fairfolio
Saved Projects

Predicting Climate-driven Human Migration from Honduras: a Geospatial Machine Learning Model Using Rainfall Deviation and Normalized Difference Vegetation Index (NDVI)

CSEF · 2023 Earth & Environmental Sciences Honorable_mention Award

Fong Paul · 12

Overview

Recently, the impacts of climate change have been increasingly visible and severe. One of the most significant consequences is fluctuations in rainfall. On the other hand, the US has recently seen an increase in migrants arriving at the southern border seeking entry and often asylum. The surge in numbers, overcrowding and poor conditions in the service facilities, and overall lack of resources needed to handle the situation humanely have made this a crisis. Therefore, there is a need for comprehensive and sustainable solutions that address the root causes of migration. This research aimed to provide additional tools for understanding how migration patterns are driven by climate change. Climate change causes fluctuations in rainfall, degrading vegetation's health. As a result, poor crop fields destabilize job and food security and could cause migration (climate-induced migration). Using the country of Honduras as an example, I developed a model to identify the statistical relationship between rainfall and human migration. I used the NDVI (Normalized Differential Vegetation Index) to indicate vegetation health. Based on satellite images from NASA, the NDVI is calculated and published by the FAO of the United Nations. To track human migration, I used the number of Honduran family units apprehended at the southern border as a proxy for migration patterns. I developed and validated statistical models to describe the relationship between rainfall, NDVI, and apprehension numbers. This study showed that the climate crisis affects Honduran migration to the United States. Using statistical models, I demonstrated that the fluctuation in the rainfall pattern damages the health of vegetation. My models predicted that a 2% reduction in rainfall correlates with a predicted NDVI reduction of 0.01 and, in turn, a 9.6% increase in the number of Honduran family units apprehended. My tools can be used to facilitate objective policy discussions on climate change, migration, and resource allocation.

Source coverage

This record comes from a published award list, not a complete project archive. Its abstract comes from CSEF's public project showcase as archived by the Internet Archive before judging (https://web.archive.org/web/20230401224130/https://ca-csef.zfairs.com/showcase/ShowcaseInfo?f=838e60b7-ea75-46e8-865c-fde4864244b3); the version presented may differ.

Awards (2)

  • Category Award: HM
  • Sponsored Award: That’s Geography Award

Competition history

  • CSEF 2023 Earth & Environmental Sciences · Entry S0918

Resources

Related projects

Closest projects by meaning, across every fair and year in the corpus.

Browse more like this

Source: California Science & Engineering Fair public projects

Save projects to your library

Sign in with Google to keep track of projects you find interesting, organized into folders. An account also raises your daily allowance for “Has this been done?”, and lets you create a key for the MCP server with a much higher limit than anonymous use. Browsing stays public.

Continue with Google