Init project

.gitignore

@@ -0,0 +1,13 @@
+# Python-generated files
+__pycache__/
+*.py[oc]
+build/
+dist/
+wheels/
+*.egg-info
+
+# Virtual environments
+.venv
+
+# Data
+data

.python-version

@@ -0,0 +1 @@
+3.12

README.md

@@ -0,0 +1,45 @@
+# eSPA for RTS
+
+Goal of this project is to utilize the entropy-optimal Scalable Probabilistic Approximations algorithm (eSPA) to create a model which can estimate the density of Retrogressive-Thaw-Slumps (RTS) across the globe with different levels of detail.
+Hoping, that a successful training could gain new knowledge about RTX-proxies.
+
+## Setup
+
+```sh
+uv sync
+```
+
+## Project Plan
+
+1. Create global hexagon grids with h3
+2. Enrich the grids with data from various sources and with labels from DARTS v2
+3. Use eSPA for simple classification: hex has [many slumps / some slumps / few slumps / no slumps]
+4. use SPARTAn for regression: one for slumps density (area) and one for total number of slumps
+
+### Data Sources and Engineering
+
+- Labels
+  - `"year"`: Year of observation
+  - `"area"`: Total land-area of the hexagon
+  - `"rts_density"`: Area of RTS divided by total land-area
+  - `"rts_count"`: Number of single RTS instances
+- ERA5 (starting 40 years from `"year"`)
+  - `"temp_yearXXXX_qY"`: Y-th quantile temperature of year XXXX. Used to enter the temperature distribution into the model.
+  - `"thawing_days_yearXXXX"`: Number of thawing-days of year XXXX.
+  - `"precip_yearXXXX_qY"`: Y-th quantile precipitation of year XXXX. Similar to temperature.
+  - `"temp_5year_diff_XXXXtoXXXX_qY"`: Difference of the Y-th quantile temperature between year XXXX and XXXX. Always 5 years difference.
+  - `"temp_10year_diff_XXXXtoXXXX_qY"`: Difference of the Y-th quantile temperature between year XXXX and XXXX. Always 10 years difference.
+  - `"temp_diff_qY"`: Difference of the Y-th quantile temperature between year XXXX and XXXX. Always 10 years difference.
+- ArcticDEM
+  - `"dissection_index"`: Dissection Index, (max - min) / max
+  - `"max_elevation"`: Maximum elevation
+  - `"elevationX_density"`: Area where the elevation is larger than X divided by the total land-area
+- TCVIS
+  - ???
+- Wildfire???
+- Permafrost???
+- GroundIceContent???
+- Biome
+
+**About temporals** Every label has its own year - all temporal dependent data features, e.g. `"temp_5year_diff_XXXXtoXXXX_qY"` are calculated respective to that year.
+The number of years added from a dataset is always the same, e.g. for ERA5 for an observation in 2024 the ERA5 data would start in 1984 and for an observation from 2023 in 1983.

pyproject.toml

@@ -0,0 +1,43 @@
+[project]
+name = "entropic-perma-risk"
+version = "0.1.0"
+description = "Add your description here"
+readme = "README.md"
+authors = [{ name = "Tobias Hölzer", email = "tobiashoelzer@hotmail.com" }]
+requires-python = ">=3.12"
+dependencies = [
+    "aiohttp>=3.12.11",
+    "bokeh>=3.7.3",
+    "cartopy>=0.24.1",
+    "cyclopts>=3.17.0",
+    "dask>=2025.5.1",
+    "distributed>=2025.5.1",
+    "entropyc",
+    "flox>=0.10.4",
+    "folium>=0.19.7",
+    "geopandas>=1.1.0",
+    "h3>=4.2.2",
+    "h5netcdf>=1.6.4",
+    "ipykernel>=6.29.5",
+    "ipywidgets>=8.1.7",
+    "mapclassify>=2.9.0",
+    "matplotlib>=3.10.3",
+    "numpy>=2.3.0",
+    "odc-geo[all]>=0.4.10",
+    "pyarrow>=20.0.0",
+    "requests>=2.32.3",
+    "rich>=14.0.0",
+    "rioxarray>=0.19.0",
+    "scipy>=1.15.3",
+    "smart-geocubes[arcticdem,dask,stac,viz]>=0.0.9",
+    "stopuhr>=0.0.10",
+    "xanimate",
+    "xarray>=2025.4.0",
+    "xdggs>=0.2.1",
+    "xvec>=0.5.1",
+    "zarr[remote]>=3.0.8",
+]
+
+[tool.uv.sources]
+entropyc = { git = "ssh://git@github.com/AlbertEMC2Stein/entropyc", branch = "refactor/tobi" }
+xanimate = { git = "https://github.com/davbyr/xAnimate" }