Monitoring the Extent of Reclamation of Small Scale Mining Areas Using Artificial Neural Networks
Small scale mining is mainly widespread in developing and underdeveloped countries. Although it is a source of livelihood for several people, it causes environmental degradation. Reclamation is needed to restore mined areas to an acceptable condition. This study uses ANN to monitor reclamation activ...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2019-04-01
|
| Series: | Heliyon |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2405844018309769 |
| _version_ | 1818543753506324480 |
|---|---|
| author | Christian Aboagye Abaidoo Edward Matthew Osei Jnr Anthony Arko-Adjei Benjamin Eric Kwesi Prah |
| author_facet | Christian Aboagye Abaidoo Edward Matthew Osei Jnr Anthony Arko-Adjei Benjamin Eric Kwesi Prah |
| author_sort | Christian Aboagye Abaidoo |
| collection | DOAJ |
| description | Small scale mining is mainly widespread in developing and underdeveloped countries. Although it is a source of livelihood for several people, it causes environmental degradation. Reclamation is needed to restore mined areas to an acceptable condition. This study uses ANN to monitor reclamation activities in small scale mining area. Landsat satellite images of study area (2007, 2011 and 2016), ground truth data and ESRI shapefile of the study area were used for the analyses. Two ANN classification methods, Unsupervised Self – Organized Mapping (SOM) and Supervised Multilayer Perceptron (MLP), were used for the classification of the satellite images. Normalized Difference Vegetation Index (NDVI) change maps were generated in order to help confirm where actual change had occurred and to what extent it had occurred. The results show disturbance and revegetation in the study area between 2007 and 2016. The Barelands/mined areas class increased by 60.4% and a decrease in the vegetation class by 18.7% from 2007 to 2011. There was revegetation from 2011 to 2016 with the Barelands/Mined Area decreasing by 51.7% and the vegetation increasing by 3.9%. The study shows an increase in the settlement class by 87.3%. The research concludes that the application of ANN be strongly encouraged for image classification and mine reclamation monitoring in the country due to the size and quality of training data, network architecture, and training parameters as well as the ability to improve the accuracy and fine tune information obtained from individual classes as compared to other classification methods. |
| first_indexed | 2024-12-11T22:39:30Z |
| format | Article |
| id | doaj.art-70813d9932964e65a5e999ac4e3b9a84 |
| institution | Directory Open Access Journal |
| issn | 2405-8440 |
| language | English |
| last_indexed | 2024-12-11T22:39:30Z |
| publishDate | 2019-04-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Heliyon |
| spelling | doaj.art-70813d9932964e65a5e999ac4e3b9a842022-12-22T00:47:50ZengElsevierHeliyon2405-84402019-04-0154e01445Monitoring the Extent of Reclamation of Small Scale Mining Areas Using Artificial Neural NetworksChristian Aboagye Abaidoo0Edward Matthew Osei Jnr1Anthony Arko-Adjei2Benjamin Eric Kwesi Prah3Corresponding author.; Department of Geomatic Engineering, KNUST, Kumasi, GhanaDepartment of Geomatic Engineering, KNUST, Kumasi, GhanaDepartment of Geomatic Engineering, KNUST, Kumasi, GhanaDepartment of Geomatic Engineering, KNUST, Kumasi, GhanaSmall scale mining is mainly widespread in developing and underdeveloped countries. Although it is a source of livelihood for several people, it causes environmental degradation. Reclamation is needed to restore mined areas to an acceptable condition. This study uses ANN to monitor reclamation activities in small scale mining area. Landsat satellite images of study area (2007, 2011 and 2016), ground truth data and ESRI shapefile of the study area were used for the analyses. Two ANN classification methods, Unsupervised Self – Organized Mapping (SOM) and Supervised Multilayer Perceptron (MLP), were used for the classification of the satellite images. Normalized Difference Vegetation Index (NDVI) change maps were generated in order to help confirm where actual change had occurred and to what extent it had occurred. The results show disturbance and revegetation in the study area between 2007 and 2016. The Barelands/mined areas class increased by 60.4% and a decrease in the vegetation class by 18.7% from 2007 to 2011. There was revegetation from 2011 to 2016 with the Barelands/Mined Area decreasing by 51.7% and the vegetation increasing by 3.9%. The study shows an increase in the settlement class by 87.3%. The research concludes that the application of ANN be strongly encouraged for image classification and mine reclamation monitoring in the country due to the size and quality of training data, network architecture, and training parameters as well as the ability to improve the accuracy and fine tune information obtained from individual classes as compared to other classification methods.http://www.sciencedirect.com/science/article/pii/S2405844018309769Environmental scienceGeography |
| spellingShingle | Christian Aboagye Abaidoo Edward Matthew Osei Jnr Anthony Arko-Adjei Benjamin Eric Kwesi Prah Monitoring the Extent of Reclamation of Small Scale Mining Areas Using Artificial Neural Networks Heliyon Environmental science Geography |
| title | Monitoring the Extent of Reclamation of Small Scale Mining Areas Using Artificial Neural Networks |
| title_full | Monitoring the Extent of Reclamation of Small Scale Mining Areas Using Artificial Neural Networks |
| title_fullStr | Monitoring the Extent of Reclamation of Small Scale Mining Areas Using Artificial Neural Networks |
| title_full_unstemmed | Monitoring the Extent of Reclamation of Small Scale Mining Areas Using Artificial Neural Networks |
| title_short | Monitoring the Extent of Reclamation of Small Scale Mining Areas Using Artificial Neural Networks |
| title_sort | monitoring the extent of reclamation of small scale mining areas using artificial neural networks |
| topic | Environmental science Geography |
| url | http://www.sciencedirect.com/science/article/pii/S2405844018309769 |
| work_keys_str_mv | AT christianaboagyeabaidoo monitoringtheextentofreclamationofsmallscaleminingareasusingartificialneuralnetworks AT edwardmatthewoseijnr monitoringtheextentofreclamationofsmallscaleminingareasusingartificialneuralnetworks AT anthonyarkoadjei monitoringtheextentofreclamationofsmallscaleminingareasusingartificialneuralnetworks AT benjaminerickwesiprah monitoringtheextentofreclamationofsmallscaleminingareasusingartificialneuralnetworks |