Regional Mapping and Spatial Distribution Analysis of Canopy Palms in an Amazon Forest Using Deep Learning and VHR Images
Mapping plant species at the regional scale to provide information for ecologists and forest managers is a challenge for the remote sensing community. Here, we use a deep learning algorithm called U-net and very high-resolution multispectral images (0.5 m) from GeoEye satellite to identify, segment...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-07-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/12/14/2225 |
| _version_ | 1827713265516412928 |
|---|---|
| author | Fabien H. Wagner Ricardo Dalagnol Ximena Tagle Casapia Annia S. Streher Oliver L. Phillips Emanuel Gloor Luiz E. O. C. Aragão |
| author_facet | Fabien H. Wagner Ricardo Dalagnol Ximena Tagle Casapia Annia S. Streher Oliver L. Phillips Emanuel Gloor Luiz E. O. C. Aragão |
| author_sort | Fabien H. Wagner |
| collection | DOAJ |
| description | Mapping plant species at the regional scale to provide information for ecologists and forest managers is a challenge for the remote sensing community. Here, we use a deep learning algorithm called U-net and very high-resolution multispectral images (0.5 m) from GeoEye satellite to identify, segment and map canopy palms over ∼3000 km<inline-formula> <math display="inline"> <semantics> <msup> <mrow></mrow> <mn>2</mn> </msup> </semantics> </math> </inline-formula> of Amazonian forest. The map was used to analyse the spatial distribution of canopy palm trees and its relation to human disturbance and edaphic conditions. The overall accuracy of the map was 95.5% and the F1-score was 0.7. Canopy palm trees covered 6.4% of the forest canopy and were distributed in more than two million patches that can represent one or more individuals. The density of canopy palms is affected by human disturbance. The post-disturbance density in secondary forests seems to be related to the type of disturbance, being higher in abandoned pasture areas and lower in forests that have been cut once and abandoned. Additionally, analysis of palm trees’ distribution shows that their abundance is controlled naturally by local soil water content, avoiding both flooded and waterlogged areas near rivers and dry areas on the top of the hills. They show two preferential habitats, in the low elevation above the large rivers, and in the slope directly below the hill tops. Overall, their distribution over the region indicates a relatively pristine landscape, albeit within a forest that is critically endangered because of its location between two deforestation fronts and because of illegal cutting. New tree species distribution data, such as the map of all adult canopy palms produced in this work, are urgently needed to support Amazon species inventory and to understand their distribution and diversity. |
| first_indexed | 2024-03-10T18:32:36Z |
| format | Article |
| id | doaj.art-63621f81c972452592c5350a641e89d7 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T18:32:36Z |
| publishDate | 2020-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-63621f81c972452592c5350a641e89d72023-11-20T06:30:27ZengMDPI AGRemote Sensing2072-42922020-07-011214222510.3390/rs12142225Regional Mapping and Spatial Distribution Analysis of Canopy Palms in an Amazon Forest Using Deep Learning and VHR ImagesFabien H. Wagner0Ricardo Dalagnol1Ximena Tagle Casapia2Annia S. Streher3Oliver L. Phillips4Emanuel Gloor5Luiz E. O. C. Aragão6GeoProcessing Division, Foundation for Science, Technology and Space Applications—FUNCATE, São José dos Campos SP 12210-131, BrazilRemote Sensing Division, National Institute for Space Research—INPE, São José dos Campos SP 12227-010, BrazilProbosques, Instituto de Investigaciones de la Amazonía Peruana—IIAP, Av. A. José Quiñones km 2.5, Iquitos AP 784, PeruRemote Sensing Division, National Institute for Space Research—INPE, São José dos Campos SP 12227-010, BrazilSchool of Geography, University of Leeds, Leeds LS2 9JT, UKSchool of Geography, University of Leeds, Leeds LS2 9JT, UKRemote Sensing Division, National Institute for Space Research—INPE, São José dos Campos SP 12227-010, BrazilMapping plant species at the regional scale to provide information for ecologists and forest managers is a challenge for the remote sensing community. Here, we use a deep learning algorithm called U-net and very high-resolution multispectral images (0.5 m) from GeoEye satellite to identify, segment and map canopy palms over ∼3000 km<inline-formula> <math display="inline"> <semantics> <msup> <mrow></mrow> <mn>2</mn> </msup> </semantics> </math> </inline-formula> of Amazonian forest. The map was used to analyse the spatial distribution of canopy palm trees and its relation to human disturbance and edaphic conditions. The overall accuracy of the map was 95.5% and the F1-score was 0.7. Canopy palm trees covered 6.4% of the forest canopy and were distributed in more than two million patches that can represent one or more individuals. The density of canopy palms is affected by human disturbance. The post-disturbance density in secondary forests seems to be related to the type of disturbance, being higher in abandoned pasture areas and lower in forests that have been cut once and abandoned. Additionally, analysis of palm trees’ distribution shows that their abundance is controlled naturally by local soil water content, avoiding both flooded and waterlogged areas near rivers and dry areas on the top of the hills. They show two preferential habitats, in the low elevation above the large rivers, and in the slope directly below the hill tops. Overall, their distribution over the region indicates a relatively pristine landscape, albeit within a forest that is critically endangered because of its location between two deforestation fronts and because of illegal cutting. New tree species distribution data, such as the map of all adult canopy palms produced in this work, are urgently needed to support Amazon species inventory and to understand their distribution and diversity.https://www.mdpi.com/2072-4292/12/14/2225U-netSemantic segmentationdeep learningspecies distribution, very high resolution images |
| spellingShingle | Fabien H. Wagner Ricardo Dalagnol Ximena Tagle Casapia Annia S. Streher Oliver L. Phillips Emanuel Gloor Luiz E. O. C. Aragão Regional Mapping and Spatial Distribution Analysis of Canopy Palms in an Amazon Forest Using Deep Learning and VHR Images Remote Sensing U-net Semantic segmentation deep learning species distribution, very high resolution images |
| title | Regional Mapping and Spatial Distribution Analysis of Canopy Palms in an Amazon Forest Using Deep Learning and VHR Images |
| title_full | Regional Mapping and Spatial Distribution Analysis of Canopy Palms in an Amazon Forest Using Deep Learning and VHR Images |
| title_fullStr | Regional Mapping and Spatial Distribution Analysis of Canopy Palms in an Amazon Forest Using Deep Learning and VHR Images |
| title_full_unstemmed | Regional Mapping and Spatial Distribution Analysis of Canopy Palms in an Amazon Forest Using Deep Learning and VHR Images |
| title_short | Regional Mapping and Spatial Distribution Analysis of Canopy Palms in an Amazon Forest Using Deep Learning and VHR Images |
| title_sort | regional mapping and spatial distribution analysis of canopy palms in an amazon forest using deep learning and vhr images |
| topic | U-net Semantic segmentation deep learning species distribution, very high resolution images |
| url | https://www.mdpi.com/2072-4292/12/14/2225 |
| work_keys_str_mv | AT fabienhwagner regionalmappingandspatialdistributionanalysisofcanopypalmsinanamazonforestusingdeeplearningandvhrimages AT ricardodalagnol regionalmappingandspatialdistributionanalysisofcanopypalmsinanamazonforestusingdeeplearningandvhrimages AT ximenataglecasapia regionalmappingandspatialdistributionanalysisofcanopypalmsinanamazonforestusingdeeplearningandvhrimages AT anniasstreher regionalmappingandspatialdistributionanalysisofcanopypalmsinanamazonforestusingdeeplearningandvhrimages AT oliverlphillips regionalmappingandspatialdistributionanalysisofcanopypalmsinanamazonforestusingdeeplearningandvhrimages AT emanuelgloor regionalmappingandspatialdistributionanalysisofcanopypalmsinanamazonforestusingdeeplearningandvhrimages AT luizeocaragao regionalmappingandspatialdistributionanalysisofcanopypalmsinanamazonforestusingdeeplearningandvhrimages |