change-detection

# Change Detection & Spatio-temporal Analysis Purpose: separate real surface change from the four great impostors — misregistration, radiometric drift, phenology, and classification error. Every method below exists to control one of them; skipping the controls produces confident maps of nothing. ## Preconditions (where change detection is won or lost) 1. **Co-registration**: sub-pixel alignment between dates (AROSICS or manual tie-points). Half a pixel of shift creates edge-shaped phantom change everywhere. Verify: flicker-compare crisp features. 2. **Radiometric consistency**: same processing level (surface reflectance), same sensor if possible; if mixing sensors, harmonize (e.g., Landsat↔Sentinel-2 HLS) or use relative normalization (PIFs). 3. **Same season / phenological stage** for bi-temporal work — a May vs September pair "detects" summer. If season can't be matched, use composites or time-series methods instead. 4. **Cloud/shadow masks intersected across dates**; analyze only mutually valid pixels and report that coverage %. ## Method selection | Situation | Method | |---|---| | Two dates, continuous "how much" | Index differencing (ΔNDVI, ΔNBR...) with statistical thresholding | | Two dates, categorical "from-what-to-what" | Post-classification comparison (only with strong classifiers) | | Two dates, multivariate robust | Change vector analysis (CVA); MAD/iMAD for sensor-robust detection | | Dense stack, gradual + abrupt | Trend + break analy...