urban-remote-sensing

Extract urban land cover and heat island patterns from satellite imagery.

33|6|Updated Mar 17, 2026

Search Tags:#change detection #rasterio #ndvi #urban remote sensing #lulc classification #urban heat island #impervious surface

Ready to run

npx skills add https://github.com/xjtulyc/awesome-rosetta-skills --skill urban-remote-sensing

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: urban-remote-sensing
Source: https://github.com/xjtulyc/awesome-rosetta-skills/tree/main/skills/18-urban-science/urban-remote-sensing
Command: npx skills add https://github.com/xjtulyc/awesome-rosetta-skills --skill urban-remote-sensing

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes assets (resource) components.

What problem does it solve?

Urban remote sensing turns satellite imagery into actionable measurements of land cover change and surface temperature patterns, saving analysts from manual, time-consuming interpretation.

Core Features & Use Cases

Impervious Surface Mapping & Vegetation Indices: Compute NDVI, NDBI, NDWI to separate vegetation, water, and built-up areas for impervious surface detection.
LULC Classification from Spectral Features: Train and apply a supervised classifier (e.g., Random Forest) using band values plus derived indices to produce an urban land use/land cover map.
Urban Heat Island (UHI) Profiling & Change Detection: Analyze LST–NDVI relationships, compute UHI intensity via transects/rings, and detect expansion between time periods using spectral index differencing.

Quick Start

Use the urban-remote-sensing Skill to analyze a multispectral urban scene by computing spectral indices, classifying land cover, and generating an urban heat island profile from satellite-like raster inputs.

Frequently Asked Questions about urban-remote-sensing

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I map impervious surfaces and compute NDVI from multispectral satellite imagery?▼

Map impervious surfaces by computing NDVI, NDBI, and NDWI spectral indices from multispectral imagery to separate vegetation, water, and built-up areas for urban land cover detection.

What is the best way to classify urban land use and land cover using Python?▼

Classify urban land cover by training a supervised Random Forest classifier using raster band values and derived spectral indices with scikit-learn to generate LULC maps.

How do I profile urban heat island intensity and analyze LST-NDVI relationships?▼

Profile urban heat island intensity by analyzing LST-NDVI relationships and computing UHI patterns via transect or ring profiling across satellite-like raster inputs.

Can I perform spectral change detection across two time periods using rasterio and numpy?▼

Perform spectral change detection across two time periods by computing spectral index differencing using numerical raster processing with numpy and rasterio for urban expansion analysis.

Do I need scikit-learn and geopandas to run supervised LULC classification and UHI analysis?▼

Yes, supervised LULC classification and UHI profiling require scikit-learn for machine learning, rasterio and geopandas for geospatial IO, and matplotlib for visualization outputs.