Wildfire Detection and Aerosol Identification Using Satellite Imagery

Kothapalli, Srija Venkata Sai Ravali (2023) Wildfire Detection and Aerosol Identification Using Satellite Imagery. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (1MB) | Preview

Abstract

Wildfires are one of the most frequent events occurring all over the world and they became the major concerning factor in the climate changes for the past decade. Early Detection of these wildfires and smoke plumes through satellite imagery is crucial since they are not easily extinguishable which may lead to catastrophic consequences for both wildlife and forest ecosystems. In this study, we propose a Convolutional neural network (CNN) model from scratch which helps in detecting the smoke plumes and identifying aerosols, the other classes of the smoke plumes emanating in the atmosphere such as haze and dust as they are very similar to smoke. Also, EfficientNet, MobileNetV3 and Inception V3 models are employed, which are popular deep learning approaches and transfer learning models applied on the same dataset. compare the performance and output parameters of the state-of-the-art models that are most recent models in rise for image classification with faster training times and enables the better accuracies. Hyperparameter tuning has been performed for more accurate results and the critically evaluated metrics in this research are accuracy, precision, recall and f1- score. This comprehensive analysis aims to identify the best transfer learning model and the model that closely aligns with the performance of the CNN built. This study provides the valuable insights into the potential of Transfer learning models and CNN proposed in Early wildfire detection by identifying the smoke plumes and helps in reducing the false fire alarms.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Yaqoob, Abid UNSPECIFIED
Subjects:	G Geography. Anthropology. Recreation > GE Environmental Sciences Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence > Computer vision Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence > Computer vision Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	15 May 2025 15:34
Last Modified:	15 May 2025 15:34
URI:	https://norma.ncirl.ie/id/eprint/7553

Actions (login required)

View Item