Logo Lanfrica
  • Accueil
  • Atlas
  • Analyses
  • Documentation
  • Sign in

© 2026 Lanfrica. Tous droits réservés. Tous les droits d'auteur des ressources affichées sur le site Web Lanfrica appartiennent aux détenteurs de droits d'auteur d'origine, sauf indication contraire explicite.

joyceonyango/Conservation-Funding-in-Africa

Domaine:

environment and energygeospatial

Type de record:

dataset
Créateur:
joy
Hôte:
Analysis of Biodiversity & Funding Allocation # 🌍 Conservation Funding Optimization in Africa --- ## 📌 Project Overview This project analyzes biodiversity records, conservation funding data, and geospatial biodiversity intactness metrics across African countries to evaluate whether conservation funding is aligned with ecological value. Using Python-based data analysis and geospatial techniques, the project identifies funding inefficiencies and highlights under-supported biodiversity-rich regions. --- ## 🎯 Problem Statement Conservation funding across Africa is unevenly distributed. This project answers the following questions: - Are biodiversity-rich countries receiving adequate funding? - Does conservation funding align with biodiversity intactness? - Which countries should be prioritized for future funding allocation? --- ## 🗂️ Dataset Description The analysis integrates three primary datasets: ### 1️⃣ Biodiversity Dataset - 11 Excel sheets combined into one dataset - 1,930 species records after cleaning - Species categorized as **Plant** or **Mammal** - 53 African countries represented ### 2️⃣ Conservation Funding Dataset - Funding values in **Million USD** - 53 country-level records - Missing values handled - Negative outliers corrected ### 3️⃣ Biodiversity Intactness Index (BII) - Raster dataset - Country-level mean extracted using zonal statistics - CRS: WGS 1984 - Index range: `0.116 – 0.995` - Africa-wide mean: `0.756` --- ## 🛠️ Technical Approach ### Data Cleaning & Preparation - Merged 11 biodiversity sheets into one DataFrame - Removed duplicate species records - Standardized country names using fuzzy string matching (FuzzyWuzzy) - Handled: - Missing funding values - Negative funding outliers - Inconsistent naming (e.g., Ivory Coast → Côte d'Ivoire) - Merged datasets with African country shapefile - Renamed shapefile columns for consistency ### Feature Engineering Generated country-level metrics: - Species count - Species type count - Mean Biodiversity Intactness Index - Total con …

Visit

github.com