Graduate Exam Abstract

Abstract: This thesis aims to address the challenge of accurate wildfire detection using satellite imagrey. Despite the availability of various satellite-based fire products, real-time detection of fire perimeters remain difficult due to limitations in the spatio-temporal resolution of current satellite imagery. For example, the GOES-R series offers high temporal resolution for frequent observations but suffers from low spatial resolution. In contrast, low Earth orbit (LEO) satellites like VIIRS provide high spatial resolution but with limited temporal coverage.
To overcome these limitations, this research proposes a deep learning framework for wildfire detection that leverages GOES observations, which are downscaled to a spatial resolution of 375 meters using a Generative Adversarial Network (GAN). High-resolution VIIRS images are used as ground truth labels during the training phase. Experimental results demonstrate that the proposed framework successfully enhances the spatial resolution of GOES data while preserving its high temporal frequency, allowing more precise and timely wildfire detection.

Adviser: Dr. Haonan Chen
Co-Adviser: N/A
Non-ECE Member: Dr. Steve Simske
Member 3: Dr. Chandrasekar Venkatachalem
Addional Members: N/A

Publications:
N/A

Program of Study:
ECE 578
ECE 556
ECE 544
SYSE 512
SYSE 571
SYSE 541
ENGR 533
ECE 699