University of Tasmania
Browse

File(s) under permanent embargo

The quest for automated land cover change detection using satellite time series data

conference contribution
posted on 2023-05-23, 07:36 authored by Brian SalmonBrian Salmon, Jan OlivierJan Olivier, Kleynhans, W, Wessels, KJ, van den Bergh, F
This paper shows that a feedforward Multilayer Perceptron (MLP) operating over a temporal sliding window of multispectral time series MODerate-resolution Imaging Spectroradiometer (MODIS) satellite data is able to detect land cover change that was artificially introduced by concatenating time series belonging to different types of land cover. The method employs an iteratively retrained MLP that is a supervised method, and thus captures all local environmental patterns. Depending on the length of the temporal sliding window used in the short-term Fourier transform, an overall change detection accuracy of between 87.62% and 97.02% was achieved. It is shown that for this type of simulated land cover change, where land cover change was abrupt, a short-term FFT window of 18 months or less, using only the two NDVI spectral bands of MODIS data was sufficient to detect change reliably.

History

Publication title

Proceedings of the IEEE International Geoscience and Remote Sensing Symposium

Volume

4

Pagination

244-247

ISBN

978-1-4244-3395-7

Department/School

School of Engineering

Publisher

IEEE

Place of publication

USA

Event title

IEEE International Geoscience and Remote Sensing Symposium

Event Venue

Cape Town, South Africa

Date of Event (Start Date)

2009-07-12

Date of Event (End Date)

2009-07-17

Rights statement

Copyright 2009 IEEE

Repository Status

  • Restricted

Socio-economic Objectives

Expanding knowledge in engineering

Usage metrics

    University Of Tasmania

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC