A Planted Forest Mapping Method Based on Long-Term Change Trend Features Derived from Dense Landsat Time Series in an Ecological Restoration Region
Planted forests provide a variety of meaningful ecological functions and services, which is a major approach for ecological restoration, especially in arid areas. However, mapping planted forests with remote-sensed data remains challenging due to the similarities in canopy spectral and structure cha...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-02-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/4/961 |
| _version_ | 1827652839932952576 |
|---|---|
| author | Yuanyuan Meng Caiyong Wei Yanpei Guo Zhiyao Tang |
| author_facet | Yuanyuan Meng Caiyong Wei Yanpei Guo Zhiyao Tang |
| author_sort | Yuanyuan Meng |
| collection | DOAJ |
| description | Planted forests provide a variety of meaningful ecological functions and services, which is a major approach for ecological restoration, especially in arid areas. However, mapping planted forests with remote-sensed data remains challenging due to the similarities in canopy spectral and structure characteristics and associated phenology features between planted forests and other vegetation types. In this study, taking advantage of the Google Earth Engine (GEE) platform and taking the Ningxia Hui Autonomous Region in northwestern China as an example, we developed an approach to map planted forests in an arid region by applying long-term features of the NDVI derived from dense Landsat time series. Our land cover map achieved a satisfactory accuracy and relatively low uncertainty, with an overall accuracy of 93.65% and a kappa value of 0.92. Specifically, the producer (PA) and user accuracies (UA) were 92.48% and 91.79% for the planted forest class, and 93.88% and 95.83% for the natural forest class, respectively. The total planted forest area was estimated as 3608.72 km<sup>2</sup> in 2020, accounting for 20.60% of the study area. The proposed mapping approach can facilitate assessment of the restoration effects of ecological engineering and research on ecosystem services and stability of planted forests. |
| first_indexed | 2024-03-09T21:07:48Z |
| format | Article |
| id | doaj.art-0dedd9d3be144e1790664e74fc681308 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T21:07:48Z |
| publishDate | 2022-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-0dedd9d3be144e1790664e74fc6813082023-11-23T21:54:46ZengMDPI AGRemote Sensing2072-42922022-02-0114496110.3390/rs14040961A Planted Forest Mapping Method Based on Long-Term Change Trend Features Derived from Dense Landsat Time Series in an Ecological Restoration RegionYuanyuan Meng0Caiyong Wei1Yanpei Guo2Zhiyao Tang3Institute of Ecology, College of Urban and Environmental Sciences and Key Laboratory for Earth Surface Processes, Peking University, Beijing 100871, ChinaSchool of Information Engineering, China University of Geosciences, Beijing 100083, ChinaInstitute of Ecology, College of Urban and Environmental Sciences and Key Laboratory for Earth Surface Processes, Peking University, Beijing 100871, ChinaInstitute of Ecology, College of Urban and Environmental Sciences and Key Laboratory for Earth Surface Processes, Peking University, Beijing 100871, ChinaPlanted forests provide a variety of meaningful ecological functions and services, which is a major approach for ecological restoration, especially in arid areas. However, mapping planted forests with remote-sensed data remains challenging due to the similarities in canopy spectral and structure characteristics and associated phenology features between planted forests and other vegetation types. In this study, taking advantage of the Google Earth Engine (GEE) platform and taking the Ningxia Hui Autonomous Region in northwestern China as an example, we developed an approach to map planted forests in an arid region by applying long-term features of the NDVI derived from dense Landsat time series. Our land cover map achieved a satisfactory accuracy and relatively low uncertainty, with an overall accuracy of 93.65% and a kappa value of 0.92. Specifically, the producer (PA) and user accuracies (UA) were 92.48% and 91.79% for the planted forest class, and 93.88% and 95.83% for the natural forest class, respectively. The total planted forest area was estimated as 3608.72 km<sup>2</sup> in 2020, accounting for 20.60% of the study area. The proposed mapping approach can facilitate assessment of the restoration effects of ecological engineering and research on ecosystem services and stability of planted forests.https://www.mdpi.com/2072-4292/14/4/961planted forestslong-term change trend featuresLandsat time seriesGoogle Earth Enginerandom forestNDVI |
| spellingShingle | Yuanyuan Meng Caiyong Wei Yanpei Guo Zhiyao Tang A Planted Forest Mapping Method Based on Long-Term Change Trend Features Derived from Dense Landsat Time Series in an Ecological Restoration Region Remote Sensing planted forests long-term change trend features Landsat time series Google Earth Engine random forest NDVI |
| title | A Planted Forest Mapping Method Based on Long-Term Change Trend Features Derived from Dense Landsat Time Series in an Ecological Restoration Region |
| title_full | A Planted Forest Mapping Method Based on Long-Term Change Trend Features Derived from Dense Landsat Time Series in an Ecological Restoration Region |
| title_fullStr | A Planted Forest Mapping Method Based on Long-Term Change Trend Features Derived from Dense Landsat Time Series in an Ecological Restoration Region |
| title_full_unstemmed | A Planted Forest Mapping Method Based on Long-Term Change Trend Features Derived from Dense Landsat Time Series in an Ecological Restoration Region |
| title_short | A Planted Forest Mapping Method Based on Long-Term Change Trend Features Derived from Dense Landsat Time Series in an Ecological Restoration Region |
| title_sort | planted forest mapping method based on long term change trend features derived from dense landsat time series in an ecological restoration region |
| topic | planted forests long-term change trend features Landsat time series Google Earth Engine random forest NDVI |
| url | https://www.mdpi.com/2072-4292/14/4/961 |
| work_keys_str_mv | AT yuanyuanmeng aplantedforestmappingmethodbasedonlongtermchangetrendfeaturesderivedfromdenselandsattimeseriesinanecologicalrestorationregion AT caiyongwei aplantedforestmappingmethodbasedonlongtermchangetrendfeaturesderivedfromdenselandsattimeseriesinanecologicalrestorationregion AT yanpeiguo aplantedforestmappingmethodbasedonlongtermchangetrendfeaturesderivedfromdenselandsattimeseriesinanecologicalrestorationregion AT zhiyaotang aplantedforestmappingmethodbasedonlongtermchangetrendfeaturesderivedfromdenselandsattimeseriesinanecologicalrestorationregion AT yuanyuanmeng plantedforestmappingmethodbasedonlongtermchangetrendfeaturesderivedfromdenselandsattimeseriesinanecologicalrestorationregion AT caiyongwei plantedforestmappingmethodbasedonlongtermchangetrendfeaturesderivedfromdenselandsattimeseriesinanecologicalrestorationregion AT yanpeiguo plantedforestmappingmethodbasedonlongtermchangetrendfeaturesderivedfromdenselandsattimeseriesinanecologicalrestorationregion AT zhiyaotang plantedforestmappingmethodbasedonlongtermchangetrendfeaturesderivedfromdenselandsattimeseriesinanecologicalrestorationregion |