electricsheepafrica/african-loss-damage-quantification

---
title: African Loss & Damage Quantification Dataset
language: en
license: cc-by-4.0
task_categories:
- tabular-regression
- tabular-classification
- time-series-forecasting
pretty_name: African Loss and Damage Quantification
size_categories:
- 10K<n<100K
source_datasets:
- original
configs:
- config_name: low_emissions
data_files: african_loss_damage_low_emissions.csv
description: Low emissions scenario (SSP1-2.6 aligned). Assumes Paris Agreement targets met.
- config_name: current_policies
data_files: african_loss_damage_current_policies.csv
description: Current policies scenario (SSP2-4.5 aligned). Extrapolates existing national commitments.
- config_name: high_emissions
data_files: african_loss_damage_high_emissions.csv
description: High emissions scenario (SSP5-8.5 aligned). Business-as-usual trajectory.
- config_name: full
data_files: african_loss_damage_full.csv
description: Complete dataset combining all three emission scenarios.
---

# African Loss & Damage Quantification Dataset

## Overview

A comprehensive quantification of climate-related loss and damage across 25 African nations, spanning three emission scenarios (low_emissions, current_policies, high_emissions) and three time horizons (2030, 2040, 2050). This dataset is designed to support COP/UNFCCC negotiations, national adaptation planning, and climate finance allocation.

## Dataset Statistics

| Metric | Value |
|--------|-------|
| Total Records | 20,000+ |
| Countries | 25 |
| Regions | 5 (West, East, Southern, North, Central Africa) |
| Scenarios | 3 |
| Time Horizons | 2030, 2040, 2050 |
| Features | 45+ |

## Countries Covered

South Africa, Nigeria, Kenya, Egypt, Morocco, Ghana, Ethiopia, Tanzania, Uganda, Ivory Coast, Senegal, Mali, Burkina Faso, Niger, Zambia, Zimbabwe, Mozambique, Cameroon, Malawi, Rwanda, Somalia, Madagascar, DRC, Chad, South Sudan.

## Features

### Identifiers
- `record_id` - Unique record identifier
- `country` - Country name
- `region` - African region
- `income_level` - World Bank income classification (low, lower_middle, upper_middle)
- `scenario` - Emission scenario (low_emissions, current_policies, high_emissions)
- `year` - Projection year (2030, 2040, 2050)

### Macro
- `population` - Country population
- `gdp_usd` - GDP in USD
- `co2_per_capita_tonnes` - Per capita CO2 emissions

### Sector Losses (USD)
- `loss_agriculture_usd` - Crop and livestock losses
- `loss_infrastructure_usd` - Built environment damage
- `loss_health_usd` - Health system costs
- `loss_water_usd` - Water resource losses
- `loss_energy_usd` - Energy infrastructure damage
- `loss_tourism_usd` - Tourism sector losses
- `total_sector_loss_usd` - Sum of all sector losses

### Attribution
- `attribution_confidence` - Confidence level (0-1) in climate attribution
- `primary_climate_hazard` - Dominant climate hazard for the country
- `hazard_weight_*` - Relative weight of each hazard type (drought, flood, cyclone, heat, sea_level, wildfire, landslide)

### Insurance
- `insurance_coverage_gap` - Proportion of losses uninsured (0-1)
- `uninsured_loss_usd` - Total uninsured economic losses

### Displacement
- `displaced_people` - Number of climate-displaced persons
- `displacement_cost_per_person_usd` - Per-person displacement cost
- `total_displacement_cost_usd` - Total displacement costs

### Ecosystem
- `ecosystem_loss_pct_gdp` - Ecosystem service loss as % of GDP
- `ecosystem_loss_usd` - Ecosystem service loss in USD

### Cultural Heritage
- `cultural_heritage_damage_usd` - Damage to cultural heritage sites

### Adaptation
- `adaptation_gap` - Proportion of adaptation needs unmet (0-1)
- `adaptation_needed_usd` - Total adaptation funding needed
- `adaptation_received_usd` - Adaptation funding received
- `adaptation_shortfall_usd` - Adaptation funding gap

### Climate Finance
- `climate_finance_received_usd` - Climate finance received
- `climate_finance_needed_usd` - Climate finance needed
- `climate_finance_gap_usd` - Climate finance gap

### GDP Impact
- `gdp_impact_pct` - Total loss and damage as % of GDP

### Mortality
- `mortality_rate_per_100k` - Climate-related mortality rate
- `mortality_count` - Number of climate-related deaths
- `mortality_cost_usd` - Economic value of mortality (VSL-based)

### Totals
- `total_loss_damage_usd` - Aggregate loss and damage
- `total_loss_damage_pct_gdp` - Total L&D as % of GDP

## Scenarios

| Scenario | Alignment | Description |
|----------|-----------|-------------|
| `low_emissions` | SSP1-2.6 | Paris Agreement targets met; 1.5-2°C warming |
| `current_policies` | SSP2-4.5 | Existing NDCs and policies; ~2.7°C warming |
| `high_emissions` | SSP5-8.5 | Business-as-usual; 4°C+ warming |

## Methodology

Parameters are calibrated against peer-reviewed literature and institutional assessments:

- **Sector loss baselines**: IPCC AR6 WGII Chapter 9 (Africa), World Bank Country Climate and Development Reports
- **Temporal projection factors**: IPCC AR6 scenario multipliers for 2030/2040/2050
- **Regional risk multipliers**: ND-GAIN Country Index, INFORM Risk Index
- **Insurance gaps**: UNFCCC Loss and Damage, Munich Climate Insurance Initiative
- **Displacement**: IDMC Internal Displacement Monitoring Centre
- **Ecosystem losses**: IPBES Global Assessment, World Bank WAVES
- **Cultural heritage**: UNESCO Climate Heritage, ICOMOS
- **Adaptation gap**: UNEP Adaptation Gap Report 2023
- **Climate finance**: Climate Policy Initiative, ODI
- **Mortality**: WHO, EM-DAT, Lancet Countdown on Health and Climate Change
- **Value of statistical life**: World Bank guidelines

## File Structure

```
african-loss-damage-quantification/
├── african_loss_damage_full.csv # All records combined
├── african_loss_damage_low_emissions.csv # Low emissions scenario
├── african_loss_damage_current_policies.csv # Current policies scenario
├── african_loss_damage_high_emissions.csv # High emissions scenario
├── dataset_summary.json # Summary statistics
├── by_country/ # Per-country CSVs
│ ├── south_africa.csv
│ ├── nigeria.csv
│ └── ...
├── by_region/ # Per-region CSVs
│ ├── west_africa.csv
│ ├── east_africa.csv
│ └── ...
├── generate_dataset.py # Generation script
├── validate_dataset.py # Validation script
├── requirements.txt # Python dependencies
└── README.md # This file
```

## Usage

```python
import pandas as pd

# Load full dataset
df = pd.read_csv("african_loss_damage_full.csv")

# Load specific scenario
df_low = pd.read_csv("african_loss_damage_low_emissions.csv")

# Filter by country and scenario
sa_2050 = df[(df["country"] == "South Africa") & (df["year"] == 2050)]

# Aggregate by region
region_summary = df.groupby(["region", "scenario"])["total_loss_damage_usd"].mean()
```

## Citation

```
@dataset{african_loss_damage_2024,
title = {African Loss and Damage Quantification Dataset},
year = {2024},
publisher = {Hugging Face},
author = {Electric Sheep Africa},
url = {https://huggingface.co/datasets/electricsheepafrica/african-loss-damage-quantification}
}
```

## References

1. IPCC (2022). Climate Change 2022: Impacts, Adaptation and Vulnerability. Chapter 9: Africa.
2. UNFCCC (2022). Glasgow-Sharm el-Sheikh work programme on loss and damage.
3. COP27 (2022). Decision on funding arrangements for loss and damage.
4. COP28 (2023). Operationalization of the Loss and Damage Fund.
5. World Bank (2023). Country Climate and Development Reports (CCDRs).
6. Climate Action Tracker (2023). Africa assessments.
7. African Group of Negotiators position papers on Loss and Damage.
8. UNEP (2023). Adaptation Gap Report.
9. WHO (2023). Climate change and health country profiles.
10. IDMC (2023). Global Report on Internal Displacement.

## License

CC BY 4.0