A Sentinel-2 based multispectral convolutional neural network for detecting artisanal small-scale mining in Ghana: Applying deep learning to shallow mining

Gallwey, Jane; Robiati, Carlo; Coggan, John; Vogt, D.; Eyre, Matthew

doi:10.1016/j.rse.2020.111970

Cited by 50 publications

(44 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The scarce vegetation with diverse geology could result error in LULC classification; hence, ground truth points were used for the post-classification refinement of the misclassified pixels. NDVI-based LULC classification is widely used for spatiotemporal differentiation of vegetation cover from other classes [34][35][36][37][47][48][49][50]. The calculated values of NDVI range from ( −)1 (no vegetation) to ( +)1 (vegetation) [51].…”

Section: Methodsmentioning

confidence: 99%

“…For the assessment of LULC due to small-scale mine, a high-resolution satellite imagery data is required. It is observed that a high degree of accuracy could be achieved for the assessment of LULC change caused by small scale and illegal mines through the application of deep convolutional neural network model using Sentinel-2 multispectral satellite imagery [36].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Characterizing Khetri copper mine environment using geospatial tools

2021

View full text Add to dashboard Cite

Mines result in land use and land cover (LULC) change due to degradation of natural resources and establishment of new infrastructure for ore extraction and beneficiation. The present study was carried out to, with objectives, (1) characterize LULC change (from 1975 to 2017) in Khetri copper mine region, (2) spatial distribution of pollution indices and (3) spectral response of elemental concentration of soil and groundwater using Landstat and ASTER satellite data. The study was designed to fulfil the objectives and for the same NDVI values were calculated for LULC classification and generated maps were analyzed for landscape pattern. Spatial distribution of pollution indices calculated using geochemical data of soil and groundwater was plotted to understand the impact of contamination on landscape pattern. The correlation of spectral response of Landstat bands with heavy metals concentration was plotted to assess their possible use in quantification of heavy metals. Results show constant increase in settlements, mines and open area while vegetation cover has decreased. Landscape and class level metrics (number of patch, patch density, aggregation index and landscape shape index) indicate increase in the fragmentation of landscape in recent years. Shannon’s Evenness Index indicates increase in uniformity in landscape and it is attributed to loss of vegetation and agriculture patches. Pollution indices, Pollution Load Index for soil is high near the overburden materials and Index of Environmental Risk (IER) and Contamination Index for ground water is high near abandoned mines. Spectral bands 5 and 6 (SWIR 1) show significant negative correlation, and 9 (Cirrus) shows significant positive correlation with metal concentration in soil and water suggesting the possible use of remote sensing in assessment of metal concentration at ground level. Thus, it can be concluded that mines significantly influence the landscape pattern and remote sensing could be used for the assessment and predication of heavy metal contamination at broader scale in a cost-effective way.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Characterizing Khetri copper mine environment using geospatial tools

2021

View full text Add to dashboard Cite

show abstract

“…As the top and base cloud height and cloud-top ruggedness are not available, it is essential to utilize an approach that does not require these important cloud characteristics. The approach considered in this work assumes that cloud-top and cloud-base height can vary in a predefined manner, an assumption that has been utilized successfully for cloud and shadow detection in MODIS data [12,28]. Various types of clouds develop in tropical areas and are expected at specific heights, with a maximum height of approximately 2 km assumed for the lower dense clouds (e.g.…”

Section: Location Of Shadow With Respect To Cloud Projectionmentioning

confidence: 99%

“…Despite the major environmental and social impacts of these activities, the fact remains that traditional land surveys are very challenging for such remote and harsh areas as they lack suitable spatial or temporal coverage. Earth observation techniques can be an improved method to detect, map, and monitor these extractive activities and assess their impacts [5,[10][11][12].…”

Section: Introductionmentioning

confidence: 99%

“…On the other hand, cloud detection for L2A products utilizes several steps of threshold filtering using indices that involve land cover to avoid detecting false cloud pixels in regions of possible false detection, such as areas of bare soil [36]. Unfortunately, the cloud detection approach of Sen2Cor has been reported to result in the unsatisfactory detection of dense clouds and their shadows [14,24,37], and has been shown to result in false positives in small-scale mining areas [12]. This paper aims to provide improved cloud and shadow detection in an approach that is simple, efficient, and based on freely available tools.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Cloud and Cloud-Shadow Detection for Applications in Mapping Small-Scale Mining in Colombia Using Sentinel-2 Imagery

Ibrahim

Jiang

Lema³

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

Small-scale placer mining in Colombia takes place in rural areas and involves excavations resulting in large footprints of bare soil and water ponds. Such excavated areas comprise a mosaic of challenging terrains for cloud and cloud-shadow detection of Sentinel-2 (S2A and S2B) data used to identify, map, and monitor these highly dynamic activities. This paper uses an efficient two-step machine-learning approach using freely available tools to detect clouds and shadows in the context of mapping small-scale mining areas, one which places an emphasis on the reduction of misclassification of mining sites as clouds or shadows. The first step is comprised of a supervised support-vector-machine classification identifying clouds, cloud shadows, and clear pixels. The second step is a geometry-based improvement of cloud-shadow detection where solar-cloud-shadow-sensor geometry is used to exclude commission errors in cloud shadows. The geometry-based approach makes use of sun angles and sensor view angles available in Sentinel-2 metadata to identify potential directions of cloud shadow for each cloud projection. The approach does not require supplementary data on cloud-top or bottom heights nor cloud-top ruggedness. It assumes that the location of dense clouds is mainly impacted by meteorological conditions and that cloud-top and cloud-base heights vary in a predefined manner. The methodology has been tested over an intensively excavated and well-studied pilot site and shows 50% more detection of clouds and shadows than Sen2Cor. Furthermore, it has reached a Specificity of 1 in the correct detection of mining sites and water ponds, proving itself to be a reliable approach for further related studies on the mapping of small-scale mining in the area. Although the methodology was tailored to the context of small-scale mining in the region of Antioquia, it is a scalable approach and can be adapted to other areas and conditions.

show abstract