On Drivers of Subpixel Classification Accuracy—An Example From Glacier Facies
Subpixel classification (SPC) extracts meaningful information on land-cover classes from the mixed pixels. However, the major challenges for SPC are to obtain reliable soft reference data (RD), use apt input data, and achieve maximum accuracy. This article addresses these issues and applies the supp...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8968758/ |
| _version_ | 1818620544687276032 |
|---|---|
| author | Bisma Yousuf Aparna Shukla Manoj K. Arora Ankit Bindal Avtar S. Jasrotia |
| author_facet | Bisma Yousuf Aparna Shukla Manoj K. Arora Ankit Bindal Avtar S. Jasrotia |
| author_sort | Bisma Yousuf |
| collection | DOAJ |
| description | Subpixel classification (SPC) extracts meaningful information on land-cover classes from the mixed pixels. However, the major challenges for SPC are to obtain reliable soft reference data (RD), use apt input data, and achieve maximum accuracy. This article addresses these issues and applies the support vector machine (SVM) to retrieve the subpixel estimates of glacier facies (GF) using high radiometric-resolution Advanced Wide Field Sensor (AWiFS) data. Precise quantification of GF has fundamental importance in the glaciological research. Efficacy of the approach was first tested on the synthetic data followed by the input AWiFS and reference MultiSpectral Instrument data, including ancillary data. SPC of synthetic data resulted in overall accuracy (OA) of 95%, proving the merit of SVM. Classification accuracy is inversely related to the glacier's surface heterogeneity. Reducing the number of classes enhanced the OA by ~18%. Source and timing of RD invariably controls the SPC accuracy. OA improved by ~5% on addressing the issue of temporal gap between input and RD. ~11% increase in OA with the inclusion of ancillary data confirmed their positive effect on the accuracy. Input and reference fractional area of GF were strongly correlated (r > 0.9) with each other substantiating the results. |
| first_indexed | 2024-12-16T17:55:04Z |
| format | Article |
| id | doaj.art-68a6d4cde93b4b60b5235a91b46ba1b5 |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-12-16T17:55:04Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-68a6d4cde93b4b60b5235a91b46ba1b52022-12-21T22:22:11ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352020-01-011360160810.1109/JSTARS.2019.29559558968758On Drivers of Subpixel Classification Accuracy—An Example From Glacier FaciesBisma Yousuf0https://orcid.org/0000-0001-5130-5216Aparna Shukla1https://orcid.org/0000-0003-2269-7796Manoj K. Arora2https://orcid.org/0000-0002-3175-5102Ankit Bindal3Avtar S. Jasrotia4Wadia Institute of Himalayan Geology, Dehradun, IndiaWadia Institute of Himalayan Geology, Dehradun, IndiaPunjab Engineering College, Chandigarh, IndiaPunjab Engineering College, Chandigarh, IndiaUniversity of Jammu, Jammu, IndiaSubpixel classification (SPC) extracts meaningful information on land-cover classes from the mixed pixels. However, the major challenges for SPC are to obtain reliable soft reference data (RD), use apt input data, and achieve maximum accuracy. This article addresses these issues and applies the support vector machine (SVM) to retrieve the subpixel estimates of glacier facies (GF) using high radiometric-resolution Advanced Wide Field Sensor (AWiFS) data. Precise quantification of GF has fundamental importance in the glaciological research. Efficacy of the approach was first tested on the synthetic data followed by the input AWiFS and reference MultiSpectral Instrument data, including ancillary data. SPC of synthetic data resulted in overall accuracy (OA) of 95%, proving the merit of SVM. Classification accuracy is inversely related to the glacier's surface heterogeneity. Reducing the number of classes enhanced the OA by ~18%. Source and timing of RD invariably controls the SPC accuracy. OA improved by ~5% on addressing the issue of temporal gap between input and RD. ~11% increase in OA with the inclusion of ancillary data confirmed their positive effect on the accuracy. Input and reference fractional area of GF were strongly correlated (r > 0.9) with each other substantiating the results.https://ieeexplore.ieee.org/document/8968758/Advanced Wide Field Sensor (AWiFS)coarse-resolutionGangotriglacier faciessubpixel classification (SPC)support vector machine (SVM) |
| spellingShingle | Bisma Yousuf Aparna Shukla Manoj K. Arora Ankit Bindal Avtar S. Jasrotia On Drivers of Subpixel Classification Accuracy—An Example From Glacier Facies IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Advanced Wide Field Sensor (AWiFS) coarse-resolution Gangotri glacier facies subpixel classification (SPC) support vector machine (SVM) |
| title | On Drivers of Subpixel Classification Accuracy—An Example From Glacier Facies |
| title_full | On Drivers of Subpixel Classification Accuracy—An Example From Glacier Facies |
| title_fullStr | On Drivers of Subpixel Classification Accuracy—An Example From Glacier Facies |
| title_full_unstemmed | On Drivers of Subpixel Classification Accuracy—An Example From Glacier Facies |
| title_short | On Drivers of Subpixel Classification Accuracy—An Example From Glacier Facies |
| title_sort | on drivers of subpixel classification accuracy x2014 an example from glacier facies |
| topic | Advanced Wide Field Sensor (AWiFS) coarse-resolution Gangotri glacier facies subpixel classification (SPC) support vector machine (SVM) |
| url | https://ieeexplore.ieee.org/document/8968758/ |
| work_keys_str_mv | AT bismayousuf ondriversofsubpixelclassificationaccuracyx2014anexamplefromglacierfacies AT aparnashukla ondriversofsubpixelclassificationaccuracyx2014anexamplefromglacierfacies AT manojkarora ondriversofsubpixelclassificationaccuracyx2014anexamplefromglacierfacies AT ankitbindal ondriversofsubpixelclassificationaccuracyx2014anexamplefromglacierfacies AT avtarsjasrotia ondriversofsubpixelclassificationaccuracyx2014anexamplefromglacierfacies |