Monitoring tailings flocculation performance using hyperspectral imagery

Entezari, Iman; Rivard, Benoît; Vajihinejad, Vahid; Wilson, Ward; Soares, João B. P.; Fisseha, Bereket; Beier, Nicholas

doi:10.1002/cjce.23493

Cited by 3 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, rice leaves can be used in studies on heavy metals in soil, allowing to directly determine the contents of related metals in soil. According to another study, hyperspectroscopy allows one to identify pollutants in "special" soil-tailings in tailing ponds [100] and to monitor the activity and flocculation of tailings [101,102]. In addition, more than 40 scholars [103] have jointly studied the global soil spectra in the visible-to-near-infrared spectrum scope and coded the spectral reflectivity or emissivity characteristics of the minerals, organic matters, water, and other components in soil into the database.…”

Section: Soil Quality Monitoringmentioning

confidence: 99%

Progress in the Remote Sensing Monitoring of the Ecological Environment in Mining Areas

Song

et al. 2020

IJERPH

View full text Add to dashboard Cite

Based on the results of an extensive literature research, we summarize the research progress of remote sensing monitoring in terms of identifying mining area boundaries and monitoring land use or land cover changes of mining areas. We also analyze the application of remote sensing in monitoring the biodiversity, landscape structure, vegetation change, soil environment, surface runoff conditions, and the atmospheric environment in mining areas and predict the prospects of remote sensing in monitoring the ecological environment in mining areas. Based on the results, the accurate classification of land use or land cover and the accurate extraction of environmental factors are the basis for remote sensing monitoring of the ecological environment in mining areas. In terms of the extraction of ecological factors, vegetation extraction is relatively advanced in contrast to the extraction of animal and microbial data. For the monitoring of environmental conditions of mining areas, sophisticated methods are available to identify pollution levels of vegetation and to accurately monitor soil quality. However, the methods for water and air pollution monitoring in mining areas still need to be improved. These limitations considerably impede the application of remote sensing monitoring in mining areas. The solving of these problems depends on the progress of multi-source remote sensing data and stereoscopic monitoring techniques.

show abstract

Section: Soil Quality Monitoringmentioning

confidence: 99%

Progress in the Remote Sensing Monitoring of the Ecological Environment in Mining Areas

Song

et al. 2020

IJERPH

View full text Add to dashboard Cite

show abstract

“…The greater availability of the technology and continuous increases in scene resolution [1], as well as the commoditization of data processing power and data storage, have made these images more common as a source of information to extract knowledge from. Hyperspectral and multispectral image processing [2] have been successfully used to perform a variety of semi-automated tasks as a way to increase the efficiency of productive processes in diverse fields [3][4][5][6][7].…”

Section: Introductionmentioning

confidence: 99%

A New Multispectral Data Augmentation Technique Based on Data Imputation

2021

View full text Add to dashboard Cite

Deep Learning (DL) has been recently introduced into the hyperspectral and multispectral image classification landscape. Despite the success of DL in the remote sensing field, DL models are computationally intensive due to the large number of parameters they need to learn. The high density of information present in remote sensing imagery with high spectral resolution can make the application of DL models to large scenes challenging. Methods such as patch-based classification require large amounts of data to be processed during the training and prediction stages, which translates into long processing times and high energy consumption. One of the solutions to decrease the computational cost of these models is to perform segment-based classification. Segment-based classification schemes can significantly decrease training and prediction times, and also offer advantages over simply reducing the size of the training datasets by randomly sampling training data. The lack of a large enough number of samples can, however, pose an additional challenge, causing these models to not generalize properly. Data augmentation methods are used to generate new synthetic samples based on existing data to increase the classification performance. In this work, we propose a new data augmentation scheme using data imputation and matrix completion methods for segment-based classification. The proposal has been validated using two high-resolution multispectral datasets from the literature. The results obtained show that the proposed approach successfully increases the classification performance across all the scenes tested and that data imputation methods applied to multispectral imagery are a valid means to perform data augmentation. A comparison of classification accuracy between different imputation methods applied to the proposed scheme was also carried out.

show abstract

Design of SiO₂-TiO₂-P(AM-DMC) cationic composite flocculant and optimization of the flocculation process using response surface methodology

Wang

Wei

et al. 2020

Journal of Dispersion Science and Technology

View full text Add to dashboard Cite

Monitoring tailings flocculation performance using hyperspectral imagery

Cited by 3 publications

References 12 publications

Progress in the Remote Sensing Monitoring of the Ecological Environment in Mining Areas

Progress in the Remote Sensing Monitoring of the Ecological Environment in Mining Areas

A New Multispectral Data Augmentation Technique Based on Data Imputation

Design of SiO₂-TiO₂-P(AM-DMC) cationic composite flocculant and optimization of the flocculation process using response surface methodology

Contact Info

Product

Resources

About

Monitoring tailings flocculation performance using hyperspectral imagery

Cited by 3 publications

References 12 publications

Progress in the Remote Sensing Monitoring of the Ecological Environment in Mining Areas

Progress in the Remote Sensing Monitoring of the Ecological Environment in Mining Areas

A New Multispectral Data Augmentation Technique Based on Data Imputation

Design of SiO2-TiO2-P(AM-DMC) cationic composite flocculant and optimization of the flocculation process using response surface methodology

Contact Info

Product

Resources

About

Design of SiO₂-TiO₂-P(AM-DMC) cationic composite flocculant and optimization of the flocculation process using response surface methodology