Date Approved
9-29-2021
Embargo Period
9-30-2021
Document Type
Dissertation
Degree Name
Ph.D. Doctor of Philosophy
Department
Electrical and Computer Engineering
College
Henry M. Rowan College of Engineering
Advisor
Nazari Rouzbeh, Ph.D.
Committee Member 1
Nidhal C. Bouaynaya, Ph.D.
Committee Member 2
Francis Haas, Ph.D.
Committee Member 3
Jess Everett, Ph.D.
Keywords
Anomaly detection, Deep learning, Landfill fire
Subject(s)
Remote sensing
Disciplines
Civil and Environmental Engineering | Electrical and Computer Engineering
Abstract
Landfill fire is a potential hazard of waste mismanagement, and could occur both on and below the surface of active and closed sites. Timely identification of temperature anomalies is critical in monitoring and detecting landfill fires, to issue warnings that can help extinguish fires at early stages. The overarching objective of this research is to demonstrate the applicability and advantages of remote sensing data, coupled with machine learning techniques, to identify landfill thermal states that can lead to fire, in the absence of onsite observations. This dissertation proposed unsupervised learning techniques, notably variational auto-encoders (VAEs), to identify temperature anomalies from aerial landfill imagery. Twenty years of Landsat satellite observations at a number of landfills were examined for hotspots that may be associated with or leading to subsurface fires. The main contribution of this dissertation is to detect temperature anomalies in landfills using the state-of-the-art unsupervised deep learning technique of VAE based on both model reconstruction error and encoder module feature extraction. Additionally, a simple framework for assessing the health state of the landfill at any given time was established by using the clustering findings to generate a past behavior for each location in the landfill and eventually assigning it to one of four risk categories (No Risk, Low Risk, Moderate Risk, and High Risk). This framework can function as a monitoring system, inferring information such as past landfill temperature profiles, predicting possible heat elevation or smoldering events as new observations are added, and identifying the percentage of each of the four risk categories and how they increase or decrease over the lifetime of the landfill.
Recommended Citation
Alfergani, Husam A., "UNSUPERVISED LEARNING FOR ANOMALY DETECTION IN REMOTE SENSING IMAGERY" (2021). Theses and Dissertations. 2949.
https://rdw.rowan.edu/etd/2949
Included in
Civil and Environmental Engineering Commons, Electrical and Computer Engineering Commons