Global Ensemble Digital Terrain Model (GEDTM30): a Tile Example of Local Enhanced Modeling via Transfer Learning
Global Ensemble Digital Terrain Model (GEDTM30): a Tile Example of Local Enhanced Modeling via Transfer Learning
This repository stores the covariates, the model, the additional samples to run a global-to-local modeling of GEDTM project (https://github.com/openlandmap/GEDTM30). Please visit here for the script of the showcase. The script describes a pre-trained random forest model (global.model_gedtm30.lz4) that is successively trained by the additional local samples (local_samples.csv). With the data from (covariates list). Below is the explanation of the covariates, the model and the additional samples. File description: global.model_gedtm30.lz4 random forest model trained by global stratified terrain samples of GEDI02 and ICESat-2 ATL08 v6. local_sample.csv: the local samples of GEDI02 and ICESat-2 ATL08 v6. dtm_y: the terrain height from global Lidar covariates list: dsm_glo.tiff: Copenricus GLO30 DEM (doi.org/10.5270/ESA-c5d3d65) dsm_aw3d30 ALOS AW3D30 DEM (Takaku et al. 2014, Tadono et al.) building.height_ghsbuilth.tiff: GHS building height ~100m resolution, resampled by cubicspline (10.2905/85005901-3A49-48DD-9D19-6261354F56FE) tree.cover_glad.tiff: tree cover precentile (Potapov et al. 2021) building.height_3dglobfp.tiff: global three-dimensional building footprint dataset, vector dataset, rasterized to ~30m resolution (Che et al. 2024) canopy.height_glad.tiff: canopy height from GLAD (Potapov et al. 2021) edge.canopy.height_glad.tiff: edge canopy height by Sobel filter, derived from GLAD canopy height canopy.height_eth.tiff: canopy height model from ETH (Lang et al. 2023) edge.canopy.height_eth.tiff:edge canopy height by Sobel filter, derived from ETH canopy height slope_etopo2022.tiff: earth topography 2022 (etopo 2022) global dem dataset ~500m resolution, resampled by cubicspline (MacFerrin et al. 2024) lcluc.change_glad.tiff: land use land cover change (Potapov et al. 2020) Landsat indices (Potapov 2020): ndvi.p025_2006.2010.tiffndvi.p50_2006.2010.tiffndvi.p975_2006.2010.tiffndvi.p025_2011.2015.tiffndvi.p50_2011.2015.tiffndvi.p975_2011.2015.tiffnir.p025_2006.2010.tiffnir.p50_2006.2010.tiffnir.p975_2006.2010.tifffnir.p025_2011.2015.tiffnir.p50_2011.2015.tiffnir.p975_2011.2015.tifndwi.p025_2006.2010.tiffndwi.p50_2006.2010.tiffndwi.p975_2006.2010.tiffndwi.p025_2011.2015.tiffndwi.p50_2011.2015.tiffndwi.p975_2011.2015.tiff Note: nir,ndvi,ndwi: Near infra-red, Normalized Difference Vegetation Index, Normalized Difference Wetness Index. p025, p050,p975: precentile 2.5, 50, 97.5.
geomorphometry, Digital Elevation Model, Digital Terrain Model
geomorphometry, Digital Elevation Model, Digital Terrain Model
selected citations These citations are derived from selected sources.This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).0 popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.Average influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).Average impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.Average
Citations provided by BIP!Popularity provided by BIP!