Land cover & land change
Land cover rasters and how they change: NLCD and ESA WorldCover downloads, change matrices, urban growth, impervious surface, class areas and categorical raster pitfalls.
A land cover map turns every pixel into a class: water, forest, cropland, four intensities of developed land. Two maps of the same place years apart say what changed, and how fast a county is being built over. The arithmetic is simple, counting pixels and multiplying by their area, but categorical rasters have their own rules: they cannot be averaged or resampled like temperatures, a declared nodata value can hide real zeros, and every product has conventions about which changes it records.
The guides here work through real data: NLCD for every year from 2001 to 2021, cut from MRLC’s web coverage service, and ESA WorldCover at 10 m. In Williamson County, Texas, developed land grew from 332 to 523 km² while the population more than doubled, and three Brushy Creek subwatersheds passed 25% impervious cover.
🧭 Start with the concepts
The ideas the how-to guides below assume you already have.
⚙️ Then do the task
Step-by-step walkthroughs with code you can copy and adapt.
- How to Download NLCD Land Cover for an Area in Python
- How to Build a Land Cover Change Matrix in Python
- How to Measure Urban Growth From NLCD in Python
- How to Measure Impervious Surface by Watershed in Python
- How to Summarise Land Cover by Polygon in Python
- How to Read ESA WorldCover Tiles for an Area in Python
Show every how-to guide in this topic
- How to Reclassify a Land Cover Raster in Python
- How to Measure Land Cover Around Points in Python
- How to Analyse a Land Cover Time Series in Python
- How to Convert a Land Cover Raster to Polygons in Python
- How to Draw a Land Cover Transition (Sankey) Diagram in Python
- How to Measure Land Cover Along Streams in Python
- How to Get Land Use Polygons From OpenStreetMap in Python
🔧 When it breaks
The errors this topic produces, with the cause explained rather than just the command.
Related topics
Subjects that keep coming up alongside this one, most overlap first.