Shining a Light on Hurricane Damage Estimation via Nighttime Light Data: Pre-processing Matters

TL;DR

This study investigates how different pre-processing techniques for nighttime light data affect the accuracy of hurricane damage estimation, emphasizing the importance of data quality enhancement methods.

Contribution

It systematically compares various pre-processing methods for NTL data and demonstrates their impact on correlating light data with hurricane-induced economic damages.

Findings

Quality masking and imputation improve correlation with economic damage data.

Pre-processing choices significantly influence the predictive power of NTL data.

VNP46A2 dataset with specific techniques shows the strongest correlation.

Abstract

Amidst escalating climate change, hurricanes are inflicting severe socioeconomic impacts, marked by heightened economic losses and increased displacement. Previous research utilized nighttime light data to predict the impact of hurricanes on economic losses. However, prior work did not provide a thorough analysis of the impact of combining different techniques for pre-processing nighttime light (NTL) data. Addressing this gap, our research explores a variety of NTL pre-processing techniques, including value thresholding, built masking, and quality filtering and imputation, applied to two distinct datasets, VSC-NTL and VNP46A2, at the zip code level. Experiments evaluate the correlation of the denoised NTL data with economic damages of Category 4-5 hurricanes in Florida. They reveal that the quality masking and imputation technique applied to VNP46A2 show a substantial correlation with economic damage data.