Limiting the Collection of Ground Truth Data for Land Use and Land Cover Maps with Machine Learning Algorithms
<p dir="ltr">Land use and land cover (LULC) classification maps help understand the state and trends of agricultural production and provide insights for applications in environmental monitoring. One of the major downfalls of the LULC technique is inherently linked to its need for gro...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | , , , , |
| Published: |
2022
|
| Subjects: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1864513531080081408 |
|---|---|
| author | Usman Ali (6586886) |
| author2 | Travis J. Esau (17541300) Aitazaz A. Farooque (17541303) Qamar U. Zaman (8060156) Farhat Abbas (5480) Mathieu F. Bilodeau (17542110) |
| author2_role | author author author author author |
| author_facet | Usman Ali (6586886) Travis J. Esau (17541300) Aitazaz A. Farooque (17541303) Qamar U. Zaman (8060156) Farhat Abbas (5480) Mathieu F. Bilodeau (17542110) |
| author_role | author |
| dc.creator.none.fl_str_mv | Usman Ali (6586886) Travis J. Esau (17541300) Aitazaz A. Farooque (17541303) Qamar U. Zaman (8060156) Farhat Abbas (5480) Mathieu F. Bilodeau (17542110) |
| dc.date.none.fl_str_mv | 2022-06-03T03:00:00Z |
| dc.identifier.none.fl_str_mv | 10.3390/ijgi11060333 |
| dc.relation.none.fl_str_mv | https://figshare.com/articles/journal_contribution/Limiting_the_Collection_of_Ground_Truth_Data_for_Land_Use_and_Land_Cover_Maps_with_Machine_Learning_Algorithms/24717546 |
| dc.rights.none.fl_str_mv | CC BY 4.0 info:eu-repo/semantics/openAccess |
| dc.subject.none.fl_str_mv | Engineering Geomatic engineering Information and computing sciences Data management and data science Machine learning remote sensing indices machine learning ground truth data LULC mapping satellite imagery |
| dc.title.none.fl_str_mv | Limiting the Collection of Ground Truth Data for Land Use and Land Cover Maps with Machine Learning Algorithms |
| dc.type.none.fl_str_mv | Text Journal contribution info:eu-repo/semantics/publishedVersion text contribution to journal |
| description | <p dir="ltr">Land use and land cover (LULC) classification maps help understand the state and trends of agricultural production and provide insights for applications in environmental monitoring. One of the major downfalls of the LULC technique is inherently linked to its need for ground truth data to cross-validate maps. This paper aimed at evaluating the efficiency of machine learning (ML) in limiting the use of ground truth data for LULC maps. This was accomplished by (1) extracting reliable LULC information from Sentinel-2 and Landsat-8 s images, (2) generating remote sensing indices used to train ML algorithms, and (3) comparing the results with ground truth data. The remote sensing indices that were tested include the difference vegetation index (DVI), the normalized difference vegetation index (NDVI), the normalized built-up index (NDBI), the urban index (UI), and the normalized bare land index (NBLI). Extracted vegetation indices were evaluated on three ML algorithms, namely, random forest (RF), k-nearest neighbour (K-NN), and k dimensional-tree (KD-Tree). The accuracy of these algorithms was assessed with standard statistical measures and ground truth data randomly collected in Prince Edward Island, Canada. Results showed that high kappa coefficient values were achieved by K-NN (82% and 74%), KD-Tree (80% and 78%), and RF (83% and 73%) for Sentinel-2A and Landsat-8 imagery, respectively. RF was a better classifier than K-NN and KD-Tree and had the highest overall accuracy with Sentinel-2A satellite images (92%). This approach provides the basis for limiting the collection of ground truth data and thus reduces the labour cost, time, and resources needed to collect ground truth data for LULC maps.</p><h2>Other Information</h2><p dir="ltr">Published in: ISPRS International Journal of Geo-Information<br>License: <a href="https://creativecommons.org/licenses/by/4.0/" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.3390/ijgi11060333" target="_blank">https://dx.doi.org/10.3390/ijgi11060333</a></p><p dir="ltr">Disclaimer: The University of Doha for Science and Technology replaced the now-former College of the North Atlantic-Qatar after an Amiri decision in 2022. UDST has become and first national applied University in Qatar; it is also second national University in the country.</p> |
| eu_rights_str_mv | openAccess |
| id | Manara2_ca2be42e50c829c8c6dd0a729f317222 |
| identifier_str_mv | 10.3390/ijgi11060333 |
| network_acronym_str | Manara2 |
| network_name_str | Manara2 |
| oai_identifier_str | oai:figshare.com:article/24717546 |
| publishDate | 2022 |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| rights_invalid_str_mv | CC BY 4.0 |
| spelling | Limiting the Collection of Ground Truth Data for Land Use and Land Cover Maps with Machine Learning AlgorithmsUsman Ali (6586886)Travis J. Esau (17541300)Aitazaz A. Farooque (17541303)Qamar U. Zaman (8060156)Farhat Abbas (5480)Mathieu F. Bilodeau (17542110)EngineeringGeomatic engineeringInformation and computing sciencesData management and data scienceMachine learningremote sensing indicesmachine learningground truth dataLULC mappingsatellite imagery<p dir="ltr">Land use and land cover (LULC) classification maps help understand the state and trends of agricultural production and provide insights for applications in environmental monitoring. One of the major downfalls of the LULC technique is inherently linked to its need for ground truth data to cross-validate maps. This paper aimed at evaluating the efficiency of machine learning (ML) in limiting the use of ground truth data for LULC maps. This was accomplished by (1) extracting reliable LULC information from Sentinel-2 and Landsat-8 s images, (2) generating remote sensing indices used to train ML algorithms, and (3) comparing the results with ground truth data. The remote sensing indices that were tested include the difference vegetation index (DVI), the normalized difference vegetation index (NDVI), the normalized built-up index (NDBI), the urban index (UI), and the normalized bare land index (NBLI). Extracted vegetation indices were evaluated on three ML algorithms, namely, random forest (RF), k-nearest neighbour (K-NN), and k dimensional-tree (KD-Tree). The accuracy of these algorithms was assessed with standard statistical measures and ground truth data randomly collected in Prince Edward Island, Canada. Results showed that high kappa coefficient values were achieved by K-NN (82% and 74%), KD-Tree (80% and 78%), and RF (83% and 73%) for Sentinel-2A and Landsat-8 imagery, respectively. RF was a better classifier than K-NN and KD-Tree and had the highest overall accuracy with Sentinel-2A satellite images (92%). This approach provides the basis for limiting the collection of ground truth data and thus reduces the labour cost, time, and resources needed to collect ground truth data for LULC maps.</p><h2>Other Information</h2><p dir="ltr">Published in: ISPRS International Journal of Geo-Information<br>License: <a href="https://creativecommons.org/licenses/by/4.0/" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.3390/ijgi11060333" target="_blank">https://dx.doi.org/10.3390/ijgi11060333</a></p><p dir="ltr">Disclaimer: The University of Doha for Science and Technology replaced the now-former College of the North Atlantic-Qatar after an Amiri decision in 2022. UDST has become and first national applied University in Qatar; it is also second national University in the country.</p>2022-06-03T03:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.3390/ijgi11060333https://figshare.com/articles/journal_contribution/Limiting_the_Collection_of_Ground_Truth_Data_for_Land_Use_and_Land_Cover_Maps_with_Machine_Learning_Algorithms/24717546CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/247175462022-06-03T03:00:00Z |
| spellingShingle | Limiting the Collection of Ground Truth Data for Land Use and Land Cover Maps with Machine Learning Algorithms Usman Ali (6586886) Engineering Geomatic engineering Information and computing sciences Data management and data science Machine learning remote sensing indices machine learning ground truth data LULC mapping satellite imagery |
| status_str | publishedVersion |
| title | Limiting the Collection of Ground Truth Data for Land Use and Land Cover Maps with Machine Learning Algorithms |
| title_full | Limiting the Collection of Ground Truth Data for Land Use and Land Cover Maps with Machine Learning Algorithms |
| title_fullStr | Limiting the Collection of Ground Truth Data for Land Use and Land Cover Maps with Machine Learning Algorithms |
| title_full_unstemmed | Limiting the Collection of Ground Truth Data for Land Use and Land Cover Maps with Machine Learning Algorithms |
| title_short | Limiting the Collection of Ground Truth Data for Land Use and Land Cover Maps with Machine Learning Algorithms |
| title_sort | Limiting the Collection of Ground Truth Data for Land Use and Land Cover Maps with Machine Learning Algorithms |
| topic | Engineering Geomatic engineering Information and computing sciences Data management and data science Machine learning remote sensing indices machine learning ground truth data LULC mapping satellite imagery |