Understanding Drought Awareness from Web Data

This is a Preprint and has not been peer reviewed. This is version 2 of this Preprint.

Add a Comment

You must log in to post a comment.


Comments

There are no comments or no comments have been made public for this article.

Downloads

Download Preprint

Authors

Mashrekur Rahman, Samuel Sandoval Solis, Thomas Harter, Mahmoud Saeedimoghaddam, Niv Efron, Grey Nearing 

Abstract

We used computer vision (U-Net) model to leverage Standardized Precipitation Evapotranspiration Index (SPEI), Google Trends Search Interest (SI), and Twitter data to understand patterns with which people in Continental United States (CONUS) indicate awareness of and interest in droughts. We found significant statistical relationships between the occurrence of meteorological droughts (MD), as measured by SPEI, and SI on drought topics over CONUS. SI tends to lag MD by a period of 2-3 months, however relationships between MD and corresponding SI varies significantly over the CONUS in both space and time. People in states with increasingly dry conditions have become increasingly interested in drought topics. However, with worsening drought conditions in California, public SI on drought topics in the state has not increased significantly between 2016 and 2020, despite the overall SI being high. We additionally applied sentiment analysis on 5 million tweets related to droughts and found that public emotions towards drought have become more polarized.

DOI

https://doi.org/10.31223/X5T37J

Subjects

Computer Sciences, Earth Sciences, Mathematics, Oceanography and Atmospheric Sciences and Meteorology, Statistics and Probability

Keywords

droughts, computer vision, Google Trends, Twitter, SPEI, machine learning

Dates

Published: 2023-08-17 14:06

Last Updated: 2023-08-18 18:59

Older Versions
License

CC BY Attribution 4.0 International

Additional Metadata

Data Availability (Reason not available):
The code to reproduce all results and figures are available at www.doi.org/10.5281/zenodo.8212808. Due to data and privacy restrictions, SPEI, Google, and Twitter datasets are not made publicly available.