The spatial-temporal patterns of land cover changes due to mining activities in the Darling Range, Western Australia: A Visual Analytics Approach

Yathunanthan Vasuki, Le Yu, Eun Jung Holden, Peter Kovesi, Daniel Wedge, Andrew H. Grigg

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

The Darling Range in Western Australia is a major bauxite producing region. Clearing, excavation and rehabilitation activities related to bauxite mining have influenced land cover within this region since mining commenced in the 1960s. This paper presents a study that used machine learning and time series visualisation to analyse the land cover changes of the Darling Range using time-lapse multispectral images, with the aim of understanding the impact of the mining activities and land rehabilitation patterns of the region. Land cover changes were analysed using 14 Landsat Thematic Mapper (TM)images between 1988 and 2014. The spatial distribution of land cover was classified automatically using machine learning algorithms, and their temporal changes were visualized for analysis. Supervised classification was carried out based on the six spectral features of the images using three machine learning algorithms, namely support vector machine (SVM), random forest (RF)and Naïve Bayes (NB). The results showed that the RF algorithm achieved overall accuracy, (ratio of correctly classified samples divided by the total number of samples), greater than 95% for all years. The temporal changes of land cover distribution over the study period were visualized using a change map. These changes were compared with land clearing and rehabilitation records of a mining company operating in that region. A close correlation was observed between the automated analysis outputs and the company's records. This work demonstrates the potential use of machine analysis in improving the accuracy of spatial data related to land clearing; and in monitoring vegetation recovery of closed and rehabilitated mines.

Original languageEnglish
Pages (from-to)23-32
Number of pages10
JournalOre Geology Reviews
Volume108
Issue numberSI
DOIs
Publication statusPublished - 1 May 2019

Fingerprint

Patient rehabilitation
Learning systems
land cover
Learning algorithms
Bauxite mines
bauxite
Aluminum Oxide
Excavation
Spatial distribution
Support vector machines
Time series
Industry
Visualization
multispectral image
Recovery
image classification
spatial data
Landsat thematic mapper
Monitoring
visualization

Cite this

@article{ee6437ffbff0434b8ce3c7f780b1a182,
title = "The spatial-temporal patterns of land cover changes due to mining activities in the Darling Range, Western Australia: A Visual Analytics Approach",
abstract = "The Darling Range in Western Australia is a major bauxite producing region. Clearing, excavation and rehabilitation activities related to bauxite mining have influenced land cover within this region since mining commenced in the 1960s. This paper presents a study that used machine learning and time series visualisation to analyse the land cover changes of the Darling Range using time-lapse multispectral images, with the aim of understanding the impact of the mining activities and land rehabilitation patterns of the region. Land cover changes were analysed using 14 Landsat Thematic Mapper (TM)images between 1988 and 2014. The spatial distribution of land cover was classified automatically using machine learning algorithms, and their temporal changes were visualized for analysis. Supervised classification was carried out based on the six spectral features of the images using three machine learning algorithms, namely support vector machine (SVM), random forest (RF)and Na{\"i}ve Bayes (NB). The results showed that the RF algorithm achieved overall accuracy, (ratio of correctly classified samples divided by the total number of samples), greater than 95{\%} for all years. The temporal changes of land cover distribution over the study period were visualized using a change map. These changes were compared with land clearing and rehabilitation records of a mining company operating in that region. A close correlation was observed between the automated analysis outputs and the company's records. This work demonstrates the potential use of machine analysis in improving the accuracy of spatial data related to land clearing; and in monitoring vegetation recovery of closed and rehabilitated mines.",
keywords = "Change detection, Land cover mapping, Machine learning, Time series",
author = "Yathunanthan Vasuki and Le Yu and Holden, {Eun Jung} and Peter Kovesi and Daniel Wedge and Grigg, {Andrew H.}",
year = "2019",
month = "5",
day = "1",
doi = "10.1016/j.oregeorev.2018.07.001",
language = "English",
volume = "108",
pages = "23--32",
journal = "Ore Geology Reviews",
issn = "0169-1368",
publisher = "Pergamon",
number = "SI",

}

The spatial-temporal patterns of land cover changes due to mining activities in the Darling Range, Western Australia : A Visual Analytics Approach. / Vasuki, Yathunanthan; Yu, Le; Holden, Eun Jung; Kovesi, Peter; Wedge, Daniel; Grigg, Andrew H.

In: Ore Geology Reviews, Vol. 108, No. SI, 01.05.2019, p. 23-32.

Research output: Contribution to journalArticle

TY - JOUR

T1 - The spatial-temporal patterns of land cover changes due to mining activities in the Darling Range, Western Australia

T2 - A Visual Analytics Approach

AU - Vasuki, Yathunanthan

AU - Yu, Le

AU - Holden, Eun Jung

AU - Kovesi, Peter

AU - Wedge, Daniel

AU - Grigg, Andrew H.

PY - 2019/5/1

Y1 - 2019/5/1

N2 - The Darling Range in Western Australia is a major bauxite producing region. Clearing, excavation and rehabilitation activities related to bauxite mining have influenced land cover within this region since mining commenced in the 1960s. This paper presents a study that used machine learning and time series visualisation to analyse the land cover changes of the Darling Range using time-lapse multispectral images, with the aim of understanding the impact of the mining activities and land rehabilitation patterns of the region. Land cover changes were analysed using 14 Landsat Thematic Mapper (TM)images between 1988 and 2014. The spatial distribution of land cover was classified automatically using machine learning algorithms, and their temporal changes were visualized for analysis. Supervised classification was carried out based on the six spectral features of the images using three machine learning algorithms, namely support vector machine (SVM), random forest (RF)and Naïve Bayes (NB). The results showed that the RF algorithm achieved overall accuracy, (ratio of correctly classified samples divided by the total number of samples), greater than 95% for all years. The temporal changes of land cover distribution over the study period were visualized using a change map. These changes were compared with land clearing and rehabilitation records of a mining company operating in that region. A close correlation was observed between the automated analysis outputs and the company's records. This work demonstrates the potential use of machine analysis in improving the accuracy of spatial data related to land clearing; and in monitoring vegetation recovery of closed and rehabilitated mines.

AB - The Darling Range in Western Australia is a major bauxite producing region. Clearing, excavation and rehabilitation activities related to bauxite mining have influenced land cover within this region since mining commenced in the 1960s. This paper presents a study that used machine learning and time series visualisation to analyse the land cover changes of the Darling Range using time-lapse multispectral images, with the aim of understanding the impact of the mining activities and land rehabilitation patterns of the region. Land cover changes were analysed using 14 Landsat Thematic Mapper (TM)images between 1988 and 2014. The spatial distribution of land cover was classified automatically using machine learning algorithms, and their temporal changes were visualized for analysis. Supervised classification was carried out based on the six spectral features of the images using three machine learning algorithms, namely support vector machine (SVM), random forest (RF)and Naïve Bayes (NB). The results showed that the RF algorithm achieved overall accuracy, (ratio of correctly classified samples divided by the total number of samples), greater than 95% for all years. The temporal changes of land cover distribution over the study period were visualized using a change map. These changes were compared with land clearing and rehabilitation records of a mining company operating in that region. A close correlation was observed between the automated analysis outputs and the company's records. This work demonstrates the potential use of machine analysis in improving the accuracy of spatial data related to land clearing; and in monitoring vegetation recovery of closed and rehabilitated mines.

KW - Change detection

KW - Land cover mapping

KW - Machine learning

KW - Time series

UR - http://www.scopus.com/inward/record.url?scp=85049444941&partnerID=8YFLogxK

U2 - 10.1016/j.oregeorev.2018.07.001

DO - 10.1016/j.oregeorev.2018.07.001

M3 - Article

VL - 108

SP - 23

EP - 32

JO - Ore Geology Reviews

JF - Ore Geology Reviews

SN - 0169-1368

IS - SI

ER -