Urbanization Index · Settlement Detection
ISU – Index of Settlement / Urbanization
ISU enhances built-up areas by combining NDBI and NDVI, suppressing vegetation
and highlighting impervious surfaces. Useful for urban expansion and settlement mapping.
1. Scientific Definition
The ISU – Index of Settlement/Urbanization is a normalized built-up index
derived from the contrast between SWIR-based urban reflectance (NDBI)
and vegetation reflectance (NDVI).
Formula
ISU = (NDBI − NDVI) / (NDBI + NDVI)
Component Indices
NDVI = (NIR − Red) / (NIR + Red)
NDBI = (SWIR − NIR) / (SWIR + NIR)
Interpretation
ISU < 0 → vegetation / water / non-built
0 – 0.2 → low-density built-up
0.2 – 0.4 → moderate urban areas
> 0.4 → dense built-up urban core
Applications
Urban growth and expansion mapping
Settlement density detection
Impervious surface estimation
2. Data Requirements
Sentinel-2 Bands
Red → B4
NIR → B8
SWIR1 → B11
Landsat 8/9
Red → B4
NIR → B5
SWIR1 → B6
Suggested Palette
[ "#0b1220", "#1c2d4a", "#32598a", "#5c8ccd", "#a3d3ff" ]
3. Google Earth Engine Code – ISU
Copy
// ISU = (NDBI - NDVI) / (NDBI + NDVI)
var roi = geometry;
Map.centerObject(roi, 11);
// Load Sentinel-2 SR
var s2 = ee.ImageCollection("COPERNICUS/S2_SR")
.filterBounds(roi)
.filterDate("2023-01-01", "2023-12-31")
.filter(ee.Filter.lt("CLOUDY_PIXEL_PERCENTAGE", 20))
.select(["B4","B8","B11"]); // Red, NIR, SWIR
var img = s2.median().clip(roi);
// NDVI
var ndvi = img.normalizedDifference(["B8","B4"]).rename("NDVI");
// NDBI
var ndbi = img.normalizedDifference(["B11","B8"]).rename("NDBI");
// ISU formula
var isu = ee.Image().expression(
"(NDBI - NDVI) / (NDBI + NDVI)",
{
"NDBI": ndbi,
"NDVI": ndvi
}
).rename("ISU");
// Visualization
var vis = {
min: -1, max: 1,
palette: ["#0b1220","#1c2d4a","#32598a","#5c8ccd","#a3d3ff"]
};
Map.addLayer(isu, vis, "ISU");
Export.image.toDrive({
image: isu,
description: "ISU_export",
fileNamePrefix: "ISU_index",
region: roi,
scale: 20,
crs: "EPSG:4326",
maxPixels: 1e13
});
ISU – Index of Settlement/Urbanization · Start4IT Remote Sensing Index Library