About the Challenge:

Aligned with the United Nations Sustainable Development Goals and the EY Ripples program, the EY Open Science AI & Data Challenge is an annual competition that gives university students, early-career professionals and EY people the opportunity to develop data models using artificial intelligence (AI) and computing technology to create solutions that address critical climate issues, building a more sustainable future for society and the planet.

The 2025 AI & data challenge is focused on a phenomenon known as the urban heat island effect, a situation that occurs due to the high density of buildings and lack of green space and water bodies in urban areas. Temperature variations between rural and urban environments can exceed 10-degrees Celsius in some cases and cause significant health-, social- and energy-related issues. Those particularly vulnerable to heat-related problems include young children, older adults, outdoor workers, and low-income populations.

All output from the challenge can help bring cooling relief to vulnerable communities, but entrants with top scores will take home cash prizes and receive an invitation to an exciting awards celebration.

Problem Statement:

The goal of the challenge is to develop a machine learning model to predict heat island hotspots in an urban location. Additionally, the model should be designed to discern and highlight the key factors that contribute significantly to the development of these hotspots within city environments.

Participants will be given near-surface air temperature data in an index format, which was collected on 24 July 2021 using a ground traverse in the Bronx and Manhattan region of New York City. This dataset constitutes traverse points (latitude and longitude) and their corresponding UHI (Urban Heat Island) index values. Participants will use this dataset to build a regression model to predict UHI Index values for a given set of locations.

It is important to understand that the UHI Index at any given location is indicative of the relative temperature difference at that specific point when compared to the city's average temperature. This index serves as a crucial metric for assessing the intensity of heat within different urban zones.

The challenge begins on January 20, 2025 and will end on March 20, 2025 at 2 PM UTC. You can enter the challenge as an individual or as a team (with maximum three people in a team). 

Check the FAQs tab for more details and good luck on the challenge!