Changes between Version 32 and Version 33 of UserApp/Proba-V


Ignore:
Timestamp:
Dec 16, 2011, 1:02:46 PM (8 years ago)
Author:
Iliyankatsarski
Comment:

Legend:

Unmodified
Added
Removed
Modified
  • UserApp/Proba-V

    v32 v33  
    475475
    476476[http://events.eoportal.org/presentations/7111/10001905.html For further info File:ProbaV Auto6.jpeg]
     477
     478= PROBA-V PERFORMANCE ASSESSMENT =
     479
     480= ABSTRACT =
     481
     482The Belgian Federal Science Policy Office (BELSPO) has initiated a Preparatory Evalua-tion/Validation Programme for
     483the products of the new PROBA-V satellite to be launched in 2012. The satellite will allow daily monitoring of terrestrial
     484vegetation cover through remote sensing, and will cover the data provision gap between the closure of the SPOT/VEGETATION
     485Programme and the launch of the SENTINEL-3 mission. The aim of this study is to evaluate the improvements that PROBA-V will
     486bring along for forest monitoring in the Atlantic Biogeographical Region of Europe, and lies within the objectives of the
     487FM@PROBA-V project. A representative site in Northern Por-tugal is selected for this reason. VEGETATION, LANDSAT-ÔÌ5, and
     488MODIS data along with the JRC Forest Cover Map are used to train the classifiers, simulate PROBA-V data, apply the classi-fiers
     489at 250 m, 1/3 of a km, and 1 km pixels, and validate the results, while quantifying the accura-cies. Maximum Likelihood (ML),
     490Artificial Neural Networks (ANN), and Support Vector Machine (SVM) methods were tested. From the confusion matrices the best
     491result is obtained by MODIS 2 bands with ANN classifier. Further analysis on the base of those confusion matrices will be
     492applied to define the best classifier taking into account all the parameters of the matrices. The best per-forming classifier
     493will then be recommended to examine its robustness against sudden disastrous events, like fire, in the same area, performing
     494change detection between sequential dates (before and after the event). The performance of the data and classifiers are
     495demonstrated, and the pre-liminary results are discussed.The Belgian Federal Science Policy Office (BELSPO) has initiated a
     496Preparatory Evalua-tion/Validation Programme for the products of the new PROBA-V satellite to be launched in 2012. The satellite
     497will allow daily monitoring of terrestrial vegetation cover through remote sensing, and will cover the data provision gap between
     498the closure of the SPOT/VEGETATION Programme and the launch of the SENTINEL-3 mission. The aim of this study is to evaluate the
     499improvements that PROBA-V will bring along for forest monitoring in the Atlantic Biogeographical Region of Europe, and lies within
     500the objectives of the FM@PROBA-V project. A representative site in Northern Por-tugal is selected for this reason. VEGETATION,
     501LANDSAT-ÔÌ5, and MODIS data along with the JRC Forest Cover Map are used to train the classifiers, simulate PROBA-V data, apply
     502the classi-fiers at 250 m, 1/3 of a km, and 1 km pixels, and validate the results, while quantifying the accura-cies. Maximum
     503Likelihood (ML), Artificial Neural Networks (ANN), and Support Vector Machine (SVM) methods were tested. From the confusion
     504matrices the best result is obtained by MODIS 2 bands with ANN classifier. Further analysis on the base of those confusion
     505matrices will be applied to define the best classifier taking into account all the parameters of the matrices. The best
     506per-forming classifier will then be recommended to examine its robustness against sudden disastrous events, like fire, in the same area,
     507performing change detection between sequential dates (before and after the event). The performance of the data and classifiers are
     508demonstrated, and the pre-liminary results are discussed.
     509= INTRODUCTION =
     510
     511
     512World forests cover roughly 31% of land area and in the last decade it has been reduced at a rate of 13 million hectares
     513per year (1). According to the global forest resources assessment 2010 of the Food and Agriculture Organization, significant
     514progress has been made towards reversing the overall trend of forest area loss and a positive trend over time has been shown
     515in some countries and regions such as in Europe where the forest area continued to expand.
     516
     517Considerable efforts are needed to improve or at least maintain this positive trend. The forest monitoring gives crucial data
     518to decision makers helping them allocate appropriate financial re-sources for effective forest conservation and management plans.
     519One of these crucial data is For-est Area, which has been selected as one of the 60 indicators for monitoring progress towards
     520the Millennium Development Goals, the 2010 Biodiversity Target and the Global Objectives on For-ests. Forest Area and its changes
     521are relatively easy to measure, especially nowadays with the technological progress made in remote sensing fields.
     522
     523The available high temporal resolution images allow operational and near real-time applications at global, continental and regional
     524scales for forest area mapping and monitoring. The VEGETATION instruments, which were developed with the objective to provide data
     525specifically for vegetation canopy monitoring, are on board two SPOT5 satellites and will be available until 2013. The instru-ments
     526of this programme (VEGETATION 1 and VEGETATION 2) have monitored and mapped the worldwide vegetation on a daily basis for more than
     52712 years now. They provide essential infor-mation on terrestrial vegetation cover for a large community of users. Therefore, to ensure
     528the continuity of the data after 2012, the SENTINEL mission, which will be launched at the earliest at the end of 2013 (2), will provide
     529data which will fulfil the needs of the current VEGETATION data users. To fill the data gap between VEGETATION-2 and SENTINEL-3, the
     530Belgian Federal Sci-ence Policy Office (BELSPO) has decided to build a satellite mission called PROBA-V which is expected to meet all
     531the specifications of the vegetation user community (2). PROBA-V will have an increased spatial resolution in comparison to the
     532VEGETATION instrument, an enhancement expected to provide new opportunities for forest monitoring.
     533
     534The aim of this study is to evaluate forest cover classification methods on the European Atlantic biogeographical region by applying the
     535Maximum Likelihood (ML), Artificial Neural Network (ANN) and Support Vector Machine (SVM) classification algorithms on simulated PROBA-V,
     536VEGETATION and MODIS data, in order to determine the optimal classification methodology for the region. This work is carried out within
     537the framework of the FM@PROBA-V project1 towards evaluation and quantification of the improvements of the products for forest monitoring
     538offered by PROBA-V, in relation to its predecessor, VEGETATION. The preliminary results of the study are presented and discussed in this paper.
     539== Study area ==
     540
     541
     542The area of interest is the southern part of the Atlantic biogeographical region of Europe (Figure 1) which is located
     543in the north of Portugal. The region is one of the rare mountainous areas in this region, and mountains in the area can
     544reach an altitude of 1500 m. Forest cover is sparse and agriculture is not very intensive in the region
     545 
     546= Methods =
     547
     548== Dataset and preprocessing ==
     549
     550
     551The data used in this study included the images used for the evaluation process of the forest cover mapping in the European Atlantic
     552biogeographical region and the data used to create the refer-ence data for the classifications. The reference data originated from the
     553classification of a Landsat TM image, acquired on 11 July 2009, using training samples and reference points identified from the JRC
     554Forest Cover Map 2006 and Google Earth images. A small subset (20 „e 20 km2) of that scene was used to simulate a part of a PROBA-V
     555scene, a process undertaken by VITO NV, Bel-gium. The datasets used to evaluate classification algorithms included the simulated
     556PROBA-V image (Red, NIR, approximated SWIR), a 10-day synthesis VEGETATION (VGT) image at 1000 m spatial resolution with 3 bands (Red, NIR, SWIR),
     557and an 8-day synthesis MODIS image at 250 m spatial resolution (again Red, NIR, resampled/ upgraded SWIR). The simulated PROBA-V
     558subset was relatively small (20 „e 20 km2) and the results were expected to be of questionable statistical significance. Hence the
     559MODIS image was additionally evaluated, as its similar charac-teristics with PROBA-V data (Table 1) would allow better evaluation of
     560the potential of the upcom-ing sensor, and its comparison with VGT data. Since only the red and NIR channels are available at 250 m
     561resolution, the SWIR 500 m channel was resampled to 250 m and two MODIS datasets were evaluated, with and without the SWIR data. All
     562images, including the JRC forest cover map where registered to the Landsat TM image in UTM WGS84, Zone 29N projection, WGS84 datum.
     563The extent of MODIS and VGT images was reduced to a subset matching the extent of Landsat TM, which was topographically normalized with the ASTER GDEM.
     564
     565
     566{| border="1"
     567|+ Image data characteristics
     568! !! VEGETATION II !! Modis !! Proba V
     569|-
     570! Blue
     571| 0.43 – 0.47 || 0.45 - 0.47 || 0.44 – 0.48
     572|-
     573! Red
     574| 0.61 – 0.68 || 0.62 – 0.67 || 0.62 – 0.69
     575|-
     576! NIR
     577|0.78 – 0.89 || 0.84 - 087 || 0.79 – 0.90 || 800 x 800 x 1000 mm
     578|-
     579! SWIR
     580| 1.58 – 1.75 || 1.62 –1.65 || 1.56 – 1.65
     581|-
     582! Spatial Resolution
     583| 1.15 km || 250m (R, NIR), 500m (SWIR) || 300m (VNIR), 600m (SWIR)
     584|}
    477585= User Segment =
    478586