This

The Statewide Marine Habitat Map 2023 was developed by DEECA applying novel machine learning methods that model and predict habitat distributions as well as a mosaic of former mapping products (listed below). The Statewide map represents 24 marine and coastal habitats complexes at Level 3, Victoria's Combined Biotope Classification Scheme (CBiCS) described by Edmunds and Flynn (2015, 2018; 2021). The final map comprises of 83% its area from predictive modelling, with the remaining 17% of area from synthesised existing habitat maps. Predictive Model: A total of 32,998 habitat survey sites (ground-truth records) were used within the model, along with 28 environmental properties mapped at a 10m resolution (including a Digital Elevation Model DEM (VCDEM2021), computed benthic terrain characteristics (toolkit: Walbridge et al. 2018), Chlorophyl a (IMOS 2000a), Sea Surface Temperature SST (IMOS 2000a), Net Primary Productivity NPP (IMOS 2000b), Sediments (Geoscience Australia; Li et al. 2011a,b,c), waves (Liu et al. 2022). To predict the distribution of habitats across Victorian waters the powerful and flexible Random Forest machine learning algorithm was applied. Random Forest is an ensemble model using bagging as the ensemble method and decision trees as the individual model (Breiman 2001). The modelling produced an accuracy (Out-of-bag) of 89%. Map Synthesis: A mosaic of former mapping products that provided higher resolution mapping by aerial imagery, field observations and high-resolution modelling were integrated into the map, classifying habitat according to the CBICS habitat classification scheme at level 3. Assessed and synthesised maps and citations include: Corangamite Coast Marine Habitat December 2009 (ANZVI0803005530); East Gippsland Marine Habitats November 2009 (ANZVI0803003974); Discovery Bay Marine National Park habitat mapping 2006 (ANZVI0803004053); Portland Coastal Habitats (ANZVI0803004236) ; Corner Inlet Mapping Marine National Park North and South 2004 (ANZVI0803004051) ; Merri Marine Sanctuary 2004 (ANZVI0803004058); Western Port Bay Biotope Mapping Fathom Pacific (2016) CBiCS-Mapping. Central Victoria Coastal Habitats (ANZVI0803004135); Mallacoota Coastal Habitats (ANZVI0803004235); Western Port Rhodolite (ANZVI0803005430) & Western Port Biogenic Reefs; Port Phillip Bay Habitat Map 2021 (ANZVI0803009278); Saltmarsh and Mangrove Habitats; DELWP 2021 Statewide Marine Habitat Map 2021 (ANZVI0803009286) and relevant citations: Ball (1999), Ball et al. (2010). Ball & Blake (2007a), Ball & Blake (2007b), Blake and Ball (2001), Blake et al. (2013), Boon et al. (2011), Cohen et al (2000), Deakin Marine Mapping (Zavalas, R et al. 2018), DELWP (1994), Edmunds &Flynn (2015), Fathom Pacific (2020), Ford et al (2016), GeoHab Victoria Estuaries Geomorphology (2010), Ierodiaconou 2007, Ierodiaconou et al. 2018, Mazor et al. (2021), Monk et al. (2011), Poore (1992), Roob and Ball (1997), Victoria Department of Transport (1999), Young et al. 2022, Zavalas, R et al. 2018. Applications: The Statewide Marine Habitat Map 2023 provides broad habitat complexes across the state and provides greater knowledge of the ecological diversity across Victoria¿s waters. The map should be used at broad scales of >25 m, and where information of larger habitat complexes is needed. This work can support the management of large-scale habitats, their condition, marine spatial planning, strategic management prospect (SMP), FeAST risk assessments, and other broad scale applications to support management decisions across Victoria. The habitat model and resulting map provides an updated broad-scale habitat map across Victoria¿s state waters and provides a baseline for future data to build upon. Full Methodology: Citation: Mazor, T., Watermeyer, K., Hobley, T., Grinter, V., Holden, R., MacDonald, K. and Ferns, L. (2023). Statewide Marine Habitat Map. Habitat Complex Modelling Method (CBiCS Level 3). The State of

The Statewide Forest Resource Inventory (SFRI) is a program of information collection and analysis of Victoria's native forests that supports statewide planning and management. One SFRI product is SFRImap Database - a database of information on the eucalypt composition, structure and history of Victoria's forests. SFRImap Database covers most of Victoria's forests on public land at a scale of 1:25,000. Relative Age is a layer derived from SFRImap. It is SFRImap dissolved on the RELAGE attribute. Derived layers from SFRImap Database are complimented with the same metadata as the SFRImap layer.

Distribution and severity of psyllid infestation of selected Departmental Forest Blocks. This layer shows the distribution and severity of psyllid infestation of selected Forest Blocks. This is an interim layer awaiting the formation of the Psyllid Working Group.

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 21 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 10.26279/5b98601d6b27e

The Victorian Land Use Information System (VLUIS) dataset has been created by the Spatial Information Sciences Group of the Agriculture Research Division in the Department of Economic Development, Jobs, Transport, and Resources. The method used to create VLUIS is significantly different to traditional methods used to create land use information and has been designed to create regular and consistent data over time. It covers the entire landmass of Victoria and separately describes the land tenure, land use and land cover for each cadastral parcel across the state, biennially for land tenure and use and annually for land cover; for each year from 2006 to 2015. The data is in the form of a feature class. To use the VLUIS data correctly it is important to understand the difference between the three components of VLUIS. The Guidelines for land use mapping in Australia: principles, procedures and definitions, Edition 3 published in 2006 by the Commonwealth of Australia, defines them as follows: Land tenure is the ownership and leasehold interests in land (VLUIS only reports ownership). Land use means the purpose to which the land cover is committed or the property type. Land cover refers to the physical surface of the earth, including various combinations of vegetation types, soils, exposed rocks and water bodies as well as anthropogenic elements, such as agriculture and built environments. The Victorian Land Use Information System (VLUIS) is an ongoing project designed to maintain and manage the Victorian land use mapping dataset. The methodology is still being refined and as such the dataset is subject to improvements and the release of later versions. It is important you speak to the custodian to be advised of the technical details of the dataset and its utility for your desired use. Land cover classification accuracy varies between classes and the overall classification accuracy may be misleading in terms of the accuracy of an individual class. Users are asked to contact the data custodians for detailed class accuracy information if required for their purposes. Irrigation activity is included when available. The data was not available in 2006-07 and there was incomplete coverage in 2012-13 and therefore the irrigation activity was not included in either of those datasets. The dataset does not replace LandUse100 which is still valid for the time in which it was created (1996 - 2005). A metadata statement, for the VLUIS 2006/07 product, and ESRI symbology files for the data can be freely downloaded from the VLUIS project page: http://vro.depi.vic.gov.au/dpi/vro/vrosite.nsf/pages/vluis DOI: http://dx.doi.org/10.5061/dryad.n08t0

Polygon coverage displaying Victorian commercial timber harvesting event data in State forest, by financial year. Other information recorded is silvicultural operation type, forest type, start/end dates of the logging event. The dataset has been updated with the 2021-22 information. Complete to the end of June 2022

This polygon layer represents seagrass habitat at nine regions in Port Phillip Bay in April 2008 mapped from aerial photography. The mapping was undertaken for the Baywide Seagrass Monitoring Program (CDP_ENV_MD_022 Rev5 - Port of Melbourne Corporation, 2010). The program is being undertaken for the Port of Melbourne Corporation as part of Baywide Monitoring to support the Channel Deepening Project.

The Victorian Land Use Information System (VLUIS) dataset has been created by the Spatial Information Sciences Group of the Agriculture Research Division in the Department of Economic Development, Jobs, Transport, and Resources. The method used to create VLUIS is significantly different to traditional methods used to create land use information and has been designed to create regular and consistent data over time. It covers the entire landmass of Victoria and separately describes the land tenure, land use and land cover for each cadastral parcel across the state, biennially for land tenure and use and annually for land cover; for each year from 2006 to 2015. The data can be provided as a spatial dataset or in tabular format. To use the VLUIS data correctly it is important to understand the difference between the three components of VLUIS. The Guidelines for land use mapping in Australia: principles, procedures and definitions, Edition 3 published in 2006 by the Commonwealth of Australia, defines them as follows: Land tenure is the ownership and leasehold interests in land (VLUIS only reports ownership). Land use means the purpose to which the land cover is committed or the property type. Land cover refers to the physical surface of the earth, including various combinations of vegetation types, soils, exposed rocks and water bodies as well as anthropogenic elements, such as agriculture and built environments. The Victorian Land Use Information System (VLUIS) is an ongoing project designed to maintain and manage the Victorian land use mapping dataset. The methodology is still being refined and as such the dataset is subject to improvements and the release of later versions. It is important you speak to the custodian to be advised of the technical details of the dataset and its utility for your desired use. Land Cover 2014: Land cover classification accuracy statements for the entire state may not be representative of land cover classification accuracy levels in the north-west of the state due to a paucity of ground truth data in this area (particularly west of Swan Hill and north of Sea Lake). Users are advised to use this land cover information with discretion and contact the data custodians for further information if required. Land cover classification accuracy varies between classes and the overall classification accuracy may be misleading in terms of the accuracy of an individual class. Users are asked to contact the data custodians for detailed class accuracy information if required for their purposes. The dataset does not replace LandUse100 which is still valid for the time in which it was created (1996 - 2005). A metadata statement, for the VLUIS 2014/15 product, and ESRI symbology files for the data can be freely downloaded from the VLUIS project page on the Victorian Resources Online website: http://vro.agriculture.vic.gov.au/dpi/vro/vrosite.nsf/pages/vluis DOI 10.4226/92/58e72ebae5380

The Victorian Land Use Information System (VLUIS) dataset has been created by the Spatial Information Sciences Group of the Agriculture Research Division in the Department of Economic Development, Jobs, Transport, and Resources. The method used to create VLUIS is significantly different to traditional methods used to create land use information and has been designed to create regular and consistent data over time. It covers the entire landmass of Victoria and separately describes the land tenure, land use and land cover for each cadastral parcel across the state, biennially for land tenure and use and annually for land cover; for each year from 2006 to 2015. The data is in the form of a feature class. To use the VLUIS data correctly it is important to understand the difference between the three components of VLUIS. The Guidelines for land use mapping in Australia: principles, procedures and definitions, Edition 3 published in 2006 by the Commonwealth of Australia, defines them as follows: Land tenure is the ownership and leasehold interests in land (VLUIS only reports ownership). Land use means the purpose to which the land cover is committed or the property type. Land cover refers to the physical surface of the earth, including various combinations of vegetation types, soils, exposed rocks and water bodies as well as anthropogenic elements, such as agriculture and built environments. The Victorian Land Use Information System (VLUIS) is an ongoing project designed to maintain and manage the Victorian land use mapping dataset. The methodology is still being refined and as such the dataset is subject to improvements and the release of later versions. It is important you speak to the custodian to be advised of the technical details of the dataset and its utility for your desired use. Irrigation activity is included when available. The data was not available in 2006-07 and there was incomplete coverage in 2012-13 and therefore the irrigation activity was not included in either of those datasets. Land cover classification accuracy varies between classes and the overall classification accuracy may be misleading in terms of the accuracy of an individual class. Users are asked to contact the data custodians for detailed class accuracy information if required for their purposes. The dataset does not replace LandUse100 which is still valid for the time in which it was created (1996 - 2005). A metadata statement, for the VLUIS 2008/09 product, and ESRI symbology files for the data can be freely downloaded from the VLUIS project page: http://vro.depi.vic.gov.au/dpi/vro/vrosite.nsf/pages/vluis DOI: http://dx.doi.org/10.5061/dryad.n08t0