The application of synthetic aperture radar for the detection and mapping of small-scale mining in Ghana

Date
2020-12
Journal Title
Journal ISSN
Volume Title
Publisher
Stellenbosch : Stellenbosch University
Abstract
ENGLISH ABSTRACT: Artisanal and small-scale mining (SSM) is a cause of major environmental concern in developing countries. In Ghana, SSM is a mixture of legal and illegal operations where illegal mining is referred to as “galamsey”. Earth observation techniques can assist local governments in regulating SSM activities by providing specific spatial information on the whereabouts of SSM mines. The tropical climate in Ghana, however, hinders the regular flow of useful optical imagery due to a high percentage of cloud cover for most parts of the year. Synthetic aperture radar (SAR) can overcome this limitation. The study area includes a portion of the Ofin River near the mining town of Obuasi, Ghana. The area is tropical in climate, rural and dominated by forests. This study aims to assess the accuracy and reliability of applying SAR for the detection and mapping of small-scale mining in Ghana with classification and change detection analysis. A literature review on remote sensing and image processing literature was conducted. The satellite imagery collected for the study included single-date C-band Sentinel-1, a time series of Sentinel-1 and a single-date X-band KompSAT-5 image for the SAR analysis with Sentinel-2 and Landsat-8 imagery as ground truth datasets. Classification analysis was conducted in two experiments which included the analysis of two classification schemes, i.e. multi-class-and a binary-water classification scheme. The first experiment assessed the accuracy of random forest classification applied to single-date Sentinel-1, KompSAT-5 and multi-temporally filtered Sentinel-1 databases. The second experiment was a comparison of five machine learning supervised classification methods applied to the multi-temporally filtered Sentinel-1 database. The potential of change detection on Sentinel-1 time series data was analysed in the third experiment for the detection of SSM. Image differencing was applied and two threshold methods were tested for producing the most accurate change maps.The classification with the object-based image analysis approach was successful in classifying water bodies associated with SSM. The multi-temporally filtered Sentinel-1 dataset was the most reliable with kappa coefficients at 0.65 and 0.82 for the multi-class classification scheme and binary-water classification scheme respectively. The single-date Sentinel-1 dataset has the highest overall accuracy at 90.93% for the binary water classification scheme. The KompSAT-5 dataset only achieved the lowest accuracy at an overall accuracy of 80.61% and a kappa coefficient of 0.61 for the binary-water classification scheme. The results of the change detection analysis indicated that the Sentinel-1 imagery was able to detect and map SSM. The change detection analysis also showed the potential of discerning active from abandoned mines, but this has to be further investigated.
AFRIKAANSE OPSOMMING: Ambags-en kleinskaalse mynbou (SSM) veroorsaak groot kommer oor die negatiewe impak daarvan in ontwikkelende lande. In Ghana, kom SSM voor as ‘n mengsel van wettige en onwettige bedrywighede. Die onwettige mynbou word in Ghana“galamsey”genoem. Aardwaarnmingstegnieke kan spesifieke ruimtelike inligting van die plekke waar SSM bedrywighede plaasvind bied om plaaslike regerings te help om die SSM aktiwiteite te reguleer. Die hoë persentasie van wolkbedekking wat in Ghana voorkom vir groot dele van die jaar, as gevolg van Ghana se tropiese klimaat, verhoed dat gereelde bruikbare optiese beelde beskikbaar is. Die gebruik van sintetiese apertuur radar(SAR)kan hierdie limitasie oorkom. Die studie gebied sluit ‘n deel van die Ofin Rivier in wat naby aan die myndorp Obuasie, Ghana geleëis. Die gebied het ‘n tropiese klimaat en is in ‘n landelike gebied wat oorheers word met woude.Die doel van die studie is om die akkuraatheid en betroubaarheid van SAR toemet betrekking tot klassifikasie en verandering-opsporing te assesseer vir die opsporing en kartering van SSM. ‘n Literatuuroorsig op afstandswaarneming en beeldverwerking was gedoen. Die satellietbeelde wat ingesamel is sluit ‘n enkel-datum C-band Sentinel-1, ‘n tydreeks van Sentinel-1 en ‘n enkel-datum X-band KompSAT-5 beeld in vir die SAR analise saam met Sentinel-2 en Landsat-8 beelde wat as grondwaarheid gebruik is. Klassifikasie analise was uitgevoer in twee eksperimente wat die analise van twee klassifikasie skemas ingesluit het, naamlik multi-klas-en binêre-water klassifikasie skemas. Die eerste eksperiment het die akkuraatheid van ewikansige woud toegepas op die enkel-datum Sentinel-1, KomSAT-5 en multi-temporaal gefilterde Sentinel-1 databasisse geassesseer. Die tweede eksperiment was ‘n vergelyking tussen vyf masjienleer toesig-klassifikasie metodes wat toegepas was op die multi-temporaal gefiterde Sentinel-1 databasis.Die potensiaal van verandering-opsporing op die Sentinel-1 tydreeks data om SSM op te spoor was geanaliseer in die derde eksperiment. Beeldaftrekking was toegepas en twee drumpel metodes was getoets vir die akkuraatste verandering kaarte. Die resultate toon aan dat die klassifikasie, met die objekgebaseerde beeldanalise benadering, suksesvol was om die waterliggame wat met SSM geassosieer word te klassifiseer. Die multi-temporaal gefilterde Sentinel-1 datastel was die mees betroubare met kappa koëffisiënte van 0.65 en 0.82 vir die multi-klas klassifikasie skema en die binêre-water klassifikasie skema onderskeidelik. Die enkel-datum Sentinel-1 datastel het die hoogste algehele akkuraatheid van 90.93% vir die binêre-water klassifikasie skema behaal. Die resultate van die verandering-opsporing analise toon dat die Sentinel-1 beelde die SSM kon opspoor en karteer. Die verandering-opsporing het ook gewys dat daar potensiaal is om die aktiewe en die verlate myne van mekaar te kan onderskei, maar dié benodig verdere ondersoek. Die samevatting is dat SAR onwettige mynbou aktiwiteite in ‘n tropiese gebied soos Ghana kan opspoor en dat die gebruik van hoë-resolusie kommersiële beelde nie nodig is nie. Die verandering-opsporing analise het SSM opgespoor waar die klassifikasie metodes net die water wat geassosieer word met SSM kon opspoor. Verdere navorsing sluit die ondersoek van die gebruik van drempeltegnieke vir die binêre-water klassifikasie in, en om die verandering-opsporing te verbeter deur segmentering en masjienleer toe te pas om die verandering-kaarte te maak.
Description
Thesis (MA)--Stellenbosch University, 2020.
Keywords
Mines and mineral resources -- Developing countries -- Ghana, Illegal Artisanal Mining (IAM) -- Developing countries -- Ghana, Sustainable development -- Developing countries -- Ghana, Machine learning, Remote sensing, SAR (Synthetic aperture radar), Mineral industries -- Developing countries -- Ghana, Galamsey, Artisanal and small-scale mining (SSM), UCTD
Citation