Improving the Accuracy of Land Use and Land Cover Classification of Landsat Data in an Agricultural Watershed
Classification of remotely sensed imagery for reliable land use and land cover (LULC) remains a challenge in areas where spectrally similar LULC features occur. For example, bare soils of harvested crop fields in agricultural watersheds exhibit spectral characteristics similar to high-intensity deve...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-08-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/16/4020 |
| _version_ | 1797583332847910912 |
|---|---|
| author | Padmanava Dash Scott L. Sanders Prem Parajuli Ying Ouyang |
| author_facet | Padmanava Dash Scott L. Sanders Prem Parajuli Ying Ouyang |
| author_sort | Padmanava Dash |
| collection | DOAJ |
| description | Classification of remotely sensed imagery for reliable land use and land cover (LULC) remains a challenge in areas where spectrally similar LULC features occur. For example, bare soils of harvested crop fields in agricultural watersheds exhibit spectral characteristics similar to high-intensity developed regions and impede an accurate classification. The goal of this study is to improve the accuracy of LULC classification of satellite imagery for the Big Sunflower River Watershed, Mississippi using ancillary data, multiple classification methods, and a post-classification correction (PCC). To determine the best approach, the methodology was applied to Landsat 8 Operational Land Imager (OLI) imagery during the growing season and post-harvest. Imagery for the growing season was acquired on 25 August 2015, and post-harvest was acquired on 7 January 2018. Three classification methods were applied: maximum likelihood (ML), support vector machine (SVM), and random forest (RF). LULC imagery was classified as open water, woody wetlands, harvested crop, rangeland, cultivated crop, high-intensity developed, and mid-low intensity developed areas. Ancillary data such as normalized difference vegetation index (NDVI), thematic maps of urban areas, river networks, transportation networks, high-resolution National Agriculture Imagery Program (NAIP) imagery, Google Earth time-series data, and phenology were used to determine the training dataset. Initially none of the three classification methods performed adequately. Hence, a post-classification correction (PCC) was implemented by masking and applying a majority filter using thematic maps of urban areas. Once PCC was implemented, the accuracies from each of the classification methods increased significantly with the SVM classification method performing best in both the growing season and post-harvest with an overall classification accuracy of 93.5% with a Kappa statistic of 0.88 in the post-harvest imagery and an overall classification accuracy of 84% with a Kappa statistic of 0.789 in the imagery from the growing season. It was found that SVM was the best classification method while PCC is an effective strategy to implement when dealing with spectrally similar LULC features. The use of SVM together with PCC increased the reliability of the information extracted. Strategies from this study can help to evaluate the LULC in agricultural and other watersheds. |
| first_indexed | 2024-03-10T23:36:27Z |
| format | Article |
| id | doaj.art-3dc2f21d84cc4eff9f505c8695f510d8 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T23:36:27Z |
| publishDate | 2023-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-3dc2f21d84cc4eff9f505c8695f510d82023-11-19T02:53:26ZengMDPI AGRemote Sensing2072-42922023-08-011516402010.3390/rs15164020Improving the Accuracy of Land Use and Land Cover Classification of Landsat Data in an Agricultural WatershedPadmanava Dash0Scott L. Sanders1Prem Parajuli2Ying Ouyang3Department of Geosciences, Mississippi State University, Mississippi State, MS 39762, USADepartment of Geosciences, Mississippi State University, Mississippi State, MS 39762, USADepartment of Agricultural and Biological Engineering, Mississippi State University, Mississippi State, MS 39762, USAUSDA Forest Service, Center for Bottomland Hardwoods Research, 775 Stone Blvd., Thompson Hall, Room 309, Mississippi State, MS 39762, USAClassification of remotely sensed imagery for reliable land use and land cover (LULC) remains a challenge in areas where spectrally similar LULC features occur. For example, bare soils of harvested crop fields in agricultural watersheds exhibit spectral characteristics similar to high-intensity developed regions and impede an accurate classification. The goal of this study is to improve the accuracy of LULC classification of satellite imagery for the Big Sunflower River Watershed, Mississippi using ancillary data, multiple classification methods, and a post-classification correction (PCC). To determine the best approach, the methodology was applied to Landsat 8 Operational Land Imager (OLI) imagery during the growing season and post-harvest. Imagery for the growing season was acquired on 25 August 2015, and post-harvest was acquired on 7 January 2018. Three classification methods were applied: maximum likelihood (ML), support vector machine (SVM), and random forest (RF). LULC imagery was classified as open water, woody wetlands, harvested crop, rangeland, cultivated crop, high-intensity developed, and mid-low intensity developed areas. Ancillary data such as normalized difference vegetation index (NDVI), thematic maps of urban areas, river networks, transportation networks, high-resolution National Agriculture Imagery Program (NAIP) imagery, Google Earth time-series data, and phenology were used to determine the training dataset. Initially none of the three classification methods performed adequately. Hence, a post-classification correction (PCC) was implemented by masking and applying a majority filter using thematic maps of urban areas. Once PCC was implemented, the accuracies from each of the classification methods increased significantly with the SVM classification method performing best in both the growing season and post-harvest with an overall classification accuracy of 93.5% with a Kappa statistic of 0.88 in the post-harvest imagery and an overall classification accuracy of 84% with a Kappa statistic of 0.789 in the imagery from the growing season. It was found that SVM was the best classification method while PCC is an effective strategy to implement when dealing with spectrally similar LULC features. The use of SVM together with PCC increased the reliability of the information extracted. Strategies from this study can help to evaluate the LULC in agricultural and other watersheds.https://www.mdpi.com/2072-4292/15/16/4020land use and land coverclassificationagricultural watershedmaximum likelihoodsupport vector machinerandom forest |
| spellingShingle | Padmanava Dash Scott L. Sanders Prem Parajuli Ying Ouyang Improving the Accuracy of Land Use and Land Cover Classification of Landsat Data in an Agricultural Watershed Remote Sensing land use and land cover classification agricultural watershed maximum likelihood support vector machine random forest |
| title | Improving the Accuracy of Land Use and Land Cover Classification of Landsat Data in an Agricultural Watershed |
| title_full | Improving the Accuracy of Land Use and Land Cover Classification of Landsat Data in an Agricultural Watershed |
| title_fullStr | Improving the Accuracy of Land Use and Land Cover Classification of Landsat Data in an Agricultural Watershed |
| title_full_unstemmed | Improving the Accuracy of Land Use and Land Cover Classification of Landsat Data in an Agricultural Watershed |
| title_short | Improving the Accuracy of Land Use and Land Cover Classification of Landsat Data in an Agricultural Watershed |
| title_sort | improving the accuracy of land use and land cover classification of landsat data in an agricultural watershed |
| topic | land use and land cover classification agricultural watershed maximum likelihood support vector machine random forest |
| url | https://www.mdpi.com/2072-4292/15/16/4020 |
| work_keys_str_mv | AT padmanavadash improvingtheaccuracyoflanduseandlandcoverclassificationoflandsatdatainanagriculturalwatershed AT scottlsanders improvingtheaccuracyoflanduseandlandcoverclassificationoflandsatdatainanagriculturalwatershed AT premparajuli improvingtheaccuracyoflanduseandlandcoverclassificationoflandsatdatainanagriculturalwatershed AT yingouyang improvingtheaccuracyoflanduseandlandcoverclassificationoflandsatdatainanagriculturalwatershed |