A Novel Dynamic Bias-Correction Framework for Hurricane Risk Assessment under Climate Change

TL;DR

This paper introduces a machine learning-based dynamic bias correction framework for GCM outputs, improving hurricane risk assessment accuracy under climate change by adaptively correcting biases and capturing evolving climate dynamics.

Contribution

It presents a novel adaptive bias correction method that dynamically adjusts GCM biases using machine learning, enhancing the realism of future hurricane risk projections.

Findings

Significant differences in projected risks with and without bias correction

Increased threat to critical infrastructure in hurricane-prone regions

Improved accuracy in hurricane risk modeling under climate change

Abstract

Conventional hurricane track generation methods typically depend on biased outputs from Global Climate Models (GCMs), which undermines their accuracy in the context of climate change. We present a novel dynamic bias correction framework that adaptively corrects biases in GCM outputs. Our approach employs machine learning to predict evolving GCM biases, allowing dynamic corrections that account for changing climate conditions. By combining dimensionality reduction with data-driven surrogate modeling, we capture the system's underlying dynamics to produce realistic spatial distributions of environmental parameters under future scenarios. Using the empirical Weibull plotting approach, we calculate return periods for wind speed and rainfall across coastal cities. Our results reveal significant differences in projected risks with and without dynamic bias correction, emphasizing the increased threat to critical infrastructure in hurricane-prone regions. This work highlights the necessity of adaptive techniques for accurately assessing future climate impacts, offering a critical advancement in hurricane risk modeling and resilience planning.