Change detection of surface mining activity and reclamation based on a machine learning approach of multi-temporal Landsat TM imagery

Abstract

Being able to quantify land cover changes due to mining and reclamation at a watershed scale is of critical importance in managing and assessing their potential impacts to the Earth system. In this study, a remote sensing-based methodology is proposed for quantifying the impact of surface mining activity and reclamation from a watershed to local scale. The method is based on a Support Vector Machines (SVMs) classifier combined with multi-temporal change detection of Landsat TM imagery. The performance of the technique was evaluated at selected open mining sites located in the island of Milos in Greece. Assessment of the mining impact in the studied areas was based on the confusion matrix statistics, supported by co-orbital QuickBird-2 very high spatial resolution imagery. Overall classification accuracy of the thematic land cover maps produced was reported over 90%. Our analysis showed expansion of mining activity throughout the whole 23-year study period, while the transition of mining areas to soil and vegetation was evident in varying rates. Our results evidenced the ability of the method under investigation in deriving highly and accurate land cover change maps, able to identify the mining areas as well as those in which excavation was replaced by natural vegetation. All in all, the proposed technique showed considerable promise towards the support of a sustainable environmental development and prudent resource management.Peer reviewe

Co-Orbital Sentinel 1 and 2 for LULC Mapping with Emphasis on Wetlands in a Mediterranean Setting Based on Machine Learning

“…Findings reported herein also align with the other studies conducted independently using different multispectral satellite data underlining as well the promising capabilities of SVMs [23,24,[59][60][61][62][63][64][65]. Evidently, a proper parameterisation can highly affect the SVMs performance [66,67].…”

A global reference database from very high resolution commercial satellite data and methodology for application to Landsat derived 30 m continuous field tree cover data

“…High resolution satellite data provide the only practical source of reference data for this global 500-sample-block dataset . Such use of relatively finer resolution satellite data as the basis of or as a component of global and large area land cover accuracy assessment has been established (Bontemps et al, 2012;De Fries, Hansen, Townshend, & Sohlberg, 1998;Desclee, Simonetti, Mayaux, & Achard, 2013;Mayaux et al, 2006;Montesano et al, 2009;Morisette et al, 2003;Petropoulos, Partsinevelos, & Mitraka, 2013;Raši et al, 2011;Scepan & Estes, 2001;Small & Lu, 2006). Our purpose in this article is to document the identification, collection and preprocessing of reference source-data, the reference map production, and the methods used in applying these high resolution thematic data to assess 30 m continuous field data layers characterizing global tree cover.…”

Satellite based mine rehabilitation monitoring using WorldView-2 imagery

“…Monitoring mine site rehabilitation and progressive growth of planted vegetation, can be achieved through remote imagery of the mine site and the surrounding area (McPherson, 2006), The common remote sensing methodology for monitoring and evaluating the status of the vegetative areas surrounding mining areas involves use of different spectral derivatives including band ratios and vegetation indices, such as the normalised difference vegetation index (NDVI), Hyperspectral remote sensing imagery from the Compact Airborne Spectrographic Imager (casi) and Probe -1 have been used effectively for monitoring the revegetation of mine tailings (Lévesque and Staenz, 2008), However, use of hyperspectral data is restricted due to its sparse availability, limited coverage (Lefsky et al, 2001), higher cost and complex processing (Varshney and Arora, 2004), Multispectral Landsat images are also capable of providing useful information for the assessment of mine restoration progress (Bonifazi et al, 2003;Cutaia et al, 2004;Bonifazi and Serranti, 2007;Petropoulos et al Bao et al (2012) used images of SPOT satellites to investigate seasonal changes in the percentage of vegetation cover of rehabilitation areas for a gold mine in Queensland, Australia.…”