performs better than the current state-of-the-art with several orders of magnitude speedup and with provably better pre-release schedules. The dramatic speedups make it possible for FIDLAR to be used for real-time flood management. The main contribution of this paper is the effective use of tools for model explainability, allowing us to understand the contribution of the various environmental factors towards its decisions.