7.5.2

What's Changed

• use python venv for pip install by @metzm in #102 and #103

Full Changelog: 7.5.1...7.5.2

7.5.1

What's Changed

• Use m.neural.network version 2.1.1

Full Changelog: 7.5.0...7.5.1

7.5.0

What's Changed

• new m.neural_network release by @metzm in #101

Full Changelog: 7.4.0...7.5.0

7.4.0

What's Changed

• Extent distance methods for center - parcel and center - building by @vbrunn in #96
• Adjust PP for usage with NN input by @linakrisztian and @vbrunn in #98
• Update technical setup for NN approach and added Dokumentation for NN V2.0.0 by @linakrisztian and @vbrunn in #99

Full Changelog: 7.3.0...7.4.0

7.3.0

Changed

• import option 'train neural network' by @vbrunn in #89
• scikit-learn fix by @metzm in #93
• add m.neural_network and Training Data Generation Documentation by @griembauer in #90

Full Changelog: 7.2.0...7.3.0

generated with gh api repos/mundialis/rvr_interface/releases/generate-notes -f tag_name="7.3.0" -f target_commitish=main -q .body

7.2.0

Changed

• tree analyses: remove duplicated calculation of NDWI and NDGB #88

7.1.0

Changed

• DGM/DTM import as tif by @vbrunn in #84
• Small improvements by @anikaweinmann and @vbrunn in #85
  • m.import.rvr improve check addon for multiaddons
  • r.trees.traindata: rename trees_pixel_ndvi to nearest_pixel_ndvi
  • nearest_pixel_ndvi is created automatically in r.trees.mltrain if not set, so that r.trees.traindata can be skipped if own training data are created
• Change tree trunk position to be created by 'r.to.vect -c' by @anikaweinmann in #86

Added

• r.trees.thresholds: addon to propose thresholds by @anikaweinmann and @vbrunn in #87

Full Changelog: 7.0.0...7.1.0

"generated with gh api repos/mundialis/rvr_interface/releases/generate-notes -f tag_name="7.1.0" -f target_commitish=main -q .body"

7.0.0

Breaking Changes

• Split r.trees.mltrain into two modules:
  • r.trees.traindata creates preliminary tree raster/vector to be used in ML processing or directly in r.trees.postprocess ("switch" for optional ML processing)
  • r.trees.mltrain samples training data points from the preliminary tree raster/vector (or any user generated or modified training dataset) and trains the ML model. The num_samples parameter is now configurable by the user. If not defined, the entire input training raster/vector dataset will be used.

--> The purpose of this change is that users may

• skip the ML processing and directly use the preliminary tree map generated by r.trees.traindata in r.trees.postprocess
• export, adapt and/or replace the preliminary tree map generated by r.trees.traindata in order to use customized training data in the ML process (r.trees.mltrain + r.trees.mlapply)

Changed

• v.trees.param:
  • dist_building, dist_tree removed from default parameter list
  • distance_building, distance_tree: default distance reduced to 50m
• v.trees.param.worker:
  • name of attribute columns for centroid position switched from pos_cent_x/y to pos_rand_x/y as they are currently at a random point within the polygon (to be adapted in r.to.vect)

Added

• Module r.trees.traindata (see above)
• r.trees.mltrain: User may pass the amount of samples for training by the new num_samples parameter (see above)

6.1.0

Changed

• m.analyse.trees: make all ndsm threshold to variable

6.0.0

Breaking Changes

• m.import.rvr: unify parameters for import addon #72
  --> options for type have changed to English
• m.analyse.trees: unify parameters for tree addons #71
  --> some parameters are renamed
• m.import.rvr: GUI changes for import module #69
  --> dtm_file is split into dtm_dir and dtm_file

Changed

• v.trees.param: make input required #76
• HTML changes #75
• m.analyse.trees: reorder params, change gui section for some optional input #74
• m.analyse.buildings: unify parameters for buildings addons #70
• set a fix version for v.alkis.buildings.import #68

Added

• r.extract.buildings + r.extract.greenroofs: add parameter for threshold #73