In this letter, we demonstrate the utility of estimating a probabilistic model of the underlying seasonal and interannual variations experienced by land cover time series in a given geographical region. Time series that deviate from these trajectories due to the human-induced change appear as outliers and can be detected using their Mahalanobis distance from the mean under the joint distribution of time samples. We apply this model to a collection of pixel time series acquired by the Moderate Resolution Imaging Spectroradiometer platform over Limpopo province, South Africa, for the task of identifying human settlement expansion. For estimation of the time of change, we present a hypothesis testing approach that tests for a decrease in correlation between samples before and after the change. This was found to be highly effective, yielding a mean absolute error of 52 days.

Item Type:	Refereed Article
Keywords:	change detection algorithms, covariance matrices, density estimation robust algorithm, remote sensing, time series analysis
Research Division:	Engineering
Research Group:	Electrical engineering
Research Field:	Electrical circuits and systems
Objective Division:	Environmental Policy, Climate Change and Natural Hazards
Objective Group:	Environmental policy, legislation and standards
Objective Field:	Environmental policy, legislation and standards not elsewhere classified
UTAS Author:	Olding, WC (Mr Willem Olding)
UTAS Author:	Olivier, JC (Professor JC Olivier)
UTAS Author:	Salmon, BP (Dr Brian Salmon)
ID Code:	129021
Year Published:	2019
Deposited By:	Engineering
Deposited On:	2018-11-02
Last Modified:	2020-01-14
Downloads:	0