wph - earth observation€¦ · wph earth observation – case study description 10 agriculture...
TRANSCRIPT
WPH - Earth Observation
1
Marek Morze
05 – 06 December 2018, Vienna, Austria
Earth Observation
2
OPERATIONAL SATELLITES = 1886
2 16 41
127
297
661
1995 2000 2005 2010 2015
30.04.2018
Earth Observation
3
Earth Observation
35%
Communications 43%
Technology development
11%
Navigation 7%
Space Science
4%
WPH Earth Observation – crucial goals
• Goals • Facilitation and improvement the mandatory statistical registers
• The usage of the EO data in official statistical production
• Support the upcoming Census 2021 and Agricultural Census
• Implementation other commitments of European Commission or United Nations
4
WPH Earth Observation
• Expectations • Identification and analysis of EO data sources for multiple
statistical themes product and development of an adequate Reference Methodological Framework for processing data
• Results • Final technical report: the evaluation of big data sources and
definition of possible statistical products from examined big data sources as well as associated with them the protection of privacy and confidentiality and other legal issues.
• Cooperation of 9 partners from 8 countries
5
WPH Earth Observation – Thematic tasks & Case studies
6
Agriculture
Build-up area
Land cover
Settlements, Enumeration Areas and Forestry
Crop recognition, mapping and monitoring
Monitoring of the off-season vegetation cover
Crop recognition with very high resolution aerial data
Implementing SDG indicator 11.7.1
Urban sprawl across urban areas in Europe
Combination of administrative and Earth Observation data to determine the quality of housing
Comparing «in-situ» and «remote-sensing» collection mode for land cover data
Land cover maps at very detailed scale
Update the INSPIRE Theme Statistical Units dataset and preventing forest fire
Case study 1
Case study 2
Case study 3
Case study 4
Case study 5
Case study 6
Case study 7
Case study 8
Case study 9
WPH Earth Observation – Activities of each case study
• For each of the case studies the following activities will be undertaken: • Statistical products description based on data sources and needs of
statistical data users; • Data access (ensuring continuity of data sources and statistical
information for longer time period); • Definition of business processes and derived metadata (auditable
steps including assurance of data security and confidentiality; ensuring data quality and its documentation);
• Quality assessment of the data; • Development of methodology for production of statistics; • IT infrastructures definition for data processing; • Treatment of legal issues (related to data access, processing and
output); • Pilot production of statistical data and assessment of quality
(including multi-purpose and multi-source aspects).
7
• Main goal • Crops mapping and area estimation
WPH Earth Observation – Case study description
8
Agriculture Crop recognition, mapping and monitoring Case study 1
spring barley winter barley corn cereal mixes
oat spring wheat
winter wheat spring triticale winter triticale winter rape rye
Satellite data
Administrative data • cadastral parcels vector
(LPIS) • information on crops
declared by farmers (ARMA) • agricultural plots borders
from General Geographic Geodatabase
Crops map
Machine learning
algorithms
Estimated area of crops [ha]
• Verification and improvement the accuracy of the crop recognition methodology (ESSnet 2016-2018)
• Crop recognition using long time series of Sentinel-1 data
• Assessment of the state of winter crops (overwintering) using Sentinel-2
• Testing machine learning algorithms
WPH Earth Observation – Case study description
9
Agriculture Crop recognition, mapping and monitoring Case study 1
WPH Earth Observation – Case study description
10
Agriculture Monitoring of the off-season vegetation cover Case study 2
• Main goal • Monitoring the off-season vegetation cover of
agricultural soils that gives important information on nutrients losses from fields to water bodies
• Proposed method would provide grounds for establishing an indicator on sustainable agriculture as land management practices closely relate to sustainability.
WPH Earth Observation – Case study description
11
Agriculture Crop recognition with very high resolution aerial data Case study 3
• Main goal • Use of the aerial photography with very high resolution (10-40
cm) to crop recognition in case of small size parcels
Small size parcels can not be recognized on images of 10 m resolution (Sentinel 1-2)
200 m
• Objectives • Implementation the UN-Habitat
methodology for the whole France
WPH Earth Observation – Case study description
12
Build-up area Implementing SDG indicator 11.7.1 Case study 4
• Bench marking this methodology with specifics data or concepts that are available in France or in Europe (French or European definition of cities, Sentinel 2, French Road maps layer)
• Promotion the results at the French level (CNIS), European level (Eurostat, UN-GGIM Europe), Global level (IAEG-SDG).
WPH Earth Observation – Case study description
13
Build-up area Urban sprawl across urban areas in Europe Case study 5
https://sourceable.net/true-costs-sprawl/
• Objectives • Characterization of urban sprawl (SDG 11.7.1) across
Urban areas in Europe by means of data-driven machine learning methods.
• Evaluation what extent can national
statistic offices benefit from Earth observation to monitor and report on the SGDs at local to national level
• Investigation the possibility of providing temporal continuity on the basis of multiple datasets provided by satellites such as MODIS and SENTINEL 2.
• Objectives • Exploration of the quality of urban living
based on EO data combined with administrative data
WPH Earth Observation – Case study description
14
Build-up area Combination of administrative and Earth Observation data to determine the quality of housing
Case study 6
• Presentation that a more comprehensive understanding can be developed through their combination rather than by analyzing only a single data source.
WPH Earth Observation – Case study description
15
Land cover Comparing «in-situ» and «remote-sensing» collection mode for land cover data
Case study 7
• TERUTI - French statistical area-frame survey on land cover and land use
• Since 2017, the administrative, geographical data and in-situ are used
OSO map (land cover maps at country scale using high resolution optical image time series which is based on supervised classification and uses existing databases as reference
data for training and validation.
70%
30%
Administrative data (LPIS) and geographical databases (i.e. BD FORET from National Geographic Institute – IGN)
In-situ by a surveyour everyyear
WPH Earth Observation – Case study description
16
Land cover Comparing «in-situ» and «remote-sensing» collection mode for land cover data
Case study 7
• Objectives
• Analysing the differences (frequency, reasons) between land cover information collected on a geo-located point in Teruti survey and LC information provided by the automatic classification of the same pixel in the OSO map ;
• Identifying land cover types which could be automatically classified by remote sensing with an adjustment of the classification used into the OSO process ;
• Identifying with a high confidence pixels which contains a high probability of land cover change in order to send a Teruti's surveyor to collect and verify the LC change on the ground.
• Objectives
• Land cover map at various scale by four bands aerial and satellite (Sentinel and LANDSAT) images based on 1st LUCAS (Land Use/Cover Area frame Survey) level legend.
• Machine learning algorithms will be used (i.e a segmentation algorithm grounded on CNN and Unet in order to recognize built-up artificial areas).
WPH Earth Observation – Case study description
17
Land cover Land cover maps at very detailed scale Case study 8
Aerial and satellite data Land cover map at various scale with legend:
Machine learning
algorithms A00 – Artificial land B00 – Cropland C00 – Woodland D00 – Shrubland E00 – Grassland F00 – Bare land and lichens/moss G00 – Water areas H00 – Wetlands
• Objectives
• to update the INSPIRE Theme Statistical Units dataset, namely the Settlements and Enumeration Areas.
WPH Earth Observation – Case study description
18
Settlements, Enumeration Areas and Forestry
Update the INSPIRE Theme Statistical Units dataset and preventing forest fire
Case study 9
• the process will contribute to build the geospatial framework to support 2021 Census.
• exploration the possibility of studying the forest and the eucalyptus plantation and its impact in preventing forest fire.
WPH Earth Observation – Case study description
19
Settlements, Enumeration Areas and Forestry
Update the INSPIRE Theme Statistical Units dataset and preventing forest fire
Case study 9
• Big challenge is:
• the spatial resolution of Sentinel images
• the integration of these geospatial data requiring methodological development
• the inexistence of explicit procedures by ESS to use these data in the statistical production process
WPH Earth Observation – Final technical report
• Partners cooperation: • similar topics and indicators;
• data access: satellite imagery (Sentinel, Modis, Landsat) and aerial imagery;
• data processing workflow including machine learning algorithms for image classification and segmentation;
• exchange of experiences among the WPH partners
• accuracy assessment of the results;
• harmonization of administrative data sources as a reference data;
• IT infrastructure definition for data processing;
• treatment of legal issues related to data access, processing and output.
20
05 – 06 December 2018, Vienna, Austria 21