asiaexperiments/Spatiotemporal-Analysis-of-Vegetation-Health-and-Climate-Variability

Spatiotemporal analysis of malnutrition and NDVI change in Somalia (2000–2020), using geospatial tools to explore the links between vegetation loss and food insecurity. # Spatiotemporal Analysis of Vegetation Health and Climate Variability in Somalia ## Project Overview ### This project explores the evolving relationship between vegetation health and climate variability in Somalia using spatiotemporal analysis and geospatial techniques. By examining trends in rainfall, temperature anomalies, and vegetation health (NDVI) from 2000 to 2020, we aim to identify regional disparities, environmental degradation patterns, and climate stress zones. This focused approach supports targeted insights for climate adaptation strategies and environmental risk planning. #### Research Questions 1.) How has vegetation health (measured by NDVI) changed regionally across Somalia from 2000 to 2020? 2.) How do changes in vegetation health (measured by NDVI) correspond with patterns of climate across regions and time? 3.) What spatial and temporal patterns emerge when comparing vegetation and climate variability? #### Objective 1.) Visualize the spatial and temporal distribution of NDVI, rainfall, and temperature anomalies across Somalia. 2.) Analyze regional climate and vegetation trends at 5-year intervals. 3.) Identify correlations between climate anomalies and changes in vegetation health. 4.) Generate maps and time series plots to support interpretation of spatiotemporal environmental risks. ### Data Sources This project integrates multiple datasets related to vegetation and climate variability: ##### NDVI (Vegetation Index): MODIS Vegetation Indices (MOD13Q1) #### Climate Data from: - NOAA Climate Data - FAO Climate & Agriculture Data - Dryad Climate Dataset ##### NDVI (Vegetation Index): - MODIS Vegetation Indices (MOD13Q1) ### Tools & Technologies This project leverages Python and GIS tools for data processing, mapping, and analysis: ##### Programming & Data Processing: - pandas, numpy, geopandas (for data handling) - matplotlib, seaborn, folium (for visualization) ##### Geospatial Analysis: - GeoPandas, Shapely, rasterio (for G …