Tutorials¶
Step-by-step guides, one per topic. Each starts with what the analysis means and why you would use it, walks through a complete example on the maps that ship with Landschaft, shows the results and how to read them, and ends with the advanced options. Every code block runs as it is: copy it into a notebook and follow along.
Before you start
Install Landschaft and read core concepts: it explains how habitat maps are coded, which all tutorials rely on.
New to landscape ecology?
The Learn course explains what each analysis measures, the theory behind it and when to use it. The tutorials focus on how to run the tools.
-
Cores, edges, bridges and islets; objects by size; parcels and the shape of habitat boundaries.
-
Habitat density at one or many scales, fragmentation classes, landscape mosaics, contagion and entropy.
-
Patch, class and landscape metrics, sample plots, moving windows, time series and spatial signatures.
-
Patches and distances as a graph: connectivity indices, the importance of every patch and link, protected-area connectivity.
-
Current flow between habitat areas and omnidirectional connectivity maps, on rasters and on networks.
-
Distance and cost maps, least-cost paths and corridors, restoration status and travel-time maps.
-
What changed between two dates: habitat gains and losses, structural change, shifts between fragmentation classes.
-
Folders of rasters, maps larger than memory, time stacks with dask and very large tables.
-
Travel-time surfaces, least-cost routes, random walks and randomised shortest paths; how much routes from a common origin overlap.
-
Simulated landscapes as null models: random, gradients, fractals, clusters and mosaics; habitat maps and null-model tests.
-
Continuous rasters without classes: roughness, height distribution, texture images, spatial structure, terrain indices of DEMs and the hilltops protected by Brazil's Forest Code.
-
Filling and breaching depressions, flow directions and accumulation, streams, height above the nearest drainage and wetness.
-
The SWAT+ model from a DEM, land use and soils: daily water balance, streamflow, soil loss on the map and a land use scenario.
-
Species records in grid cells: richness, endemism, phylogenetic diversity and endemism, randomisations, CANAPE and regions.
-
Rank a landscape for many species with Zonation: performance curves, weights, costs, existing reserves and connectivity.
-
The cheapest plan that meets every target: reserves, compactness, budgets, importance, actions against threats, and a report.
-
How much of every converted cell to restore: original vegetation, habitat gains, extinction risk, carbon, intactness, budgets, regions and uncertainty.
-
Clean and thin occurrence records, prepare predictors and background, fit and cross-validate models on spatial folds, project and check extrapolation.
-
Project land use from two maps: demand, transition potential and four allocations, validation at several resolutions, calibration, scenarios with replicates, roads and stocks that change with the model.