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

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.

Download Full-text

Classification Ensembles for Beach Cast and Drifting Vegetation Mapping with Sentinel-2 and PlanetScope

Geosciences ◽

10.3390/geosciences12010015 ◽

2021 ◽

Vol 12 (1) ◽

pp. 15

Author(s):

Florian Uhl ◽

Trine Græsdal Rasmussen ◽

Natascha Oppelt

Keyword(s):

Aquatic Vegetation ◽

Temporal Dynamics ◽

Spatial Scales ◽

Gradient Boosting ◽

Support Vector ◽

Small Scale ◽

Stochastic Gradient Boosting ◽

Starting Point ◽

Sentinel 2 ◽

Beach Cast

Along the Baltic coastline of Germany, drifting vegetation and beach cast create overlays at the otherwise sandy or stony beaches. These overlays influence the morphodynamics and structures of the beaches. To better understand the influence of these patchy habitats on coastal environments, regular monitoring is necessary. Most studies, however, have been conducted on spatially larger and temporally more stable occurrences of aquatic vegetation such as floating fields of Sargassum. Nevertheless, drifting vegetation and beach cast pose a particular challenge, as they exhibit high temporal dynamics and sometimes small spatial extent. Regular surveys and mappings are the traditional methods to record their habitats, but they are time-consuming and cost-intensive. Spaceborne remote sensing can provide frequent recordings of the coastal zone at lower cost. Our study therefore aims at the monitoring of drifting vegetation and beach cast on spatial scales between 3 and 10 m. We developed an automated coastline masking algorithm and tested six supervised classification methods and various classification ensembles for their suitability to detect small-scale assemblages of drifting vegetation and beach cast in a study area at the coastline of the Western Baltic Sea using multispectral data of the sensors Sentinel-2 MSI and PlanetScope. The shoreline masking algorithm shows high accuracies in masking the land area while preserving the sand-covered shoreline. We could achieve best classification results using PlanetScope data with an ensemble of a random forest classifier, cart classifier, support vector machine classifier, naïve bayes classifier and stochastic gradient boosting classifier. This ensemble accomplished a combined f1-score of 0.95. The accuracy of the Sentinel-2 classifications was lower but still achieved a combined f1-score of 0.86 for the same ensemble. The results of this study can be considered as a starting point for the development of time series analysis of the vegetation dynamics along Baltic beaches.

Download Full-text

Classification of Sentinel-2 Images Utilizing Abundance Representation

Proceedings ◽

10.3390/ecrs-2-05141 ◽

2018 ◽

Vol 2 (7) ◽

pp. 328 ◽

Cited By ~ 6

Author(s):

Eleftheria Mylona ◽

Vassiliki Daskalopoulou ◽

Olga Sykioti ◽

Konstantinos Koutroumbas ◽

Athanasios Rontogiannis

Keyword(s):

Clustering Algorithm ◽

Nearest Neighbor ◽

Unsupervised Classification ◽

Bare Soil ◽

Spectral Unmixing ◽

Support Vector ◽

Endmember Extraction ◽

Bayes Algorithm ◽

Sentinel 2

This paper deals with (both supervised and unsupervised) classification of multispectral Sentinel-2 images, utilizing the abundance representation of the pixels of interest. The latter pixel representation uncovers the hidden structured regions that are not often available in the reference maps. Additionally, it encourages class distinctions and bolsters accuracy. The adopted methodology, which has been successfully applied to hyperpsectral data, involves two main stages: (I) the determination of the pixel’s abundance representation; and (II) the employment of a classification algorithm applied to the abundance representations. More specifically, stage (I) incorporates two key processes, namely (a) endmember extraction, utilizing spectrally homogeneous regions of interest (ROIs); and (b) spectral unmixing, which hinges upon the endmember selection. The adopted spectral unmixing process assumes the linear mixing model (LMM), where each pixel is expressed as a linear combination of the endmembers. The pixel’s abundance vector is estimated via a variational Bayes algorithm that is based on a suitably defined hierarchical Bayesian model. The resulting abundance vectors are then fed to stage (II), where two off-the-shelf supervised classification approaches (namely nearest neighbor (NN) classification and support vector machines (SVM)), as well as an unsupervised classification process (namely the online adaptive possibilistic c-means (OAPCM) clustering algorithm), are adopted. Experiments are performed on a Sentinel-2 image acquired for a specific region of the Northern Pindos National Park in north-western Greece containing water, vegetation and bare soil areas. The experimental results demonstrate that the ad-hoc classification approaches utilizing abundance representations of the pixels outperform those utilizing the spectral signatures of the pixels in terms of accuracy.

Download Full-text

Deforestation and forest regeneration following small-scale gold mining in the Amazon: the case of Suriname

Environmental Conservation ◽

10.1017/s0376892901000121 ◽

2001 ◽

Vol 28 (2) ◽

pp. 117-126 ◽

Cited By ~ 43

Author(s):

Garry D. Peterson ◽

Marieke Heemskerk

Keyword(s):

Gold Mining ◽

Forest Cover ◽

Qualitative Interviews ◽

Gold Rush ◽

Forest Recovery ◽

Small Scale ◽

Old Growth ◽

Mining Sites ◽

Mining Areas ◽

Old Growth Forest

Despite scientific concern about Amazon deforestation and the impacts of the Amazon gold rush, few researchers have assessed the long-term impacts of small-scale gold mining on forest cover. This study estimates deforestation from gold mining and analyses the regeneration of abandoned mining areas in the Suriname Amazon. Fieldwork in December 1998 included observations and ecological measurements, as well as qualitative interviews with local miners about mining history and technology. Vegetation cover of abandoned mining sites of different ages was compared with that in old-growth forest. By present estimates, gold miners clear 48–96 km2 of old-growth forest in Suriname annually. Based on different assumptions about changes in technology and the amount of mining that takes place on previously mined sites, cumulative deforestation is expected to reach 750–2280 km2 by 2010. Furthermore, the analysis of abandoned mining sites suggests that forest recovery following mining is slow and qualitatively inferior compared to regeneration following other land uses. Unlike areas in nearby old-growth forest, large parts of mined areas remain bare ground, grass, and standing water. The area deforested by mining may seem relatively small, but given the slow forest recovery and the concentration of mining in selected areas, small-scale gold mining is expected to reduce local forest cover and ecosystem services in regions where mining takes place.

Download Full-text

Sentinel-2 Multitemporal Bare Soil Composites for predicting soil properties using machine learning methods

10.5194/egusphere-egu2020-18564 ◽

2020 ◽

Author(s):

Daniel Zizala

Keyword(s):

Machine Learning ◽

Time Series ◽

Surface Roughness ◽

Soil Properties ◽

Bare Soil ◽

Soil Mapping ◽

Digital Soil Mapping ◽

Support Vector ◽

Composite Formation ◽

Sentinel 2

Previous studies have shown that remote sensing data can be very useful input into soil prediction models. This input usually represents reflectance from bare soils, which, however, make up only a small part of the total area in a given part of the year. For eliminating masking effect of vegetation time series of individual images (&#381;&#237;&#382;ala et al. 2019; Shabou et al. 2015; Dematt&#234; et al. 2016; Blasch et al. 2015a) or multitemporal composites of spectral data can be used. Exposed Soil Composite Mapping Processor (SCMaP) (Rogge et al. 2018), Geospatial Soil Sensing System (GEOS3) (Dematt&#234; et al. 2018), Bare Soil Composite Image (Gallo et al. 2018), and Barest Pixel Composite for Agricultural Areas (Diek et al. 2017), all developed from Landsat time series, multitemporal bare soil image developed from RapidEye time series (Blasch et al. 2015b), or bare soil mosaic (Loiseau et al. 2019) derived from Sentinel-2 data can serve as examples of such composites. However, only some of the composite products have been used yet to predict soil properties. Promising results were achieved; however, the potential of these spectral composites has not yet been tested in a relevant number of studies. Further research is needed for its evaluation.Aims of this study are to analyze and to compare the prediction ability of models using different types of multitemporal bare soil composites derived from Sentinel-2 images and their applicability for mapping soil properties in large areas. The study was conducted on a regional scale in the soil heterogeneous region of central Czechia with dissected relief and variable soil properties, where data from 100 soil profiles with soil analytics were available. Sentinel-2 images from 2016-2019 were used for composite formation in the python numpy environment. Different methods of cloud masking, bare soil identification and data aggregation (both already used in previous studies and newly derived) have been tested to compare which is the most suitable for prediction of soil properties. The principles of digital soil mapping and machine learning algorithms (random forest and support vector machine multivariate methods) were used for prediction.Results reveal that Sentinel-2 multitemporal bare soil composites can be successfully applied in the prediction of soil properties. The setting of basic parameters of composite creation is very complex and challenging and it requires to use exact algorithms for masking clouds and bare soil. Soil moisture and surface roughness also greatly affect spectral characteristics of bare soil and thus a very important aspect of compositing is finding appropriate statistics to derive final pixel values of reflectance (minimum, mean, median, ...). One possible way to minimize the effect of moisture and surface roughness may be incorporation radar backscatter information from Sentinel-1. However, it further complicates the processing of data and makes the composite creation more complex.The research has been supported by the project no. QK1820389 " Production of actual detailed maps of soil properties in the Czech Republic based on database of Large-scale Mapping of Agricultural Soils in Czechoslovakia and application of digital soil mapping" funding by Ministry of Agriculture.

Download Full-text

Food Security in Artisanal Mining Communities: An Exploration of Rural Markets in Northern Guinea

Foods ◽

10.3390/foods9040479 ◽

2020 ◽

Vol 9 (4) ◽

pp. 479

Author(s):

Laetitia X. Zhang ◽

Fatima Koroma ◽

Mohammed Lamine Fofana ◽

Alpha Oumar Barry ◽

Sadio Diallo ◽

...

Keyword(s):

Food Security ◽

Rural Areas ◽

Small Scale ◽

Future Market ◽

Structured Interviews ◽

Mining Communities ◽

Customer Needs ◽

Mining Sites ◽

The Republic ◽

Study Sites

The number of people engaged in artisanal and small-scale mining (ASM) has grown rapidly in the past twenty years, but they continue to be an understudied population experiencing high rates of malnutrition, poverty, and food insecurity. This paper explores how characteristics of markets that serve ASM populations facilitate and pose challenges to acquiring a nutritious and sustainable diet. The study sites included eight markets across four mining districts in the Kankan Region in the Republic of Guinea. Market descriptions to capture the structure of village markets, as well as twenty in-depth structured interviews with food vendors at mining site markets were conducted. We identified three forms of market organization based on location and distance from mining sites. Markets located close to mining sites offered fewer fruit and vegetable options, as well as a higher ratio of prepared food options as compared with markets located close to village centers. Vendors were highly responsive to customer needs. Food accessibility and utilization, rather than availability, are critical for food security in non-agricultural rural areas such as mining sites. Future market-based nutrition interventions need to consider the diverse market settings serving ASM communities and leverage the high vendor responsiveness to customer needs.

Download Full-text

Young-Child Feeding in Challenging Settings: A Case Study in Artisanal Mining Families in the Republic of Guinea

Current Developments in Nutrition ◽

10.1093/cdn/nzaa051_011 ◽

2020 ◽

Vol 4 (Supplement_2) ◽

pp. 714-714

Author(s):

Rolf Klemm ◽

Stella Nordhagen ◽

Peter Winch

Keyword(s):

South Carolina ◽

Young Children ◽

Dietary Diversity ◽

Food Choices ◽

Small Scale ◽

Complementary Foods ◽

Child Feeding ◽

Cross Sectional ◽

Mining Sites ◽

Mining Areas

Abstract Objectives Artisanal and small-scale mining (ASM) is a common livelihood across 80 LMICs, particularly among the rural poor in remote areas. Such livelihoods offer higher income potential but also potentially higher environmental and health risks which may incude child malnutrition. Wasting affects ∼15% of children in gold-mining households in northern Guinea, for example, and higher-than-average levels observed in non-mining areas of other countries. This research aims to understand potential causes of child undernutrition by examining diets of children in ASM communities as well as factors driving caregivers’ food choices. Methods Data were collected in 2018–2019 via cross-sectional surveys of mining households with young children (n = 611); in-depth interviews with young children's mothers and other caregivers (n = 112), and observations at mining sites and in young children's homes (n = 25). Quantitative data were analyzed, via descriptive and associational analysis. Qualitative data were analyzed using deductive coding. Results Young children's diets were generally very poor, with only 22% and 21% meeting minimum dietary diversity and minimum meal frequency, respectively. Consumption of micronutrient-rich foods was rare. Key factors influencing household food purchase and food consumption for young children included highly variable day-to-day incomes, low availability of fresh food and appropriate complementary foods, higher availability of highly processed foods, concerns about food hygiene and safety, and limited time available for buying food. A lack of childcare options, combined with unsafe environments for children at mining sites, led to young children being cared for by non-parent caregivers who struggled to provide nutritious meals. Conclusions Social and economic realities shape food choices for young children in households that subsist on unstable, informal livelihoods. Improving children's nutrition in such areas will require improving availability of appropriate complementary foods and engagement of caregivers and food vendors. Funding Sources Funded by Drivers of Food Choice Competitive Grants Program through DFID and Bill & Melinda Gates Foundation, and managed by the University of South Carolina. The views expressed do not necessarily reflect the UK Government's official policies.

Download Full-text

Mapping Mining Areas in the Brazilian Amazon Using MSI/Sentinel-2 Imagery (2017)

Remote Sensing ◽

10.3390/rs10081178 ◽

2018 ◽

Vol 10 (8) ◽

pp. 1178 ◽

Cited By ~ 24

Author(s):

Felipe de Lucia Lobo ◽

Pedro Walfir M. Souza-Filho ◽

Evlyn Márcia Leão de Moraes Novo ◽

Felipe Menino Carlos ◽

Claudio Clemente Faria Barbosa

Keyword(s):

Environmental Impacts ◽

Brazilian Amazon ◽

Mining Area ◽

Current Status ◽

Small Scale ◽

Detection Accuracy ◽

Mining Areas ◽

Geography Information ◽

Sentinel 2A ◽

Sentinel 2

Although mining plays an important role for the economy of the Amazon, little is known about its attributes such as area, type, scale, and current status as well as socio/environmental impacts. Therefore, we first propose a low time-consuming and high detection accuracy method for mapping the current mining areas within 13 regions of the Brazilian Amazon using Sentinel-2 images. Then, integrating the maps in a GIS (Geography Information System) environment, mining attributes for each region were further assessed with the aid of the DNPM (National Department for Mineral Production) database. Detection of the mining area was conducted in five main steps. (a) MSI (MultiSpectral Instrument)/Sentinel-2A (S2A) image selection; (b) definition of land-use classes and training samples; (c) supervised classification; (d) vector editing for quality control; and (e) validation with high-resolution RapidEye images (Kappa = 0.70). Mining areas derived from validated S2A classification totals 1084.7 km2 in the regions analyzed. Small-scale mining comprises up to 64% of total mining area detected comprises mostly gold (617.8 km2), followed by tin mining (73.0 km2). The remaining 36% is comprised by industrial mining such as iron (47.8), copper (55.5) and manganese (8.9 km2) in Carajás, bauxite in Trombetas (78.4) and Rio Capim (48.5 km2). Given recent events of mining impacts, the large extension of mining areas detected raises a concern regarding its socio-environmental impacts for the Amazonian ecosystems and for local communities.

Download Full-text

INVESTIGATING THE POSSIBILITY OF PREPARING SMALL SCALE SOIL MOISTURE MAP FROM COUPLED SENTINEL-1 AND SENTINEL-2 DATA

ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences ◽

10.5194/isprs-archives-xlii-4-w18-127-2019 ◽

2019 ◽

Vol XLII-4/W18 ◽

pp. 127-129

Author(s):

R. Attarzadeh ◽

J. Amini

Keyword(s):

Soil Moisture ◽

Radar Data ◽

Support Vector ◽

Small Scale ◽

Image Objects ◽

Object Based Image Analysis ◽

Object Based ◽

Level 3 ◽

Sentinel 2 ◽

Small Scale Soil

Abstract. With the failure of the radar instrument on NASA's Soil Moisture Active Passive (SMAP) satellite, the Sentinel-1 sensor has been considered as an alternative for replacing the SMAP radar data and restoring the combined radar and radiometer SMC product. A challenging subject to this purpose is the immense discrepancy between the spatial resolution of planned SMAP radar instrument (3 km) and Sentinel-1 data (10 m). In this paper, we investigate the possibility of preparing small scale soil moisture map and its quality from the synergy of Sentinel-1 and Sentinel-2 data using object-based image analysis (OBIA). To reach this goal, the most related features with soil moisture variable extracted from Sentinel-1 and Sentinel-2 data have been used as input layers to multi-resolution segmentation (MRS) algorithm to create image objects. Then the support vector regression (SVR) estimator has been used to calculate the soil moisture value of image objects. Initial evaluations demonstrate that produced soil moisture map obtained acceptable accuracy. In addition, the flexibility of the final product improves on the scale of the soil moisture map regarding the shape and size of image objects. It is also possible to combine this soil moisture product with a Level-3 SMAP SSM product to exploit the advantages of both products. This combination would lead to a small scale soil moisture map with enhanced accuracy and flexible scale.

Download Full-text

Managing the impacts of mining on Ghana’s water resources from a legal perspective

Journal of Energy and Natural Resource Management ◽

10.26796/jenrm.v1i2.33 ◽

2018 ◽

Vol 1 (3) ◽

pp. 156-165 ◽

Cited By ~ 3

Author(s):

Nasirudeen Abdul Fatawu

Keyword(s):

Surface Water ◽

Water Resources ◽

Environmental Protection Agency ◽

Large Scale ◽

Small Scale ◽

Mining Activities ◽

Protection Agency ◽

Environmental Laws ◽

Mining Areas ◽

Legal Perspective

Recent floods in Ghana are largely blamed on mining activities. Not only are lives lost through these floods, farms andproperties are destroyed as a result. Water resources are diverted, polluted and impounded upon by both large-scale minersand small-scale miners. Although these activities are largely blamed on behavioural attitudes that need to be changed, thereare legal dimensions that should be addressed as well. Coincidentally, a great proportion of the water resources of Ghana arewithin these mining areas thus the continual pollution of these surface water sources is a serious threat to the environmentand the development of the country as a whole. The environmental laws need to be oriented properly with adequate sanctionsto tackle the impacts mining has on water resources. The Environmental Impact Assessment (EIA) procedure needs to bestreamlined and undertaken by the Environmental Protection Agency (EPA) and not the company itself.

Download Full-text

SPEAR (Solar Pyrolysis Energy Access Reactor): Theoretical Design and Evaluation of a Small-Scale Low-Cost Pyrolysis Unit for Implementation in Rural Communities

Energies ◽

10.3390/en14082189 ◽

2021 ◽

Vol 14 (8) ◽

pp. 2189

Author(s):

Cesare Caputo ◽

Ondřej Mašek

Keyword(s):

Waste Management ◽

Rural Areas ◽

Net Present Value ◽

Agricultural Waste ◽

Tracking Error ◽

Sub Saharan Africa ◽

Small Scale ◽

Energy Access ◽

Efficient System ◽

Pyrolysis Unit

Energy access and waste management are two of the most pressing developmental and environmental issues on a global level to help mitigate the accelerating impacts of climate change. They are particularly relevant in Sub–Saharan Africa where electrification rates are significantly below global averages and rural areas are lacking a formal waste management sector. This paper explores the potential of integrating solar energy into a biomass pyrolysis unit as a potentially synergetic solution to both issues. The full design of a slow pyrolysis batch reactor targeted at biochar production, following a strict cost minimization approach, is presented in light of the relevant considerations. SPEAR is powered using a Cassegrain optics parabolic dish system, integrated into the reactor via a manual tracking system and optically optimized with a Monte-Carlo ray tracing methodology. The design approach employed has led to the development an overall cost efficient system, with the potential to achieve optical efficiencies up 72% under a 1.5° tracking error. The outputs of the system are biochar and electricity, to be used for soil amendment and energy access purposes, respectively. There is potential to pyrolyze a number of agricultural waste streams for the region, producing at least 5 kg of biochar per unit per day depending on the feedstock employed. Financial assessment of SPEAR yields a positive Net Present Value (NPV) in nearly all scenarios evaluated and a reasonable competitiveness with small scale solar for electrification objectives. Finally, SPEAR presents important positive social and environmental externalities and should be feasibly implementable in the region in the near term.

Download Full-text