Land cover mapping data is an annual component of the Victorian Land Use Information System, the VLUIS. The land cover information has been created specifically for the VLUIS using time series analysis of the MOD13Q1 or MYD13Q1 products produced by NASA using data collected by the MODIS sensor and freely available on the Reverb | ECHO website.
Ground data is collected annually across Victoria using a stratified random sampling approach for calibration of the annual seasonal curves and validation of the classification output. The ground data is split into three groups with 50% used to develop classification rules, 25% used to produce interim validation results that feed back into the rule development process with the remaining 25% used to independently validate the final classification. Error matrices for each land cover dataset from 2009 have been produced from this final validation.
The TIMESAT GUI is used to create smoothed annual time series for the Normalised Difference Vegetation Index (NDVI), Enhanced Vegetation Index (EVI) and the Red and Near Infrared (NIR) MOD13Q1 or MYD13Q1 bands using the Savitsky-Golay algorithm. A time series of 23 images was used and a suite of 11 seasonal parameters created that each numerically describe features of the annual seasonal curves for each band. In addition the standard deviation of the annual seasonal curve is calculated for each band and used in conjunction with the seasonal parameters.
A three-tiered hierarchical classification was developed to assign a dominant land cover class to each pixel. Initially, rules developed using the data mining tool See5 and / or expert knowledge were applied to the seasonal parameters and the annual standard deviation in conjunction with a GIS data-set of water bodies greater than 12.5ha in area to classify each pixel as either Tree, Non-tree or Water based on two data sets from the corporate spatial data library, HY_WATER_AREA_POLY.shp and VM_LITE_HY_WATER_AREA.shp; and are combined to form the water bodies layer. In addition, the primary classes are cross checked using data from preceding and following years to reduce misclassification prior to the secondary classification.
A secondary classification developed using rules based on expert knowledge and / or See5 is applied to split the primary class Tree into the secondary classes Native Woody Cover and Treed Production and the primary class Non-tree into the secondary classes Pasture/ Grassland and Crops.
Finally, a tertiary classification further divides the secondary class Treed Production into the tertiary classes Hardwood Plantation, Softwood Plantation and evergreen or deciduous Woody Horticulture and the secondary class Crops into the tertiary classes Brassicas, Legumes, Cereals and Non-Woody Horticulture based on rules developed using the data mining tool See5 and modified where appropriate by expert knowledge.
Additional information on land cover mapping, including map symbology, can be found on Victorian Resources Online.
DOI 10.4226/92/58e732125d9d0
Creative Commons Attribution 4.0 (CC-BY)
(
License Text
)
The custodian should be contacted to assess the utility of this dataset for your purpose.
Data Existence:
Metadata Name
Descriptions
Resource Name:
LANDCOVER_2015
Title:
Victorian Land Cover Mapping 2015
Anzlic ID:
ANZVI0803005645
Custodian:
Owner:
Jurisdiction:
Victoria
Abstract:
Land cover mapping data is an annual component of the Victorian Land Use Information System, the VLUIS. The land cover information has been created specifically for the VLUIS using time series analysis of the MOD13Q1 or MYD13Q1 products produced by NASA using data collected by the MODIS sensor and freely available on the Reverb | ECHO website.
Ground data is collected annually across Victoria using a stratified random sampling approach for calibration of the annual seasonal curves and validation of the classification output. The ground data is split into three groups with 50% used to develop classification rules, 25% used to produce interim validation results that feed back into the rule development process with the remaining 25% used to independently validate the final classification. Error matrices for each land cover dataset from 2009 have been produced from this final validation.
The TIMESAT GUI is used to create smoothed annual time series for the Normalised Difference Vegetation Index (NDVI), Enhanced Vegetation Index (EVI) and the Red and Near Infrared (NIR) MOD13Q1 or MYD13Q1 bands using the Savitsky-Golay algorithm. A time series of 23 images was used and a suite of 11 seasonal parameters created that each numerically describe features of the annual seasonal curves for each band. In addition the standard deviation of the annual seasonal curve is calculated for each band and used in conjunction with the seasonal parameters.
A three-tiered hierarchical classification was developed to assign a dominant land cover class to each pixel. Initially, rules developed using the data mining tool See5 and / or expert knowledge were applied to the seasonal parameters and the annual standard deviation in conjunction with a GIS data-set of water bodies greater than 12.5ha in area to classify each pixel as either Tree, Non-tree or Water based on two data sets from the corporate spatial data library, HY_WATER_AREA_POLY.shp and VM_LITE_HY_WATER_AREA.shp; and are combined to form the water bodies layer. In addition, the primary classes are cross checked using data from preceding and following years to reduce misclassification prior to the secondary classification.
A secondary classification developed using rules based on expert knowledge and / or See5 is applied to split the primary class Tree into the secondary classes Native Woody Cover and Treed Production and the primary class Non-tree into the secondary classes Pasture/ Grassland and Crops.
Finally, a tertiary classification further divides the secondary class Treed Production into the tertiary classes Hardwood Plantation, Softwood Plantation and evergreen or deciduous Woody Horticulture and the secondary class Crops into the tertiary classes Brassicas, Legumes, Cereals and Non-Woody Horticulture based on rules developed using the data mining tool See5 and modified where appropriate by expert knowledge.
Additional information on land cover mapping, including map symbology, can be found on Victorian Resources Online.
DOI 10.4226/92/58e732125d9d0
Search Words:
Society
,
Farming
Purpose:
Geographic Extent Polygon:
Geographic Bounding Box:
-34
141
150
-39
Beginning to Ending Date:
2015-01-01 - 2015-12-31
Maintainence and Update Frequency:
Annually
Stored Data Format:
Geotiff 3
Available Format(s) Types:
Not Known
Positional Accuracy:
Not Known
Attribute Accuracy:
Land cover 2014: Overall accuracy for this land cover classification was 66.4%. The accuracy for individual classes may vary and users are asked to refer to the data error matrix for more detailed accuracy information.
Land cover 2015: Overall accuracy for this land cover classification was 72.1%. The accuracy for individual classes may vary and users are asked to refer to the data error matrix for more detailed accuracy information.
Logical Consistency:
Not Known
Data Source:
Dataset Source: The dataset has been created by the Spatial Information Sciences Group of the Department of Economic Development, Jobs, Transport, and Resources, Agriculture Research Division.
Tertiary Dominant Land Classes:
0 Unknown
1 Water
11 Native Woody Cover
121 Deciduous Woody Horticulture
122 Evergreen Woody Horticulture
123 Hardwood Plantation
124 Softwood Plantation
21 Pasture and grassland
221 Brassicas
222 Cereals
223 Legumes
224 Non-woody Horticulture
3 Bare and non-photosynthetic material
Dataset Originality: Primary & Derived
Contact Organisation:
Contact Position:
Address:
Telephone:
Facsimile:
Email Address:
Metadata Date:
2021-07-14
Additional Metadata:
Related Documents: None
http://vro.depi.vic.gov.au/dpi/vro/vrosite.nsf/pages/luis
http://vro.depi.vic.gov.au/dpi/vro/vrosite.nsf/pages/luis
))