SlideShare une entreprise Scribd logo
1  sur  24
Using European Sentinel-2A to update
the Copernicus High-Resolution Layer
Imperviousness
Antoine Lefebvre1
, Christophe Sannier2
(1) CNES, UMR IRISA, Rennes, France
(2) SIRS SAS, Villeneuve d’Ascq, France
CONTEXT – Copernicus High Resolution Layers
• 5 Layers produced for 2012:
– Forest
– Grassland
– Wetland
– Permanent water bodies
– Imperviousness
• HRL Imperviousness, main specifications
– Resolution : 20x20m ; 100x100m
– Soil sealing degree : 0 – 100%
• Seamless European-wide coverage over 39
EEA countries
CONTEXT – Sentinel-2
• Launched on 23 June 2015
• 13 multi-spectral bands
– High Spatial Resolution :
• up to 10m
• Spectral capabilities :
– 3 bands in the red-edge
– 2 bands in the SWIR
• Repetitiveness :
– up to 5 days (with constellation)
• None provides a cloud-free coverage
• Incomplete time series (gaps)
– How to get an homogeneous result over Europe ?
– How to do it in an automatic and operational way ?
t1 t2
t3 t4
KEY IDEA – Exploiting Sezntinel-2
Repetitiveness
• Sum of overlays provides a cloud-free coverage
t1 t2
t3 t4 Sum of overlays
KEY IDEA – Exploiting Sezntinel-2
Repetitiveness
• Sum of overlays provides a cloud-free coverage
• Combination of single scene classification with data fusion technique
t1 t2
t3 t4 Sum of overlays
KEY IDEA – Exploiting Sezntinel-2
Repetitiveness
• 2 Former Urban Areas
– Prague, Czech Republic
• 6,900 km2
– Rennes, France
• 2,500 km2
• Sentinel-2 and Landsat-8
images
METHOD – Study Areas
• Input dataset
– All spectral bands
– Pantex
• Based on blue band (Sentinel-2)
• Based on Panchromatic band
(Landsat-8)
• Cloud mask extraction
– Sentinel-2: semi-automatic
– Landsat-8: F-mask
S2 PANTEX
S2 Cloud mask
S2 image
S2 image
METHOD – Data Preparation
• Sampling
– Automatic sampling on Copernicus High Resolution Layer (2012)
• 20x20m
• Range from 1 to 100%
• Available on all 39 EEA countries
• Classifier
– Random Forest
• Uncertainty
– Kappa
METHOD – Single Scene Classification
METHOD – Data Fusion
• Dempster-Shafer Theory (DST):
– Dealing with imprecision and uncertainty
• Kappa computed on each individual scene
• Associative rule:
– Combination of numerous separate information
• Sentinel-2, Landsat-8, … and some more if available
1. Data Preparation
METHOD – Processing Chain
2. Single Scene
Classification
METHOD – Processing Chain
3. Multi-temporal
fusion
METHOD – Processing Chain
METHOD – Processing Chain
4. Multi-source
fusion
RESULTS – Variable Importance
# Rank
1.Texture
2.NIR
3.Blue
4.SWIR
RESULTS - Uncertainty
Uncertainty
(1-Kappa)
decreases with
data fusion
RESULTS - Benefits of multi-temporal data
Limitation of
commision errors
Urban areas
Agricultural areas
RESULTS - Benefits of multi-source data
Geometric
accuracy
enhancement
Urban areas
Imprecise edges
• Comparison: 2015 classifications and 2012 HRL Imperviousness
• Validation strategy (Built-Up / Non Built-Up)
– 400 randomly selected pixels and stratified selection
• 200 points in the change areas
• 200 points in the unchanged areas
– To prevent problems due to geometrical accuracy
• selected sample is surrounded by the same thematic class in a 3x3 window.
– Interpretation of samples is performed manually
Update Copernicus HRL Imperviousness
Update Copernicus HRL Imperviousness
Update Copernicus HRL Imperviousness
Update Copernicus HRL Imperviousness
2010 Google Earth 2015 Sentinel-2 2012-2015
HRL
Change Map
2015
HRL
Imperviousness
Update Copernicus HRL Imperviousness
2011 Google Earth 2015 Sentinel-2 2012-2015
HRL
Change Map
2015
HRL
Imperviousness
CONCLUSION
• Simple method to process Sentinel-2 time-series
• Overcome missing data
• Provide cloud-free coverage
• Sentinel-2 information
• Spectral resolution: cloud extraction, classification
• Spatial resolution: texture features
• Temporal resolution: repetitiveness
• Efficiency & Operationality
• Limited interaction with the user
• Automatic sampling (can be applied on the all 39 EEA countries)
• No image selection
• Good accuracy
• More overlays, less uncertainty, better accuracy
• Multi-source ability
• Complementarity with other sensors (Landsat-8 here but also, possible with any others)

Contenu connexe

En vedette

Openaccess badges à découper pour support carte
Openaccess badges à découper pour support carteOpenaccess badges à découper pour support carte
Openaccess badges à découper pour support carteAlain Marois
 
Outils pour la recherche documentaire en psychologie et sciences cognitives -...
Outils pour la recherche documentaire en psychologie et sciences cognitives -...Outils pour la recherche documentaire en psychologie et sciences cognitives -...
Outils pour la recherche documentaire en psychologie et sciences cognitives -...Alain Marois
 
Демоверсии ЕГЭ-2016: русский язык
Демоверсии ЕГЭ-2016: русский языкДемоверсии ЕГЭ-2016: русский язык
Демоверсии ЕГЭ-2016: русский языкNewtonew
 
Zotero avancé - juin 2016
Zotero avancé - juin 2016Zotero avancé - juin 2016
Zotero avancé - juin 2016Alain Marois
 

En vedette (6)

0944388579
09443885790944388579
0944388579
 
Openaccess badges à découper pour support carte
Openaccess badges à découper pour support carteOpenaccess badges à découper pour support carte
Openaccess badges à découper pour support carte
 
Outils pour la recherche documentaire en psychologie et sciences cognitives -...
Outils pour la recherche documentaire en psychologie et sciences cognitives -...Outils pour la recherche documentaire en psychologie et sciences cognitives -...
Outils pour la recherche documentaire en psychologie et sciences cognitives -...
 
DXN CULTURA DXN HOLDINGS GLOBAL DXN INTERNATIONAL.GANE DINERO WHATSAPP CEL ...
DXN  CULTURA DXN HOLDINGS GLOBAL DXN INTERNATIONAL.GANE DINERO  WHATSAPP CEL ...DXN  CULTURA DXN HOLDINGS GLOBAL DXN INTERNATIONAL.GANE DINERO  WHATSAPP CEL ...
DXN CULTURA DXN HOLDINGS GLOBAL DXN INTERNATIONAL.GANE DINERO WHATSAPP CEL ...
 
Демоверсии ЕГЭ-2016: русский язык
Демоверсии ЕГЭ-2016: русский языкДемоверсии ЕГЭ-2016: русский язык
Демоверсии ЕГЭ-2016: русский язык
 
Zotero avancé - juin 2016
Zotero avancé - juin 2016Zotero avancé - juin 2016
Zotero avancé - juin 2016
 

Similaire à LPS16_16_9_antoine

e-SOTER Regional pilot platform as EU contribution to a Global Soil Observing...
e-SOTER Regional pilot platform as EU contribution to a Global Soil Observing...e-SOTER Regional pilot platform as EU contribution to a Global Soil Observing...
e-SOTER Regional pilot platform as EU contribution to a Global Soil Observing...FAO
 
BELSPO 2016/10/25 : Monitoring urban areas with Sentinel_2
BELSPO 2016/10/25 : Monitoring urban areas with Sentinel_2BELSPO 2016/10/25 : Monitoring urban areas with Sentinel_2
BELSPO 2016/10/25 : Monitoring urban areas with Sentinel_2Antoine Lefebvre
 
Grassland Mowing Events Detection
Grassland Mowing Events DetectionGrassland Mowing Events Detection
Grassland Mowing Events DetectionENVISION H2020
 
The performance of portable mid-infrared spectroscopy for the prediction of s...
The performance of portable mid-infrared spectroscopy for the prediction of s...The performance of portable mid-infrared spectroscopy for the prediction of s...
The performance of portable mid-infrared spectroscopy for the prediction of s...ExternalEvents
 
WaPOR version 3 - H Pelgrum - eLeaf - 05 May 2023.pdf
WaPOR version 3 - H Pelgrum - eLeaf - 05 May 2023.pdfWaPOR version 3 - H Pelgrum - eLeaf - 05 May 2023.pdf
WaPOR version 3 - H Pelgrum - eLeaf - 05 May 2023.pdfWaPOR
 
4. lecture 3 data capturing techniques - total station and gps
4. lecture 3   data capturing techniques - total station and gps4. lecture 3   data capturing techniques - total station and gps
4. lecture 3 data capturing techniques - total station and gpsFenTaHun6
 
4. lecture 3 data capturing techniques - total station and gps
4. lecture 3   data capturing techniques - total station and gps4. lecture 3   data capturing techniques - total station and gps
4. lecture 3 data capturing techniques - total station and gpsFenTaHun6
 
BAUP_IGARSS_2011.pdf
BAUP_IGARSS_2011.pdfBAUP_IGARSS_2011.pdf
BAUP_IGARSS_2011.pdfgrssieee
 
Advances in Agricultural remote sensings
Advances in Agricultural remote sensingsAdvances in Agricultural remote sensings
Advances in Agricultural remote sensingsAyanDas644783
 
Environmental Remote Sensing
 Environmental Remote Sensing  Environmental Remote Sensing
Environmental Remote Sensing Ghassan Hadi
 
Cultivated Crop Type Maps
Cultivated Crop Type Maps Cultivated Crop Type Maps
Cultivated Crop Type Maps ENVISION H2020
 
Analytics on Vegetation & Soil Index time-series and DataCube End Point service
Analytics on Vegetation & Soil Index time-series and DataCube End Point serviceAnalytics on Vegetation & Soil Index time-series and DataCube End Point service
Analytics on Vegetation & Soil Index time-series and DataCube End Point serviceENVISION H2020
 
03 Landsat Legacy.pptx
03 Landsat Legacy.pptx03 Landsat Legacy.pptx
03 Landsat Legacy.pptxHrudayKumar8
 
Development of a soil carbon map for the United Republic of Tanzania
Development of a soil carbon map for the United Republic of TanzaniaDevelopment of a soil carbon map for the United Republic of Tanzania
Development of a soil carbon map for the United Republic of TanzaniaExternalEvents
 
Landmap CETIS 2012
Landmap CETIS 2012Landmap CETIS 2012
Landmap CETIS 2012Bharti Gupta
 
IGARSS_2011_GALLOZA.pptx
IGARSS_2011_GALLOZA.pptxIGARSS_2011_GALLOZA.pptx
IGARSS_2011_GALLOZA.pptxgrssieee
 
7. Global Forest Watch & Monitoring Forests Using Remote Sensing
7. Global Forest Watch & Monitoring Forests Using Remote Sensing7. Global Forest Watch & Monitoring Forests Using Remote Sensing
7. Global Forest Watch & Monitoring Forests Using Remote SensingENPI FLEG
 

Similaire à LPS16_16_9_antoine (20)

e-SOTER Regional pilot platform as EU contribution to a Global Soil Observing...
e-SOTER Regional pilot platform as EU contribution to a Global Soil Observing...e-SOTER Regional pilot platform as EU contribution to a Global Soil Observing...
e-SOTER Regional pilot platform as EU contribution to a Global Soil Observing...
 
BELSPO 2016/10/25 : Monitoring urban areas with Sentinel_2
BELSPO 2016/10/25 : Monitoring urban areas with Sentinel_2BELSPO 2016/10/25 : Monitoring urban areas with Sentinel_2
BELSPO 2016/10/25 : Monitoring urban areas with Sentinel_2
 
Grassland Mowing Events Detection
Grassland Mowing Events DetectionGrassland Mowing Events Detection
Grassland Mowing Events Detection
 
The performance of portable mid-infrared spectroscopy for the prediction of s...
The performance of portable mid-infrared spectroscopy for the prediction of s...The performance of portable mid-infrared spectroscopy for the prediction of s...
The performance of portable mid-infrared spectroscopy for the prediction of s...
 
WaPOR version 3 - H Pelgrum - eLeaf - 05 May 2023.pdf
WaPOR version 3 - H Pelgrum - eLeaf - 05 May 2023.pdfWaPOR version 3 - H Pelgrum - eLeaf - 05 May 2023.pdf
WaPOR version 3 - H Pelgrum - eLeaf - 05 May 2023.pdf
 
4. lecture 3 data capturing techniques - total station and gps
4. lecture 3   data capturing techniques - total station and gps4. lecture 3   data capturing techniques - total station and gps
4. lecture 3 data capturing techniques - total station and gps
 
4. lecture 3 data capturing techniques - total station and gps
4. lecture 3   data capturing techniques - total station and gps4. lecture 3   data capturing techniques - total station and gps
4. lecture 3 data capturing techniques - total station and gps
 
BAUP_IGARSS_2011.pdf
BAUP_IGARSS_2011.pdfBAUP_IGARSS_2011.pdf
BAUP_IGARSS_2011.pdf
 
Advances in Agricultural remote sensings
Advances in Agricultural remote sensingsAdvances in Agricultural remote sensings
Advances in Agricultural remote sensings
 
Environmental Remote Sensing
 Environmental Remote Sensing  Environmental Remote Sensing
Environmental Remote Sensing
 
842 manobianco
842 manobianco842 manobianco
842 manobianco
 
Cultivated Crop Type Maps
Cultivated Crop Type Maps Cultivated Crop Type Maps
Cultivated Crop Type Maps
 
Analytics on Vegetation & Soil Index time-series and DataCube End Point service
Analytics on Vegetation & Soil Index time-series and DataCube End Point serviceAnalytics on Vegetation & Soil Index time-series and DataCube End Point service
Analytics on Vegetation & Soil Index time-series and DataCube End Point service
 
03 Landsat Legacy.pptx
03 Landsat Legacy.pptx03 Landsat Legacy.pptx
03 Landsat Legacy.pptx
 
Development of a soil carbon map for the United Republic of Tanzania
Development of a soil carbon map for the United Republic of TanzaniaDevelopment of a soil carbon map for the United Republic of Tanzania
Development of a soil carbon map for the United Republic of Tanzania
 
Landmap CETIS 2012
Landmap CETIS 2012Landmap CETIS 2012
Landmap CETIS 2012
 
Earth Observation
Earth ObservationEarth Observation
Earth Observation
 
IGARSS_2011_GALLOZA.pptx
IGARSS_2011_GALLOZA.pptxIGARSS_2011_GALLOZA.pptx
IGARSS_2011_GALLOZA.pptx
 
7. Global Forest Watch & Monitoring Forests Using Remote Sensing
7. Global Forest Watch & Monitoring Forests Using Remote Sensing7. Global Forest Watch & Monitoring Forests Using Remote Sensing
7. Global Forest Watch & Monitoring Forests Using Remote Sensing
 
matdid473708.pdf
matdid473708.pdfmatdid473708.pdf
matdid473708.pdf
 

LPS16_16_9_antoine

  • 1. Using European Sentinel-2A to update the Copernicus High-Resolution Layer Imperviousness Antoine Lefebvre1 , Christophe Sannier2 (1) CNES, UMR IRISA, Rennes, France (2) SIRS SAS, Villeneuve d’Ascq, France
  • 2. CONTEXT – Copernicus High Resolution Layers • 5 Layers produced for 2012: – Forest – Grassland – Wetland – Permanent water bodies – Imperviousness • HRL Imperviousness, main specifications – Resolution : 20x20m ; 100x100m – Soil sealing degree : 0 – 100% • Seamless European-wide coverage over 39 EEA countries
  • 3. CONTEXT – Sentinel-2 • Launched on 23 June 2015 • 13 multi-spectral bands – High Spatial Resolution : • up to 10m • Spectral capabilities : – 3 bands in the red-edge – 2 bands in the SWIR • Repetitiveness : – up to 5 days (with constellation)
  • 4. • None provides a cloud-free coverage • Incomplete time series (gaps) – How to get an homogeneous result over Europe ? – How to do it in an automatic and operational way ? t1 t2 t3 t4 KEY IDEA – Exploiting Sezntinel-2 Repetitiveness
  • 5. • Sum of overlays provides a cloud-free coverage t1 t2 t3 t4 Sum of overlays KEY IDEA – Exploiting Sezntinel-2 Repetitiveness
  • 6. • Sum of overlays provides a cloud-free coverage • Combination of single scene classification with data fusion technique t1 t2 t3 t4 Sum of overlays KEY IDEA – Exploiting Sezntinel-2 Repetitiveness
  • 7. • 2 Former Urban Areas – Prague, Czech Republic • 6,900 km2 – Rennes, France • 2,500 km2 • Sentinel-2 and Landsat-8 images METHOD – Study Areas
  • 8. • Input dataset – All spectral bands – Pantex • Based on blue band (Sentinel-2) • Based on Panchromatic band (Landsat-8) • Cloud mask extraction – Sentinel-2: semi-automatic – Landsat-8: F-mask S2 PANTEX S2 Cloud mask S2 image S2 image METHOD – Data Preparation
  • 9. • Sampling – Automatic sampling on Copernicus High Resolution Layer (2012) • 20x20m • Range from 1 to 100% • Available on all 39 EEA countries • Classifier – Random Forest • Uncertainty – Kappa METHOD – Single Scene Classification
  • 10. METHOD – Data Fusion • Dempster-Shafer Theory (DST): – Dealing with imprecision and uncertainty • Kappa computed on each individual scene • Associative rule: – Combination of numerous separate information • Sentinel-2, Landsat-8, … and some more if available
  • 11. 1. Data Preparation METHOD – Processing Chain
  • 14. METHOD – Processing Chain 4. Multi-source fusion
  • 15. RESULTS – Variable Importance # Rank 1.Texture 2.NIR 3.Blue 4.SWIR
  • 17. RESULTS - Benefits of multi-temporal data Limitation of commision errors Urban areas Agricultural areas
  • 18. RESULTS - Benefits of multi-source data Geometric accuracy enhancement Urban areas Imprecise edges
  • 19. • Comparison: 2015 classifications and 2012 HRL Imperviousness • Validation strategy (Built-Up / Non Built-Up) – 400 randomly selected pixels and stratified selection • 200 points in the change areas • 200 points in the unchanged areas – To prevent problems due to geometrical accuracy • selected sample is surrounded by the same thematic class in a 3x3 window. – Interpretation of samples is performed manually Update Copernicus HRL Imperviousness
  • 20. Update Copernicus HRL Imperviousness
  • 21. Update Copernicus HRL Imperviousness
  • 22. Update Copernicus HRL Imperviousness 2010 Google Earth 2015 Sentinel-2 2012-2015 HRL Change Map 2015 HRL Imperviousness
  • 23. Update Copernicus HRL Imperviousness 2011 Google Earth 2015 Sentinel-2 2012-2015 HRL Change Map 2015 HRL Imperviousness
  • 24. CONCLUSION • Simple method to process Sentinel-2 time-series • Overcome missing data • Provide cloud-free coverage • Sentinel-2 information • Spectral resolution: cloud extraction, classification • Spatial resolution: texture features • Temporal resolution: repetitiveness • Efficiency & Operationality • Limited interaction with the user • Automatic sampling (can be applied on the all 39 EEA countries) • No image selection • Good accuracy • More overlays, less uncertainty, better accuracy • Multi-source ability • Complementarity with other sensors (Landsat-8 here but also, possible with any others)