Deep Learning Approach to Improve Spatial Resolution of GOES-17 Wildfire Boundaries using VIIRS Satellite Data
Loading...
Authors
Badhan, Mukul
Issue Date
2023
Type
Thesis
Language
Keywords
Alternative Title
Abstract
The rising severity and frequency of wildfires in recent years in the U.S. have raised numerous concerns regarding the improvement in wildfire emergency response management and decision-making systems, which require operational high temporal and spatial resolution monitoring capabilities. Satellites are one of the tools that can be used for wildfire monitoring. However, none of the currently available satellites provide both high temporal and spatial resolution. For example, GOES-17 geostationary satellite has a high temporal (5 min) but a low spatial resolution (2 km), and VIIRS polar orbiter satellite has a low temporal (~12 h) but high spatial resolution (375 m). This study aims to leverage currently available satellite data sources, such as GOES and VIIRS, along with Deep Learning (DL) advances to achieve an operational high-resolution wildfire monitoring tool.This study considers the problem of increasing the spatial resolution of low resolution satellite data using high resolution satellite. An Autoencoder DL model is proposed to learn how to map GOES-17 geostationary low spatial resolution satellite images to VIIRS polar orbiter high spatial resolution satellite images. In this context, several loss functions and architectures are implemented and tested to predict both the area of fire and corresponding fire radiance values. These models are trained and tested on wildfire sites from 2019 to 2021 in the western U.S. The results indicate that DL models can improve the spatial resolution of GOES-17 images, leading to images that mimic the spatial resolution of VIIRS images. Combined with GOES-17 higher temporal resolution, the DL model can provide high-resolution near-real-time wildfire monitoring capability as well as semi-continuous wildfire progression maps.