Windstorm Economic Impacts on the Spanish Resilience: A Machine Learning Real-Data Approach

TL;DR

This paper uses machine learning classification models on public data to estimate economic losses from windstorms in Spain, aiming to improve urban resilience and disaster management strategies.

Contribution

It introduces a novel ML-based approach to assess windstorm impacts on Spanish urban areas using real-world data, aiding decision-making for resilience enhancement.

Findings

ML models effectively classify windstorm impacts.

Enhanced understanding of windstorm economic losses.

Supports informed disaster preparedness decisions.

Abstract

Climate change-associated disasters have become a significant concern, principally when affecting urban areas. Assessing these regions' resilience to strengthen their disaster management is crucial, especially in the areas vulnerable to windstorms, one of Spain's most critical disasters. Smart cities and machine learning offer promising solutions to manage disasters, but accurately estimating economic losses from windstorms can be difficult due to the unique characteristics of each region and limited data. This study proposes utilizing ML classification models to enhance disaster resilience by analyzing publicly available data on windstorms in the Spanish areas. This approach can help decision-makers make informed decisions regarding preparedness and mitigation actions, ultimately creating a more resilient urban environment that can better withstand windstorms in the future.