Vicmap Vegetation Tree Extent provides the most detailed statewide picture of tree cover available to date and is an excellent source of data for any applications requiring the identification of small patches of remnant tree cover such as connectivity analyses and  habitat modelling. The dataset also lends itself well to map presentation and  makes an excellent backdrop for other thematic information shown on maps.

Tree Extent was derived from a machine  learning  output. The dataset was created by assigning each  pixel in the aerial photography into two classes: tree or not tree.  The data was created using a machine  learning  method called semantic segmentation. In semantic segmentation, the machine  learning  model is trained on aerial  images, learning  from a corresponding raster mask that indicates which pixels represent  trees. From the training examples, the machine  learning  model learns  to distinguish pixels that belong to woody vegetation from those that belong to all other features, such as ground cover, roads, and human-built  structures.  The model was trained on 20cm aerial  photography. After processing the state-wide  tree  extent a waterbody and crop mask were  applied to remove any incorrectly classified pixels as tree cover found over those areas. No additional human  intervention post processing was performed on the data. 

For more information: Vicmap Vegetation (land.vic.gov.au)

Vicmap Vegetation Tree Extent provides the most detailed statewide picture of tree cover available to date and is an excellent source of data for any applications requiring the identification of small patches of remnant tree cover such as connectivity analyses and  habitat modelling. The dataset also lends itself well to map presentation and  makes an excellent backdrop for other thematic information shown on maps.

Tree Extent was derived from a machine  learning  output. The dataset was created by assigning each  pixel in the aerial photography into two classes: tree or not tree.  The data was created using a machine  learning  method called semantic segmentation. In semantic segmentation, the machine  learning  model is trained on aerial  images, learning  from a corresponding raster mask that indicates which pixels represent  trees. From the training examples, the machine  learning  model learns  to distinguish pixels that belong to woody vegetation from those that belong to all other features, such as ground cover, roads, and human-built  structures.  The model was trained on 20cm aerial  photography. After processing the state-wide  tree  extent a waterbody and crop mask were  applied to remove any incorrectly classified pixels as tree cover found over those areas. No additional human  intervention post processing was performed on the data. 

For more information: Vicmap Vegetation (land.vic.gov.au)