Heat Index Estimation
Project Description
The aim of the Heat Index project is to develop an advanced algorithm capable of estimating a high-resolution heat index across Hong Kong. This effort is motivated by the unique thermal challenges of urban environments, where localized variations in heat perception can be substantial. Factors such as building shadows, terrain features, and urban morphology play a significant role in influencing how heat is experienced in different areas. For instance, shaded locations may feel significantly cooler than areas directly exposed to sunlight, while terrain obstructions and building density can alter wind flow, further impacting the perceived temperature.

The concept of perceived heat, or apparent temperature, goes beyond the actual measured temperature. It incorporates the combined effects of meteorological factors such as temperature, humidity, and wind speed, as well as environmental and physical conditions like altitude, building shadows, and exposure to direct sunlight. Building materials, urban density, and reflective surfaces in cities also amplify or mitigate heat conditions, creating micro-climates that standard temperature measurements cannot fully capture.
Supervisor
FUNG, Jimmy Chi Hung
Co-Supervisor
LAU, Alexis Kai Hon
Quota
3
Course type
UROP1000
UROP1100
UROP2100
UROP3100
Applicant's Roles
To address these complexities, the project will integrate meteorological data, including temperature, humidity, and wind speed, with urban morphology parameters such as building layouts, terrain elevation, and sun exposure angles. By combining these datasets, the algorithm will be able to provide a detailed and accurate estimation of the heat index at a highly localized scale. This high-resolution approach aims to reflect the diverse thermal conditions across Hong Kong's urban landscape, offering valuable insights for urban planning, public health, and climate adaptation strategies.
Applicant's Learning Objectives
Through this project, students will learn how to apply AI techniques to solve complex, real-world problems by integrating diverse datasets. They will gain hands-on experience in data preprocessing, feature engineering, and developing advanced machine learning algorithms to analyze meteorological and urban morphology data. Students will explore AI concepts such as spatial analysis, predictive modeling, and the integration of geospatial data with environmental factors. They will also learn about the importance of interdisciplinary approaches, combining AI with urban planning and climate science to address challenges like urban heat islands. Overall, the project will enhance their skills in data-driven decision-making, algorithm optimization, and the development of AI solutions for environmental sustainability and public health.
Complexity of the project
Moderate