NigelMwangi/Land-cover-change-in-Kenya

# Land-cover-change-in-Kenya ## Overview Vegetation is a critical component of ecosystems, shaping biodiversity, climate regulation, and the livelihoods of millions of people. Monitoring vegetation health and change over time is essential for understanding environmental dynamics, managing natural resources, and supporting sustainable development. Kenya's diverse landscapes — from forests and savannahs to urban centers — face ongoing environmental pressures including deforestation, land degradation, and climate variability. Understanding the spatial and temporal patterns of vegetation change across the country is therefore essential for conservation planning, agricultural management, and land-use policy. This project applies spatial analysis techniques to Sentinel-2 satellite imagery via Google Earth Engine to calculate annual NDVI (Normalized Difference Vegetation Index) for Kenya between 2019 and 2024, identify regions of vegetation gain or loss, and aggregate results at the county level to reveal spatial patterns nationwide. ## Objectives - Compute annual NDVI for Kenya using Sentinel-2 Surface Reflectance imagery (2019–2024) - Quantify vegetation change by comparing 2019 (baseline) vs. 2024 (most recent) NDVI - Aggregate and compare vegetation trends at the county (administrative Level 1) scale - Visualize spatial patterns of vegetation gain and loss across Kenya - Provide insights to support conservation planning, land management, and policy-making ## Methodology Data acquisition — Filter Sentinel-2 imagery by Kenya's boundary, year, and cloud cover (< 20%) NDVI computation — Generate a median composite per year and calculate: NDVI = (NIR − Red) / (NIR + Red) Time-series aggregation — Compute annual NDVI for each year from 2019–2024 Change detection — Subtract 2019 NDVI from 2024 NDVI to produce a pixel-level change map Zonal statistics — Aggregate mean NDVI change per county using reduceRegion Visualization — Render change maps (red = loss, green = gain) …