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

Abstract

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.

Drying conditions in Switzerland – indication from a 35-year Landsat time-series analysis of vegetation water content estimates to support SDGs

“…According to Li and Roy (2017) under midlatitude regions, we can have approximately an image available every 3 days. Moreover, optical satellite images are known to be strongly affected by cloud contamination (Ibrahim et al, 2021;Nazarova, Martin, & Giuliani, 2020). In the SDC, clouds were filtered out using the cloud cover information included in the Landsat Collection 1 Level-1 Quality Assessment (QA) Band (Dwyer et al, 2018;Ernst, Lymburner, & Sixsmith, 2018).…”

Assessing the Applications of Earth Observation Data for Monitoring Artisanal and Small-Scale Gold Mining (ASGM) in Developing Countries

“…Among these, OTB, SNAP, Multispec, and QGIS are free software. Furthermore, open-source packages in R [36] and Python are available [16]. As datasets can be large, especially in the case of time-series analysis, cloud computing has become a critical component of RS data storage especially in the case of wide area and long-term monitoring of ASGM activities.…”

“…The most common approach is pixel-based, although this sometimes comes with a new form of challenge regarding misclassification in mapping mining-related landcover [24,38]. Approaches utilizing pixel-based classification followed by post-classification improvements through the appropriate knowledge of the mining setting have been successful in overcoming these limitations and reducing omission and commission errors [16,39]. It is important to take note of periods within a given year where the differences between mining sites and bare soils are more evident and unambiguous.…”

“…The World Database of Protected Areas also used RS tools to map about 700 ha of protected areas that have been disturbed by ASGM activities in Latin America and Africa [13]. Other examples include the works of Bruno, et al [14], Isidro, et al [15], Ibrahim, et al [16], Lobo, et al [17], de Lucia Lobo, et al [18], Nyamekye, et al [19], and Telmer and Stapper [20]. These studies have used both optical spaceborne RS data of high and medium resolution to identify and follow the evolution of artisanal and small-scale mines across space and time.…”

Sentinel-2 Recognition of Uncovered and Plastic Covered Agricultural Soil

“…The first essential task prior to analysing the Sentinel-2 imagery was the detection of clouds and their shadows, and subsequently excluding affected pixels. The direct use of cloud and shadow masks and quality bands available for Sentinel-2 data through Sen2Cor [46] were challenging as various clouds and shadows could be falsely omitted [47]. Using GEE, a collection of level (L)1C top of atmosphere (TOA) reflectance data covering Flanders were filtered to exclude those with cloud coverage exceeding 50% and were spatially mosaicked per acquisition date.…”