NDWI, NDBI, SAVI & EVI Explained + Calculated in PyQGIS | Remote Sensing Indices

📡 What if I told you that with just TWO satellite bands and ONE formula, you can
map all the water bodies in a region? Or detect urban sprawl? Or measure crop
stress? That's the power of Remote Sensing Indices — and in Day 10, we cover FOUR
of them!
📌 What You'll Learn:
✅ What Remote Sensing Indices are — and why they outperform raw band values
✅ NDWI (Water Index) — formula, physics, and PyQGIS code
✅ NDBI (Built-up Index) — how to detect cities from satellite imagery
✅ SAVI (Soil-Adjusted Vegetation Index) — fixing NDVI for sparse vegetation
✅ EVI (Enhanced Vegetation Index) — NASA's improvement for dense forests &
atmosphere
✅ When to use NDVI vs SAVI vs EVI — a clear decision guide
✅ Step-by-step Python code for NDWI, NDBI, and SAVI in PyQGIS
✅ Real-world applications: flood mapping, urban sprawl, drought, precision
agriculture
📊 Formulas Covered:- NDWI = (Green − NIR) / (Green + NIR) → Landsat Bands 3 & 5- NDBI = (SWIR − NIR) / (SWIR + NIR) → Landsat Bands 6 & 5- SAVI = [(NIR − Red) / (NIR + Red + L)] × (1 + L) → L = 0.5- EVI = 2.5 × (NIR − Red) / (NIR + 6×Red − 7.5×Blue + 1)
⏱ Timestamps:
00:00 – Introduction
00:45 – What Are Remote Sensing Indices?
02:30 – Categories of Indices
03:15 – NDWI: Water Index
05:00 – NDBI: Built-up Index
06:30 – SAVI: Soil-Adjusted Vegetation Index
08:15 – EVI: Enhanced Vegetation Index
10:00 – Calculating NDWI in PyQGIS
#NDWI #NDBI #SAVI #EVI #PyQGIS #RemoteSensing #SatelliteImagery #Landsat
#PythonGIS

Видео NDWI, NDBI, SAVI & EVI Explained + Calculated in PyQGIS | Remote Sensing Indices канала Learn Computer Science with Prof. Rashi