Multisource Environmental Data Analysis
Project Description
In an era marked by rapid climate change and complex ecological shifts, effective environmental monitoring depends on integrating diverse data streams from satellite remote sensing, ground-based monitoring stations, and bottom-up emissions calculations. Analyzing these multi-source datasets is essential to uncover spatial patterns, forecast climate trends, and shape evidence-based policy.
Supervisor
FUNG, Chi Hung
Quota
3
Course type
UROP1000
UROP1100
UROP2100
UROP3100
Applicant's Roles
This research project demonstrates how modern mathematical tools and Python programming can process, fuse, and analyze heterogeneous environmental data. Applying core techniques from linear algebra and applied statistics, students will build computational workflows to clean noisy datasets, fuse spatiotemporal data, and model complex environmental dynamics.
Applicant's Learning Objectives
Using Python libraries such as NumPy, Pandas, and Matplotlib, this project bridges theoretical mathematics and practical data science, equipping second-year mathematics students to tackle real-world environmental challenges.
Keywords: Spatiotemporal Data Fusion, Environmental Data Analytics, Applied Statistics
Complexity of the project
Moderate

Apply  Return home