Land Cover Classification Based on UAV Photogrammetry and Deep Learning for Supporting Mine Reclamation: A Case Study of Mae Moh Mine in Lampang Province, Thailand
Detailed, accurate, and frequent mapping of land cover are the prerequisite regarding areas of reclaimed mines and the development of sustainable project-level for goals. Mine reclamation is essential as the extractive organizations are bounded by-laws that have been established by stakeholders to...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Environmental Research Institute, Chulalongkorn University
2021-10-01
|
| Series: | Applied Environmental Research |
| Subjects: | |
| Online Access: | https://ph01.tci-thaijo.org/jer/index.php/aer/article/view/245734 |
| _version_ | 1797294873828655104 |
|---|---|
| author | Tejendra K. Yadav Polpreecha Chidburee Nattapon Mahavik |
| author_facet | Tejendra K. Yadav Polpreecha Chidburee Nattapon Mahavik |
| author_sort | Tejendra K. Yadav |
| collection | DOAJ |
| description |
Detailed, accurate, and frequent mapping of land cover are the prerequisite regarding areas of reclaimed mines and the development of sustainable project-level for goals. Mine reclamation is essential as the extractive organizations are bounded by-laws that have been established by stakeholders to ensure that the mined areas are properly restored. As databases at the mines area become outdated, an automated process of upgrading is needed. Currently, there are only few studies regarding mine reclamation which has less potential of land cover classification using Unmanned Aerial Vehicle (UAV) photogrammetry with Deep learning (DL). This paper aims to employ the classification of land cover for monitoring mine reclamation using DL from the UAV photogrammetric results. The land cover was classified into five classes, comprising: 1) trees, 2) shadow, 3) grassland, 4) barren land, and 5) others (as undefined). To perform the classification using DL, the UAV photogrammetric results, orthophoto and Digital Surface Model (DSM) were used. The effectiveness of both results was examined to verify the potential of land cover classification. The experimental findings showed that effective results for land cover classification over test area were obtained by DL through the combination of orthophoto and DSM with an Overall Accuracy of 0.904, Average Accuracy of 0.681, and Kappa index of 0.937. Our experiments showed that land cover classification from combination orthophoto with DSM was more precise than using orthophoto only. This research provides framework for conducting an analytical process, a UAV approach with DL based evaluation of mine reclamation with safety, also providing a time series information for future efforts to evaluate reclamation. The procedure resulting from this research constitutes approach that is intended to be adopted by government organizations and private corporations so that it will provide accurate evaluation of reclamation in timely manner with reasonable budget.
|
| first_indexed | 2024-03-07T21:38:26Z |
| format | Article |
| id | doaj.art-510a7fb4cb2242e497e5b5b9e548c0c6 |
| institution | Directory Open Access Journal |
| issn | 2287-075X |
| language | English |
| last_indexed | 2024-03-07T21:38:26Z |
| publishDate | 2021-10-01 |
| publisher | Environmental Research Institute, Chulalongkorn University |
| record_format | Article |
| series | Applied Environmental Research |
| spelling | doaj.art-510a7fb4cb2242e497e5b5b9e548c0c62024-02-26T10:49:36ZengEnvironmental Research Institute, Chulalongkorn UniversityApplied Environmental Research2287-075X2021-10-0143410.35762/AER.2021.43.4.4Land Cover Classification Based on UAV Photogrammetry and Deep Learning for Supporting Mine Reclamation: A Case Study of Mae Moh Mine in Lampang Province, ThailandTejendra K. Yadav0Polpreecha Chidburee1Nattapon Mahavik2Faculty of Agriculture Natural Resources and Environment, Naresuan University, Phitsanulok, ThailandFaculty of Engineering, Naresuan University, Phitsanulok, ThailandFaculty of Agriculture Natural Resources and Environment, Naresuan University, Phitsanulok, Thailand Detailed, accurate, and frequent mapping of land cover are the prerequisite regarding areas of reclaimed mines and the development of sustainable project-level for goals. Mine reclamation is essential as the extractive organizations are bounded by-laws that have been established by stakeholders to ensure that the mined areas are properly restored. As databases at the mines area become outdated, an automated process of upgrading is needed. Currently, there are only few studies regarding mine reclamation which has less potential of land cover classification using Unmanned Aerial Vehicle (UAV) photogrammetry with Deep learning (DL). This paper aims to employ the classification of land cover for monitoring mine reclamation using DL from the UAV photogrammetric results. The land cover was classified into five classes, comprising: 1) trees, 2) shadow, 3) grassland, 4) barren land, and 5) others (as undefined). To perform the classification using DL, the UAV photogrammetric results, orthophoto and Digital Surface Model (DSM) were used. The effectiveness of both results was examined to verify the potential of land cover classification. The experimental findings showed that effective results for land cover classification over test area were obtained by DL through the combination of orthophoto and DSM with an Overall Accuracy of 0.904, Average Accuracy of 0.681, and Kappa index of 0.937. Our experiments showed that land cover classification from combination orthophoto with DSM was more precise than using orthophoto only. This research provides framework for conducting an analytical process, a UAV approach with DL based evaluation of mine reclamation with safety, also providing a time series information for future efforts to evaluate reclamation. The procedure resulting from this research constitutes approach that is intended to be adopted by government organizations and private corporations so that it will provide accurate evaluation of reclamation in timely manner with reasonable budget. https://ph01.tci-thaijo.org/jer/index.php/aer/article/view/245734Land cover classificationUnmanned Aerial Vehicle (UAV)PhotogrammetryDeep learning (DL)Convolution neural network (CNN) |
| spellingShingle | Tejendra K. Yadav Polpreecha Chidburee Nattapon Mahavik Land Cover Classification Based on UAV Photogrammetry and Deep Learning for Supporting Mine Reclamation: A Case Study of Mae Moh Mine in Lampang Province, Thailand Applied Environmental Research Land cover classification Unmanned Aerial Vehicle (UAV) Photogrammetry Deep learning (DL) Convolution neural network (CNN) |
| title | Land Cover Classification Based on UAV Photogrammetry and Deep Learning for Supporting Mine Reclamation: A Case Study of Mae Moh Mine in Lampang Province, Thailand |
| title_full | Land Cover Classification Based on UAV Photogrammetry and Deep Learning for Supporting Mine Reclamation: A Case Study of Mae Moh Mine in Lampang Province, Thailand |
| title_fullStr | Land Cover Classification Based on UAV Photogrammetry and Deep Learning for Supporting Mine Reclamation: A Case Study of Mae Moh Mine in Lampang Province, Thailand |
| title_full_unstemmed | Land Cover Classification Based on UAV Photogrammetry and Deep Learning for Supporting Mine Reclamation: A Case Study of Mae Moh Mine in Lampang Province, Thailand |
| title_short | Land Cover Classification Based on UAV Photogrammetry and Deep Learning for Supporting Mine Reclamation: A Case Study of Mae Moh Mine in Lampang Province, Thailand |
| title_sort | land cover classification based on uav photogrammetry and deep learning for supporting mine reclamation a case study of mae moh mine in lampang province thailand |
| topic | Land cover classification Unmanned Aerial Vehicle (UAV) Photogrammetry Deep learning (DL) Convolution neural network (CNN) |
| url | https://ph01.tci-thaijo.org/jer/index.php/aer/article/view/245734 |
| work_keys_str_mv | AT tejendrakyadav landcoverclassificationbasedonuavphotogrammetryanddeeplearningforsupportingminereclamationacasestudyofmaemohmineinlampangprovincethailand AT polpreechachidburee landcoverclassificationbasedonuavphotogrammetryanddeeplearningforsupportingminereclamationacasestudyofmaemohmineinlampangprovincethailand AT nattaponmahavik landcoverclassificationbasedonuavphotogrammetryanddeeplearningforsupportingminereclamationacasestudyofmaemohmineinlampangprovincethailand |