A Comparison of Three Temporal Smoothing Algorithms to Improve Land Cover Classification: A Case Study from NEPAL
Time series land cover data statistics often fluctuate abruptly due to seasonal impact and other noise in the input image. Temporal smoothing techniques are used to reduce the noise in time series data used in land cover mapping. The effects of smoothing may vary based on the smoothing method and la...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-09-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/12/18/2888 |
| _version_ | 1827706767016984576 |
|---|---|
| author | Nishanta Khanal Mir Abdul Matin Kabir Uddin Ate Poortinga Farrukh Chishtie Karis Tenneson David Saah |
| author_facet | Nishanta Khanal Mir Abdul Matin Kabir Uddin Ate Poortinga Farrukh Chishtie Karis Tenneson David Saah |
| author_sort | Nishanta Khanal |
| collection | DOAJ |
| description | Time series land cover data statistics often fluctuate abruptly due to seasonal impact and other noise in the input image. Temporal smoothing techniques are used to reduce the noise in time series data used in land cover mapping. The effects of smoothing may vary based on the smoothing method and land cover category. In this study, we compared the performance of Fourier transformation smoothing, Whittaker smoother and Linear-Fit averaging smoother on Landsat 5, 7 and 8 based yearly composites to classify land cover in Province No. 1 of Nepal. The performance of each smoother was tested based on whether it was applied on image composites or on land cover primitives generated using the random forest machine learning method. The land cover data used in the study was from the years 2000 to 2018. Probability distribution was examined to check the quality of primitives and accuracy of the final land cover maps were accessed. The best results were found for the Whittaker smoothing for stable classes and Fourier smoothing for other classes. The results also show that classification using a properly selected smoothing algorithm outperforms a classification based on its unsmoothed data set. The final land cover generated by combining the best results obtained from different smoothing approaches increased our overall land cover map accuracy from 79.18% to 83.44%. This study shows that smoothing can result in a substantial increase in the quality of the results and that the smoothing approach should be carefully considered for each land cover class. |
| first_indexed | 2024-03-10T16:32:17Z |
| format | Article |
| id | doaj.art-d521ea97da4c4f159e5a98c8c7ae54b7 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T16:32:17Z |
| publishDate | 2020-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-d521ea97da4c4f159e5a98c8c7ae54b72023-11-20T12:46:42ZengMDPI AGRemote Sensing2072-42922020-09-011218288810.3390/rs12182888A Comparison of Three Temporal Smoothing Algorithms to Improve Land Cover Classification: A Case Study from NEPALNishanta Khanal0Mir Abdul Matin1Kabir Uddin2Ate Poortinga3Farrukh Chishtie4Karis Tenneson5David Saah6International Centre for Integrated Mountain Development, Kathmandu GPO Box 3226, NepalInternational Centre for Integrated Mountain Development, Kathmandu GPO Box 3226, NepalInternational Centre for Integrated Mountain Development, Kathmandu GPO Box 3226, NepalSpatial Informatics Group, LLC, 2529 Yolanda Ct., Pleasanton, CA 94566, USASpatial Informatics Group, LLC, 2529 Yolanda Ct., Pleasanton, CA 94566, USASpatial Informatics Group, LLC, 2529 Yolanda Ct., Pleasanton, CA 94566, USASpatial Informatics Group, LLC, 2529 Yolanda Ct., Pleasanton, CA 94566, USATime series land cover data statistics often fluctuate abruptly due to seasonal impact and other noise in the input image. Temporal smoothing techniques are used to reduce the noise in time series data used in land cover mapping. The effects of smoothing may vary based on the smoothing method and land cover category. In this study, we compared the performance of Fourier transformation smoothing, Whittaker smoother and Linear-Fit averaging smoother on Landsat 5, 7 and 8 based yearly composites to classify land cover in Province No. 1 of Nepal. The performance of each smoother was tested based on whether it was applied on image composites or on land cover primitives generated using the random forest machine learning method. The land cover data used in the study was from the years 2000 to 2018. Probability distribution was examined to check the quality of primitives and accuracy of the final land cover maps were accessed. The best results were found for the Whittaker smoothing for stable classes and Fourier smoothing for other classes. The results also show that classification using a properly selected smoothing algorithm outperforms a classification based on its unsmoothed data set. The final land cover generated by combining the best results obtained from different smoothing approaches increased our overall land cover map accuracy from 79.18% to 83.44%. This study shows that smoothing can result in a substantial increase in the quality of the results and that the smoothing approach should be carefully considered for each land cover class.https://www.mdpi.com/2072-4292/12/18/2888remote sensingtemporal smoothinggoogle earth enginemachine learningrandom forestland cover |
| spellingShingle | Nishanta Khanal Mir Abdul Matin Kabir Uddin Ate Poortinga Farrukh Chishtie Karis Tenneson David Saah A Comparison of Three Temporal Smoothing Algorithms to Improve Land Cover Classification: A Case Study from NEPAL Remote Sensing remote sensing temporal smoothing google earth engine machine learning random forest land cover |
| title | A Comparison of Three Temporal Smoothing Algorithms to Improve Land Cover Classification: A Case Study from NEPAL |
| title_full | A Comparison of Three Temporal Smoothing Algorithms to Improve Land Cover Classification: A Case Study from NEPAL |
| title_fullStr | A Comparison of Three Temporal Smoothing Algorithms to Improve Land Cover Classification: A Case Study from NEPAL |
| title_full_unstemmed | A Comparison of Three Temporal Smoothing Algorithms to Improve Land Cover Classification: A Case Study from NEPAL |
| title_short | A Comparison of Three Temporal Smoothing Algorithms to Improve Land Cover Classification: A Case Study from NEPAL |
| title_sort | comparison of three temporal smoothing algorithms to improve land cover classification a case study from nepal |
| topic | remote sensing temporal smoothing google earth engine machine learning random forest land cover |
| url | https://www.mdpi.com/2072-4292/12/18/2888 |
| work_keys_str_mv | AT nishantakhanal acomparisonofthreetemporalsmoothingalgorithmstoimprovelandcoverclassificationacasestudyfromnepal AT mirabdulmatin acomparisonofthreetemporalsmoothingalgorithmstoimprovelandcoverclassificationacasestudyfromnepal AT kabiruddin acomparisonofthreetemporalsmoothingalgorithmstoimprovelandcoverclassificationacasestudyfromnepal AT atepoortinga acomparisonofthreetemporalsmoothingalgorithmstoimprovelandcoverclassificationacasestudyfromnepal AT farrukhchishtie acomparisonofthreetemporalsmoothingalgorithmstoimprovelandcoverclassificationacasestudyfromnepal AT karistenneson acomparisonofthreetemporalsmoothingalgorithmstoimprovelandcoverclassificationacasestudyfromnepal AT davidsaah acomparisonofthreetemporalsmoothingalgorithmstoimprovelandcoverclassificationacasestudyfromnepal AT nishantakhanal comparisonofthreetemporalsmoothingalgorithmstoimprovelandcoverclassificationacasestudyfromnepal AT mirabdulmatin comparisonofthreetemporalsmoothingalgorithmstoimprovelandcoverclassificationacasestudyfromnepal AT kabiruddin comparisonofthreetemporalsmoothingalgorithmstoimprovelandcoverclassificationacasestudyfromnepal AT atepoortinga comparisonofthreetemporalsmoothingalgorithmstoimprovelandcoverclassificationacasestudyfromnepal AT farrukhchishtie comparisonofthreetemporalsmoothingalgorithmstoimprovelandcoverclassificationacasestudyfromnepal AT karistenneson comparisonofthreetemporalsmoothingalgorithmstoimprovelandcoverclassificationacasestudyfromnepal AT davidsaah comparisonofthreetemporalsmoothingalgorithmstoimprovelandcoverclassificationacasestudyfromnepal |