Auxiliary datasets improve accuracy of object-based land use/land cover classification in heterogeneous savanna landscapes

Show simple item record

dc.contributor.author Hurskainen, Pekka
dc.contributor.author Adhikari, Hari
dc.contributor.author Siljander, Mika
dc.contributor.author Pellikka, Petri
dc.contributor.author Hemp, Andreas
dc.date.accessioned 2019-09-05T10:42:02Z
dc.date.available 2019-09-05T10:42:02Z
dc.date.issued 2019-11
dc.identifier.citation Hurskainen , P , Adhikari , H , Siljander , M , Pellikka , P & Hemp , A 2019 , ' Auxiliary datasets improve accuracy of object-based land use/land cover classification in heterogeneous savanna landscapes ' , Remote Sensing of Environment , vol. 233 , no. 111354 , 111354 . https://doi.org/10.1016/j.rse.2019.111354
dc.identifier.other PURE: 126480693
dc.identifier.other PURE UUID: 9d4b9e86-18f4-4c4c-a564-d14489c14d24
dc.identifier.other ORCID: /0000-0003-1039-3357/work/64976801
dc.identifier.other WOS: 000497601000033
dc.identifier.other ORCID: /0000-0002-9089-3249/work/66563685
dc.identifier.uri http://hdl.handle.net/10138/305233
dc.description.abstract Classifying land use/land cover (LULC) with sufficient accuracy in heterogeneous landscapes is challenging using only satellite imagery. To improve classification accuracy inclusion of features from auxiliary geospatial datasets in classification models is applied since 1980s. However, the method is mostly limited to pixel-based classifications, and the coverage, accuracy and resolution of free and open-access auxiliary datasets have been poor until recent years. We evaluated how recent global coverage open-access geospatial datasets improve object-based LULC classification accuracy compared to using only spectral and texture features from satellite images. We applied feature sets topography, population, soil, canopy cover, distance to watercourses and spectral-temporal metrics from Landsat-8 time series on the southern foothills and savanna of Mt. Kilimanjaro, Tanzania, where the landscape is characterized by heterogeneous and fragmented mosaic of disturbed savanna vegetation, croplands, and settlements. The classification was based on image objects (groups of spectrally similar pixels) derived from segmentation of four Formosat-2 scenes with 8m spatial resolution using 1370 ground reference points for training, validation, and for defining 17 LULC classes. We built six Random Forest classification models with different sets of object features in each. The baseline model having only spectral and texture features was compared with five other models supplemented with auxiliary features. Inclusion of auxiliary features significantly improved classification overall accuracy (OA). The baseline model gave a median OA of 60.7%, but auxiliary features in other models increased median OA between 6.1 and 16.5 percentage points. The best OA was achieved with a model including all features of which elevation was the most important auxiliary feature followed by Enhanced Vegetation Index temporal range and slope degree. Applying object-based classification to geospatial information on topography, soil, settlement patterns and vegetation phenology, the discriminatory potential of challenging LULC classes can be significantly improved. We demonstrated this for the first time, and the technique shows good potential for improving LULC mapping across a multitude of fragmented landscapes worldwide. fi
dc.format.extent 17
dc.language.iso eng
dc.relation.ispartof Remote Sensing of Environment
dc.rights cc_by
dc.rights.uri info:eu-repo/semantics/openAccess
dc.subject 1171 Geosciences
dc.subject image segmentation
dc.subject OBIA
dc.subject Land use
dc.subject Land cover classification
dc.subject Auxiliary data
dc.subject Random Forest
dc.subject Satellite Time Series
dc.subject Image segmentation
dc.subject OBIA
dc.subject Land use/land cover mapping
dc.subject Auxiliary data
dc.subject Random Forest
dc.subject Satellite Time Series
dc.subject IMAGE-ANALYSIS
dc.subject RANDOM FOREST
dc.subject MT. KILIMANJARO
dc.subject TIME-SERIES
dc.subject SURFACE TEMPERATURE
dc.subject SOUTHERN SLOPES
dc.subject ANCILLARY DATA
dc.subject VEGETATION
dc.subject MULTISOURCE
dc.subject SELECTION
dc.title Auxiliary datasets improve accuracy of object-based land use/land cover classification in heterogeneous savanna landscapes en
dc.type Article
dc.contributor.organization Department of Geosciences and Geography
dc.contributor.organization Earth Change Observation Laboratory (ECHOLAB)
dc.contributor.organization Helsinki Institute of Sustainability Science (HELSUS)
dc.description.reviewstatus Peer reviewed
dc.relation.doi https://doi.org/10.1016/j.rse.2019.111354
dc.relation.issn 0034-4257
dc.rights.accesslevel openAccess
dc.type.version publishedVersion
dc.relation.funder Ministry for Foreign Affairs of Finland
dc.relation.grantnumber

Files in this item

Total number of downloads: Loading...

Files Size Format View
1_s2.0_S0034425719303736_main.pdf 5.303Mb PDF View/Open

This item appears in the following Collection(s)

Show simple item record